Search

Your search keyword '"Gatti, Alice"' showing total 31 results
Start Over Author "Gatti, Alice"
31 results on '"Gatti, Alice"'

1. The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems

Author

Ren, Richard, Agarwal, Arunim, Mazeika, Mantas, Menghini, Cristina, Vacareanu, Robert, Kenstler, Brad, Yang, Mick, Barrass, Isabelle, Gatti, Alice, Yin, Xuwang, Trevino, Eduardo, Geralnik, Matias, Khoja, Adam, Lee, Dean, Yue, Summer, and Hendrycks, Dan

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Computers and Society
Abstract

As large language models (LLMs) become more capable and agentic, the requirement for trust in their outputs grows significantly, yet at the same time concerns have been mounting that models may learn to lie in pursuit of their goals. To address these concerns, a body of work has emerged around the notion of "honesty" in LLMs, along with interventions aimed at mitigating deceptive behaviors. However, evaluations of honesty are currently highly limited, with no benchmark combining large scale and applicability to all models. Moreover, many benchmarks claiming to measure honesty in fact simply measure accuracy--the correctness of a model's beliefs--in disguise. In this work, we introduce a large-scale human-collected dataset for measuring honesty directly, allowing us to disentangle accuracy from honesty for the first time. Across a diverse set of LLMs, we find that while larger models obtain higher accuracy on our benchmark, they do not become more honest. Surprisingly, while most frontier LLMs obtain high scores on truthfulness benchmarks, we find a substantial propensity in frontier LLMs to lie when pressured to do so, resulting in low honesty scores on our benchmark. We find that simple methods, such as representation engineering interventions, can improve honesty. These results underscore the growing need for robust evaluations and effective interventions to ensure LLMs remain trustworthy., Comment: Website: https://www.mask-benchmark.ai

Published
2025

2. Humanity's Last Exam

Author

Phan, Long, Gatti, Alice, Han, Ziwen, Li, Nathaniel, Hu, Josephina, Zhang, Hugh, Zhang, Chen Bo Calvin, Shaaban, Mohamed, Ling, John, Shi, Sean, Choi, Michael, Agrawal, Anish, Chopra, Arnav, Khoja, Adam, Kim, Ryan, Ren, Richard, Hausenloy, Jason, Zhang, Oliver, Mazeika, Mantas, Nguyen, Tung, Anderson, Daron, Shah, Imad Ali, Doroshenko, Mikhail, Stokes, Alun Cennyth, Mahmood, Mobeen, Lee, Jaeho, Pokutnyi, Oleksandr, Iskra, Oleg, Wang, Jessica P., Gerbicz, Robert, Levin, John-Clark, Popov, Serguei, Feng, Fiona, Feng, Steven Y., Zhao, Haoran, Yu, Michael, Gangal, Varun, Zou, Chelsea, Wang, Zihan, Kazakov, Mstyslav, Galgon, Geoff, Schmitt, Johannes, Sanchez, Alvaro, Lee, Yongki, Yeadon, Will, Sauers, Scott, Roth, Marc, Agu, Chidozie, Riis, Søren, Giska, Fabian, Utpala, Saiteja, Cheatom, Antrell, Giboney, Zachary, Goshu, Gashaw M., Crowson, Sarah-Jane, Naiya, Mohinder Maheshbhai, Burns, Noah, Finke, Lennart, Cheng, Zerui, Park, Hyunwoo, Fournier-Facio, Francesco, Zampese, Jennifer, Wydallis, John B., Hoerr, Ryan G., Nandor, Mark, Gehrunger, Tim, Cai, Jiaqi, McCarty, Ben, Nam, Jungbae, Taylor, Edwin, Jin, Jun, Loume, Gautier Abou, Cao, Hangrui, Garretson, Alexis C, Sileo, Damien, Ren, Qiuyu, Cojoc, Doru, Arkhipov, Pavel, Qazi, Usman, Bacho, Aras, Li, Lianghui, Motwani, Sumeet, de Witt, Christian Schroeder, Kopylov, Alexei, Veith, Johannes, Singer, Eric, Rissone, Paolo, Jin, Jaehyeok, Shi, Jack Wei Lun, Willcocks, Chris G., Prabhu, Ameya, Tang, Longke, Zhou, Kevin, Santos, Emily de Oliveira, Maksimov, Andrey Pupasov, Vendrow, Edward, Zenitani, Kengo, Robinson, Joshua, Mikov, Aleksandar, Guillod, Julien, Li, Yuqi, Pageler, Ben, Vendrow, Joshua, Kuchkin, Vladyslav, Marion, Pierre, Efremov, Denis, Lynch, Jayson, Liang, Kaiqu, Gritsevskiy, Andrew, Martinez, Dakotah, Crispino, Nick, Zvonkine, Dimitri, Fraga, Natanael Wildner, Soori, Saeed, Press, Ori, Tang, Henry, Salazar, Julian, Green, Sean R., Brüssel, Lina, Twayana, Moon, Dieuleveut, Aymeric, Rogers, T. Ryan, Zhang, Wenjin, Finocchio, Ross, Li, Bikun, Yang, Jinzhou, Rao, Arun, Loiseau, Gabriel, Kalinin, Mikhail, Lukas, Marco, Manolescu, Ciprian, Stambaugh, Nate, Mishra, Subrata, Kamdoum, Ariel Ghislain Kemogne, Hogg, Tad, Jin, Alvin, Bosio, Carlo, Sun, Gongbo, Coppola, Brian P, Heidinger, Haline, Sayous, Rafael, Ivanov, Stefan, Cavanagh, Joseph M, Shen, Jiawei, Imperial, Joseph Marvin, Schwaller, Philippe, Senthilkuma, Shaipranesh, Bran, Andres M, Algaba, Andres, Verbeken, Brecht, Houte, Kelsey Van den, Van Der Sypt, Lynn, Noever, David, Schut, Lisa, Sucholutsky, Ilia, Zheltonozhskii, Evgenii, Yuan, Qiaochu, Lim, Derek, Stanley, Richard, Sivarajan, Shankar, Yang, Tong, Maar, John, Wykowski, Julian, Oller, Martí, Sandlin, Jennifer, Sahu, Anmol, Ardito, Cesare Giulio, Hu, Yuzheng, Dias, Felipe Meneguitti, Kreiman, Tobias, Rawal, Kaivalya, Vilchis, Tobias Garcia, Zu, Yuexuan, Lackner, Martin, Koppel, James, Nguyen, Jeremy, Antonenko, Daniil S., Chern, Steffi, Zhao, Bingchen, Arsene, Pierrot, Ivanov, Sergey, Poświata, Rafał, Wang, Chenguang, Li, Daofeng, Crisostomi, Donato, Dehghan, Ali, Achilleos, Andrea, Ambay, John Arnold, Myklebust, Benjamin, Sen, Archan, Perrella, David, Kaparov, Nurdin, Inlow, Mark H, Zang, Allen, Ramakrishnan, Kalyan, Orel, Daniil, Poritski, Vladislav, Ben-David, Shalev, Berger, Zachary, Whitfill, Parker, Foster, Michael, Munro, Daniel, Ho, Linh, Hava, Dan Bar, Kuchkin, Aleksey, Lauff, Robert, Holmes, David, Sommerhage, Frank, Zhang, Anji, Moat, Richard, Schneider, Keith, Pyda, Daniel, Kazibwe, Zakayo, Singh, Mukhwinder, Clarke, Don, Kim, Dae Hyun, Fish, Sara, Elser, Veit, Vilchis, Victor Efren Guadarrama, Klose, Immo, Demian, Christoph, Anantheswaran, Ujjwala, Zweiger, Adam, Albani, Guglielmo, Li, Jeffery, Daans, Nicolas, Radionov, Maksim, Rozhoň, Václav, Ginis, Vincent, Ma, Ziqiao, Stump, Christian, Platnick, Jacob, Nevirkovets, Volodymyr, Basler, Luke, Piccardo, Marco, Cohen, Niv, Singh, Virendra, Tkadlec, Josef, Rosu, Paul, Goldfarb, Alan, Padlewski, Piotr, Barzowski, Stanislaw, Montgomery, Kyle, Menezes, Aline, Patel, Arkil, Wang, Zixuan, Tucker-Foltz, Jamie, Stade, Jack, Grabb, Declan, Goertzen, Tom, Kazemi, Fereshteh, Milbauer, Jeremiah, Shukla, Abhishek, Elgnainy, Hossam, Labrador, Yan Carlos Leyva, He, Hao, Zhang, Ling, Givré, Alan, Wolff, Hew, Demir, Gözdenur, Aziz, Muhammad Fayez, Kaddar, Younesse, Ängquist, Ivar, Chen, Yanxu, Thornley, Elliott, Zhang, Robin, Pan, Jiayi, Terpin, Antonio, Muennighoff, Niklas, Schoelkopf, Hailey, Zheng, Eric, Carmi, Avishy, Shah, Jainam, Brown, Ethan D. L., Zhu, Kelin, Bartolo, Max, Wheeler, Richard, Ho, Andrew, Barkan, Shaul, Wang, Jiaqi, Stehberger, Martin, Kretov, Egor, Bradshaw, Peter, Heimonen, JP, Sridhar, Kaustubh, Hossain, Zaki, Akov, Ido, Makarychev, Yury, Tam, Joanna, Hoang, Hieu, Cunningham, David M., Goryachev, Vladimir, Patramanis, Demosthenes, Krause, Michael, Redenti, Andrew, Aldous, David, Lai, Jesyin, Coleman, Shannon, Xu, Jiangnan, Lee, Sangwon, Magoulas, Ilias, Zhao, Sandy, Tang, Ning, Cohen, Michael K., Carroll, Micah, Paradise, Orr, Kirchner, Jan Hendrik, Steinerberger, Stefan, Ovchynnikov, Maksym, Matos, Jason O., Shenoy, Adithya, Wang, Michael, Nie, Yuzhou, Giordano, Paolo, Petersen, Philipp, Sztyber-Betley, Anna, Faraboschi, Paolo, Riblet, Robin, Crozier, Jonathan, Halasyamani, Shiv, Pinto, Antonella, Verma, Shreyas, Joshi, Prashant, Meril, Eli, Yong, Zheng-Xin, Tee, Allison, Andréoletti, Jérémy, Weller, Orion, Singhal, Raghav, Zhang, Gang, Ivanov, Alexander, Khoury, Seri, Gustafsson, Nils, Mostaghimi, Hamid, Thaman, Kunvar, Chen, Qijia, Khánh, Tran Quoc, Loader, Jacob, Cavalleri, Stefano, Szlyk, Hannah, Brown, Zachary, Narayan, Himanshu, Roberts, Jonathan, Alley, William, Sun, Kunyang, Stendall, Ryan, Lamparth, Max, Reuel, Anka, Wang, Ting, Xu, Hanmeng, Hernández-Cámara, Pablo, Martin, Freddie, Preu, Thomas, Korbak, Tomek, Abramovitch, Marcus, Williamson, Dominic, Bosio, Ida, Chen, Ziye, Bálint, Biró, Lo, Eve J. Y., Nunes, Maria Inês S., Jiang, Yibo, Bari, M Saiful, Kassani, Peyman, Wang, Zihao, Ansarinejad, Behzad, Sun, Yewen, Durand, Stephane, Douville, Guillaume, Tordera, Daniel, Balabanian, George, Anderson, Earth, Kvistad, Lynna, Moyano, Alejandro José, Milliron, Hsiaoyun, Sakor, Ahmad, Eron, Murat, McAlister, Isaac C., O., Andrew Favre D., Shah, Shailesh, Zhou, Xiaoxiang, Kamalov, Firuz, Clark, Ronald, Abdoli, Sherwin, Santens, Tim, Wang, Harrison K, Chen, Evan, Tomasiello, Alessandro, De Luca, G. Bruno, Looi, Shi-Zhuo, Le, Vinh-Kha, Kolt, Noam, Mündler, Niels, Semler, Avi, Rodman, Emma, Drori, Jacob, Fossum, Carl J, Gloor, Luk, Jagota, Milind, Pradeep, Ronak, Fan, Honglu, Shah, Tej, Eicher, Jonathan, Chen, Michael, Thaman, Kushal, Merrill, William, Firsching, Moritz, Harris, Carter, Ciobâcă, Stefan, Gross, Jason, Pandey, Rohan, Gusev, Ilya, Jones, Adam, Agnihotri, Shashank, Zhelnov, Pavel, Usawasutsakorn, Siranut, Mofayezi, Mohammadreza, Piperski, Alexander, Carauleanu, Marc, Zhang, David K., Dobarskyi, Kostiantyn, Ler, Dylan, Leventov, Roman, Soroko, Ignat, Jansen, Thorben, Creighton, Scott, Lauer, Pascal, Duersch, Joshua, Taamazyan, Vage, Bezzi, Dario, Morak, Wiktor, Ma, Wenjie, Held, William, Huy, Tran Đuc, Xian, Ruicheng, Zebaze, Armel Randy, Mohamed, Mohanad, Leser, Julian Noah, Yuan, Michelle X, Yacar, Laila, Lengler, Johannes, Olszewska, Katarzyna, Shahrtash, Hossein, Oliveira, Edson, Jackson, Joseph W., Gonzalez, Daniel Espinosa, Zou, Andy, Chidambaram, Muthu, Manik, Timothy, Haffenden, Hector, Stander, Dashiell, Dasouqi, Ali, Shen, Alexander, Duc, Emilien, Golshani, Bita, Stap, David, Uzhou, Mikalai, Zhidkovskaya, Alina Borisovna, Lewark, Lukas, Rodriguez, Miguel Orbegozo, Vincze, Mátyás, Wehr, Dustin, Tang, Colin, Phillips, Shaun, Samuele, Fortuna, Muzhen, Jiang, Ekström, Fredrik, Hammon, Angela, Patel, Oam, Farhidi, Faraz, Medley, George, Mohammadzadeh, Forough, Peñaflor, Madellene, Kassahun, Haile, Friedrich, Alena, Sparrow, Claire, Perez, Rayner Hernandez, Sakal, Taom, Dhamane, Omkar, Mirabadi, Ali Khajegili, Hallman, Eric, Okutsu, Kenchi, Battaglia, Mike, Maghsoudimehrabani, Mohammad, Amit, Alon, Hulbert, Dave, Pereira, Roberto, Weber, Simon, Handoko, Peristyy, Anton, Malina, Stephen, Albanie, Samuel, Cai, Will, Mehkary, Mustafa, Aly, Rami, Reidegeld, Frank, Dick, Anna-Katharina, Friday, Cary, Sidhu, Jasdeep, Shapourian, Hassan, Kim, Wanyoung, Costa, Mariana, Gurdogan, Hubeyb, Weber, Brian, Kumar, Harsh, Jiang, Tong, Agarwal, Arunim, Ceconello, Chiara, Vaz, Warren S., Zhuang, Chao, Park, Haon, Tawfeek, Andrew R., Aggarwal, Daattavya, Kirchhof, Michael, Dai, Linjie, Kim, Evan, Ferret, Johan, Wang, Yuzhou, Yan, Minghao, Burdzy, Krzysztof, Zhang, Lixin, Franca, Antonio, Pham, Diana T., Loh, Kang Yong, Jackson, Abram, Gul, Shreen, Chhablani, Gunjan, Du, Zhehang, Cosma, Adrian, Colino, Jesus, White, Colin, Votava, Jacob, Vinnikov, Vladimir, Delaney, Ethan, Spelda, Petr, Stritecky, Vit, Shahid, Syed M., Mourrat, Jean-Christophe, Vetoshkin, Lavr, Sponselee, Koen, Bacho, Renas, de la Rosa, Florencia, Li, Xiuyu, Malod, Guillaume, Lang, Leon, Laurendeau, Julien, Kazakov, Dmitry, Adesanya, Fatimah, Portier, Julien, Hollom, Lawrence, Souza, Victor, Zhou, Yuchen Anna, Degorre, Julien, Yalın, Yiğit, Obikoya, Gbenga Daniel, Arnaboldi, Luca, Rai, Bigi, Filippo, Boscá, M. C., Shumar, Oleg, Bacho, Kaniuar, Clavier, Pierre, Recchia, Gabriel, Popescu, Mara, Shulga, Nikita, Tanwie, Ngefor Mildred, Peskoff, Denis, Lux, Thomas C. H., Rank, Ben, Ni, Colin, Brooks, Matthew, Yakimchyk, Alesia, Huanxu, Liu, Häggström, Olle, Verkama, Emil, Gundlach, Hans, Brito-Santana, Leonor, Amaro, Brian, Vajipey, Vivek, Grover, Rynaa, Fan, Yiyang, Silva, Gabriel Poesia Reis e, Xin, Linwei, Kratish, Yosi, Łucki, Jakub, Li, Wen-Ding, Gopi, Sivakanth, Caciolai, Andrea, Xu, Justin, Scaria, Kevin Joseph, Vargus, Freddie, Habibi, Farzad, Long, Lian, Rodolà, Emanuele, Robins, Jules, Cheng, Vincent, Fruhauff, Tony, Raynor, Brad, Qi, Hao, Jiang, Xi, Segev, Ben, Fan, Jingxuan, Martinson, Sarah, Wang, Erik Y., Hausknecht, Kaylie, Brenner, Michael P., Mao, Mao, Zhang, Xinyu, Avagian, David, Scipio, Eshawn Jessica, Ragoler, Alon, Tan, Justin, Sims, Blake, Plecnik, Rebeka, Kirtland, Aaron, Bodur, Omer Faruk, Shinde, D. P., Adoul, Zahra, Zekry, Mohamed, Karakoc, Ali, Santos, Tania C. B., Shamseldeen, Samir, Karim, Loukmane, Liakhovitskaia, Anna, Resman, Nate, Farina, Nicholas, Gonzalez, Juan Carlos, Maayan, Gabe, Hoback, Sarah, Pena, Rodrigo De Oliveira, Sherman, Glen, Kelley, Elizabeth, Mariji, Hodjat, Pouriamanesh, Rasoul, Wu, Wentao, Mendoza, Sandra, Alarab, Ismail, Cole, Joshua, Ferreira, Danyelle, Johnson, Bryan, Safdari, Mohammad, Dai, Liangti, Arthornthurasuk, Siriphan, Pronin, Alexey, Fan, Jing, Ramirez-Trinidad, Angel, Cartwright, Ashley, Pottmaier, Daphiny, Taheri, Omid, Outevsky, David, Stepanic, Stanley, Perry, Samuel, Askew, Luke, Rodríguez, Raúl Adrián Huerta, Minissi, Ali M. R., Ali, Sam, Lorena, Ricardo, Iyer, Krishnamurthy, Fasiludeen, Arshad Anil, Salauddin, Sk Md, Islam, Murat, Gonzalez, Juan, Ducey, Josh, Somrak, Maja, Mavroudis, Vasilios, Vergo, Eric, Qin, Juehang, Borbás, Benjámin, Chu, Eric, Lindsey, Jack, Radhakrishnan, Anil, Jallon, Antoine, McInnis, I. M. J., Kumar, Pawan, Goswami, Laxman Prasad, Bugas, Daniel, Heydari, Nasser, Jeanplong, Ferenc, Apronti, Archimedes, Galal, Abdallah, Ze-An, Ng, Singh, Ankit, Xavier, Joan of Arc, Agarwal, Kanu Priya, Berkani, Mohammed, Junior, Benedito Alves de Oliveira, Malishev, Dmitry, Remy, Nicolas, Hartman, Taylor D., Tarver, Tim, Mensah, Stephen, Gimenez, Javier, Montecillo, Roselynn Grace, Campbell, Russell, Sharma, Asankhaya, Meer, Khalida, Alapont, Xavier, Patil, Deepakkumar, Maheshwari, Rajat, Dendane, Abdelkader, Shukla, Priti, Bogdanov, Sergei, Möller, Sören, Siddiqi, Muhammad Rehan, Saxena, Prajvi, Gupta, Himanshu, Enyekwe, Innocent, P V, Ragavendran, EL-Wasif, Zienab, Maksapetyan, Aleksandr, Rossbach, Vivien, Harjadi, Chris, Bahaloohoreh, Mohsen, Bian, Song, Lai, John, Uro, Justine Leon, Bateman, Greg, Sayed, Mohamed, Menshawy, Ahmed, Duclosel, Darling, Jain, Yashaswini, Aaron, Ashley, Tiryakioglu, Murat, Siddh, Sheeshram, Krenek, Keith, Hoover, Alex, McGowan, Joseph, Patwardhan, Tejal, Yue, Summer, Wang, Alexandr, and Hendrycks, Dan

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computation and Language
Abstract

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of human knowledge, designed to be the final closed-ended academic benchmark of its kind with broad subject coverage. HLE consists of 2,700 questions across dozens of subjects, including mathematics, humanities, and the natural sciences. HLE is developed globally by subject-matter experts and consists of multiple-choice and short-answer questions suitable for automated grading. Each question has a known solution that is unambiguous and easily verifiable, but cannot be quickly answered via internet retrieval. State-of-the-art LLMs demonstrate low accuracy and calibration on HLE, highlighting a significant gap between current LLM capabilities and the expert human frontier on closed-ended academic questions. To inform research and policymaking upon a clear understanding of model capabilities, we publicly release HLE at https://lastexam.ai., Comment: 27 pages, 6 figures

Published
2025

3. Tamper-Resistant Safeguards for Open-Weight LLMs

Author

Tamirisa, Rishub, Bharathi, Bhrugu, Phan, Long, Zhou, Andy, Gatti, Alice, Suresh, Tarun, Lin, Maxwell, Wang, Justin, Wang, Rowan, Arel, Ron, Zou, Andy, Song, Dawn, Li, Bo, Hendrycks, Dan, and Mazeika, Mantas

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computation and Language
Abstract

Rapid advances in the capabilities of large language models (LLMs) have raised widespread concerns regarding their potential for malicious use. Open-weight LLMs present unique challenges, as existing safeguards lack robustness to tampering attacks that modify model weights. For example, recent works have demonstrated that refusal and unlearning safeguards can be trivially removed with a few steps of fine-tuning. These vulnerabilities necessitate new approaches for enabling the safe release of open-weight LLMs. We develop a method, called TAR, for building tamper-resistant safeguards into open-weight LLMs such that adversaries cannot remove the safeguards even after hundreds of steps of fine-tuning. In extensive evaluations and red teaming analyses, we find that our method greatly improves tamper-resistance while preserving benign capabilities. Our results demonstrate that progress on tamper-resistance is possible, opening up a promising new avenue to improve the safety and security of open-weight LLMs., Comment: Website: https://www.tamper-resistant-safeguards.com

Published
2024

4. Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?

Author

Ren, Richard, Basart, Steven, Khoja, Adam, Gatti, Alice, Phan, Long, Yin, Xuwang, Mazeika, Mantas, Pan, Alexander, Mukobi, Gabriel, Kim, Ryan H., Fitz, Stephen, and Hendrycks, Dan

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Computers and Society
Abstract

As artificial intelligence systems grow more powerful, there has been increasing interest in "AI safety" research to address emerging and future risks. However, the field of AI safety remains poorly defined and inconsistently measured, leading to confusion about how researchers can contribute. This lack of clarity is compounded by the unclear relationship between AI safety benchmarks and upstream general capabilities (e.g., general knowledge and reasoning). To address these issues, we conduct a comprehensive meta-analysis of AI safety benchmarks, empirically analyzing their correlation with general capabilities across dozens of models and providing a survey of existing directions in AI safety. Our findings reveal that many safety benchmarks highly correlate with both upstream model capabilities and training compute, potentially enabling "safetywashing"--where capability improvements are misrepresented as safety advancements. Based on these findings, we propose an empirical foundation for developing more meaningful safety metrics and define AI safety in a machine learning research context as a set of clearly delineated research goals that are empirically separable from generic capabilities advancements. In doing so, we aim to provide a more rigorous framework for AI safety research, advancing the science of safety evaluations and clarifying the path towards measurable progress., Comment: NeurIPS 2024

Published
2024

5. Performance Evaluation of Smart Bin Systems Using Markovian Agents for Efficient Garbage Collection

Author

Barbierato, Enrico, Gatti, Alice, Gribaudo, Marco, Iacono, Mauro, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Doncel, Josu, editor, Remke, Anne, editor, and Di Pompeo, Daniele, editor

Published
2025
Full Text
View/download PDF

6. The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

Author

Li, Nathaniel, Pan, Alexander, Gopal, Anjali, Yue, Summer, Berrios, Daniel, Gatti, Alice, Li, Justin D., Dombrowski, Ann-Kathrin, Goel, Shashwat, Phan, Long, Mukobi, Gabriel, Helm-Burger, Nathan, Lababidi, Rassin, Justen, Lennart, Liu, Andrew B., Chen, Michael, Barrass, Isabelle, Zhang, Oliver, Zhu, Xiaoyuan, Tamirisa, Rishub, Bharathi, Bhrugu, Khoja, Adam, Zhao, Zhenqi, Herbert-Voss, Ariel, Breuer, Cort B., Marks, Samuel, Patel, Oam, Zou, Andy, Mazeika, Mantas, Wang, Zifan, Oswal, Palash, Lin, Weiran, Hunt, Adam A., Tienken-Harder, Justin, Shih, Kevin Y., Talley, Kemper, Guan, John, Kaplan, Russell, Steneker, Ian, Campbell, David, Jokubaitis, Brad, Levinson, Alex, Wang, Jean, Qian, William, Karmakar, Kallol Krishna, Basart, Steven, Fitz, Stephen, Levine, Mindy, Kumaraguru, Ponnurangam, Tupakula, Uday, Varadharajan, Vijay, Wang, Ruoyu, Shoshitaishvili, Yan, Ba, Jimmy, Esvelt, Kevin M., Wang, Alexandr, and Hendrycks, Dan

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Computers and Society
Abstract

The White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing biological, cyber, and chemical weapons. To measure these risks of malicious use, government institutions and major AI labs are developing evaluations for hazardous capabilities in LLMs. However, current evaluations are private, preventing further research into mitigating risk. Furthermore, they focus on only a few, highly specific pathways for malicious use. To fill these gaps, we publicly release the Weapons of Mass Destruction Proxy (WMDP) benchmark, a dataset of 3,668 multiple-choice questions that serve as a proxy measurement of hazardous knowledge in biosecurity, cybersecurity, and chemical security. WMDP was developed by a consortium of academics and technical consultants, and was stringently filtered to eliminate sensitive information prior to public release. WMDP serves two roles: first, as an evaluation for hazardous knowledge in LLMs, and second, as a benchmark for unlearning methods to remove such hazardous knowledge. To guide progress on unlearning, we develop RMU, a state-of-the-art unlearning method based on controlling model representations. RMU reduces model performance on WMDP while maintaining general capabilities in areas such as biology and computer science, suggesting that unlearning may be a concrete path towards reducing malicious use from LLMs. We release our benchmark and code publicly at https://wmdp.ai, Comment: See the project page at https://wmdp.ai

Published
2024

7. Improving Energy Conserving Descent for Machine Learning: Theory and Practice

Author

De Luca, G. Bruno, Gatti, Alice, and Silverstein, Eva

Subjects
Computer Science - Machine Learning, Astrophysics - Instrumentation and Methods for Astrophysics, High Energy Physics - Theory, Mathematics - Optimization and Control, Statistics - Machine Learning
Abstract

We develop the theory of Energy Conserving Descent (ECD) and introduce ECDSep, a gradient-based optimization algorithm able to tackle convex and non-convex optimization problems. The method is based on the novel ECD framework of optimization as physical evolution of a suitable chaotic energy-conserving dynamical system, enabling analytic control of the distribution of results - dominated at low loss - even for generic high-dimensional problems with no symmetries. Compared to previous realizations of this idea, we exploit the theoretical control to improve both the dynamics and chaos-inducing elements, enhancing performance while simplifying the hyper-parameter tuning of the optimization algorithm targeted to different classes of problems. We empirically compare with popular optimization methods such as SGD, Adam and AdamW on a wide range of machine learning problems, finding competitive or improved performance compared to the best among them on each task. We identify limitations in our analysis pointing to possibilities for additional improvements., Comment: 15 pages + appendices, full code available

Published
2023

8. Combinatorics of Vogan diagrams for almost-K\'ahler manifolds

Author

Gatti, Alice

Subjects
Mathematics - Combinatorics, Mathematics - Differential Geometry, Mathematics - Symplectic Geometry
Abstract

Let $G$ be a non-compact classical semisimple Lie group and let $G/V$ be the adjoint orbit with respect to a fixed element in $G$. These manifolds can be equipped with an almost-K\"ahler structure and we provide explicit formulae for the existence of special almost-complex structures on $G/V$ purely in terms of the combinatorics of the associated Vogan diagram. The formulae are given separately for Lie groups whose Lie algebras are of type $A_{\ell}$, $B_{\ell}$, $C_{\ell}$, $D_{\ell}$, where $\ell$ denotes the rank of the Lie algebra., Comment: 28 pages

Published
2022

9. Deep Learning and Spectral Embedding for Graph Partitioning

Author

Gatti, Alice, Hu, Zhixiong, Smidt, Tess, Ng, Esmond G., and Ghysels, Pieter

Subjects
Computer Science - Machine Learning
Abstract

We present a graph bisection and partitioning algorithm based on graph neural networks. For each node in the graph, the network outputs probabilities for each of the partitions. The graph neural network consists of two modules: an embedding phase and a partitioning phase. The embedding phase is trained first by minimizing a loss function inspired by spectral graph theory. The partitioning module is trained through a loss function that corresponds to the expected value of the normalized cut. Both parts of the neural network rely on SAGE convolutional layers and graph coarsening using heavy edge matching. The multilevel structure of the neural network is inspired by the multigrid algorithm. Our approach generalizes very well to bigger graphs and has partition quality comparable to METIS, Scotch and spectral partitioning, with shorter runtime compared to METIS and spectral partitioning.

Published
2021

10. Graph Partitioning and Sparse Matrix Ordering using Reinforcement Learning and Graph Neural Networks

Author

Gatti, Alice, Hu, Zhixiong, Smidt, Tess, Ng, Esmond G., and Ghysels, Pieter

Subjects
Computer Science - Machine Learning
Abstract

We present a novel method for graph partitioning, based on reinforcement learning and graph convolutional neural networks. Our approach is to recursively partition coarser representations of a given graph. The neural network is implemented using SAGE graph convolution layers, and trained using an advantage actor critic (A2C) agent. We present two variants, one for finding an edge separator that minimizes the normalized cut or quotient cut, and one that finds a small vertex separator. The vertex separators are then used to construct a nested dissection ordering to permute a sparse matrix so that its triangular factorization will incur less fill-in. The partitioning quality is compared with partitions obtained using METIS and SCOTCH, and the nested dissection ordering is evaluated in the sparse solver SuperLU. Our results show that the proposed method achieves similar partitioning quality as METIS and SCOTCH. Furthermore, the method generalizes across different classes of graphs, and works well on a variety of graphs from the SuiteSparse sparse matrix collection.

Published
2021

12. Almost Kaehler geometry of adjoint orbits of semisimple Lie groups

Author

Della Vedova, Alberto and Gatti, Alice

Subjects
Mathematics - Differential Geometry, Mathematics - Symplectic Geometry, 53D05, 53C25 (Primary), 53C30, 22E46 (Secondary)
Abstract

We study the almost Kaehler geometry of adjoint orbits of non-compact real semisimple Lie groups endowed with the Kirillov-Kostant-Souriau symplectic form and a canonically defined almost complex structure. We give explicit formulas for the Chern-Ricci form, the Hermitian scalar curvature and the Nijenhuis tensor in terms of root data. We also discuss when the Chern-Ricci form is a multiple of the symplectic form, and when compact quotients of these orbits are of Kaehler type., Comment: 42 pages. Exposition improved. Appendix enhanced with more tables and more data. Many typos fixed

Published
2018

14. Robust Synthetic Data Generation for Sequential Financial Models Using Hybrid Variational Autoencoder–Markov Chain Monte Carlo Architectures.

Author

Bruni Prenestino, Francesco, Barbierato, Enrico, and Gatti, Alice

Subjects
MARKOV chain Monte Carlo, GENERATIVE adversarial networks, DATA privacy, TIME series analysis, MACHINE learning
Abstract

Generating high-quality synthetic data is essential for advancing machine learning applications in financial time series, where data scarcity and privacy concerns often pose significant challenges. This study proposes a novel hybrid architecture that combines variational autoencoders (VAEs) with Markov Chain Monte Carlo (MCMC) sampling to enhance the generation of robust synthetic sequential data. The model leverages Gated Recurrent Unit (GRU) layers for capturing long-term temporal dependencies and MCMC sampling for effective latent space exploration, ensuring high variability and accuracy. Experimental evaluations on datasets of Google, Tesla, and Nestlé stock prices demonstrate the model's superior performance in preserving statistical and temporal patterns, as validated by quantitative metrics (discriminative and predictive scores), statistical tests (Kolmogorov–Smirnov), and t-Distributed Stochastic Neighbour Embedding (t-SNE) visualisations. The experiments reveal the model's scalability, maintaining high fidelity even under augmented dataset sizes and missing data scenarios. These findings position the proposed framework as a computationally efficient and structurally simple alternative to Generative Adversarial Network (GAN)-based methods, suitable for real-world applications in data-driven financial modelling. [ABSTRACT FROM AUTHOR]

Published
2025
Full Text
View/download PDF

16. Decoding Urban Intelligence: Clustering and Feature Importance in Smart Cities.

Author

Barbierato, Enrico and Gatti, Alice

Subjects
CITIES & towns, SMART cities, STANDARD of living, SUPPORT vector machines, SUPERVISED learning
Abstract

The rapid urbanization trend underscores the need for effective management of city resources and services, making the concept of smart cities increasingly important. This study leverages the IMD Smart City Index (SCI) dataset to analyze and rank smart cities worldwide. Our research has a dual objective: first, we aim to apply a set of unsupervised learning models to cluster cities based on their smartness indices. Second, we aim to employ supervised learning models such as random forest, support vector machines (SVMs), and others to determine the importance of various features that contribute to a city's smartness. Our findings reveal that while smart living was the most critical factor, with an importance of 0.259014. Smart mobility and smart environment also played significant roles, with the importance of 0.170147 and 0.163159, respectively, in determining a city's smartness. While the clustering provides insights into the similarities and groupings among cities, the feature importance analysis elucidates the critical factors that drive these classifications. The integration of these two approaches aims to demonstrate that understanding the similarities between smart cities is of limited utility without a clear comprehension of the importance of the underlying features. This holistic approach provides a comprehensive understanding of what makes a city 'smart' and offers a robust framework for policymakers to enhance urban living standards. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

20. Balancing the Scale: Data Augmentation Techniques for Improved Supervised Learning in Cyberattack Detection.

Author

Medvedieva, Kateryna, Tosi, Tommaso, Barbierato, Enrico, and Gatti, Alice

Subjects
SUPERVISED learning, DATA augmentation, SKEWNESS (Probability theory), RANDOM forest algorithms, CYBERTERRORISM
Abstract

The increasing sophistication of cyberattacks necessitates the development of advanced detection systems capable of accurately identifying and mitigating potential threats. This research addresses the critical challenge of cyberattack detection by employing a comprehensive approach that includes generating a realistic yet imbalanced dataset simulating various types of cyberattacks. Recognizing the inherent limitations posed by imbalanced data, we explored multiple data augmentation techniques to enhance the model's learning effectiveness and ensure robust performance across different attack scenarios. Firstly, we constructed a detailed dataset reflecting real-world conditions of network intrusions by simulating a range of cyberattack types, ensuring it embodies the typical imbalances observed in genuine cybersecurity threats. Subsequently, we applied several data augmentation techniques, including SMOTE and ADASYN, to address the skew in class distribution, thereby providing a more balanced dataset for training supervised machine learning models. Our evaluation of these techniques across various models, such as Random Forests and Neural Networks, demonstrates significant improvements in detection capabilities. Moreover, the analysis also extends to the investigation of feature importance, providing critical insights into which attributes most significantly influence the predictive outcomes of the models. This not only enhances the interpretability of the models but also aids in refining feature engineering and selection processes to optimize performance. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

21. Enhancing Financial Time Series Prediction with Quantum-Enhanced Synthetic Data Generation: A Case Study on the S&P 500 Using a Quantum Wasserstein Generative Adversarial Network Approach with a Gradient Penalty.

Author

Orlandi, Filippo, Barbierato, Enrico, and Gatti, Alice

Subjects
GENERATIVE adversarial networks, STANDARD & Poor's 500 Index, TIME series analysis, FORECASTING
Abstract

This study introduces a novel Quantum Wasserstein Generative Adversarial Network approach with a Gradient Penalty (QWGAN-GP) model that leverages a quantum generator alongside a classical discriminator to synthetically generate time series data. This approach aims to accurately replicate the statistical properties of the S&P 500 index. The synthetic data generated by this model were compared to the original series using various metrics, including Wasserstein distance, Dynamic Time Warping (DTW) distance, and entropy measures, among others. The outcomes demonstrate the model's robustness, with the generated data exhibiting a high degree of fidelity to the statistical characteristics of the original data. Additionally, this study explores the applicability of the synthetic time series in enhancing prediction models. An LSTM (Long-Short Term Memory)-based model was developed to evaluate the impact of incorporating synthetic data on forecasting accuracy, particularly focusing on general trends and extreme market events. The findings reveal that models trained on a mix of synthetic and real data significantly outperform those trained solely on historical data, improving predictive performance. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

22. Combinatorics of Vogan diagrams for almost-Kähler manifolds.

Author

Gatti, Alice

Subjects
*LIE groups, *COMBINATORICS, *SEMISIMPLE Lie groups, *ORBITS (Astronomy)
Abstract

Let G be a non-compact classical semisimple Lie group and let G / V be the adjoint orbit with respect to a fixed element in G. These manifolds can be equipped with an almost-Kähler structure and we provide explicit formulae for the existence of special almost-complex structures on G / V purely in terms of the combinatorics of the associated Vogan diagram. The formulae are given separately for Lie groups whose Lie algebras are of type A ℓ , B ℓ , C ℓ , D ℓ , where ℓ denotes the rank of the Lie algebra. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

25. GU-CA-COVID: a clinical audit among Italian genitourinary oncologists during the first COVID-19 outbreak

Author

Bersanelli, Melissa, Buti, Sebastiano, Rizzo, Mimma, Cortellini, Alessio, Cattrini, Carlo, Massari, Francesco, Masini, Cristina, Vitale, Maria Giuseppa, Fornarini, Giuseppe, Caffo, Orazio, Atzori, Francesco, Gatti, Alice, Macrini, Serena, Mucciarini, Claudia, Galli, Luca, Morelli, Franco, Stellato, Marco, Marco, Fanelli, Martina, Corti, Francesca, Zucali, Paolo Andrea, Toscani, Ilaria, Dalla Volta, Alberto, Gernone, Angela, Baldessari, Cinzia, La Torre, Leonardo, Zara, Diego, Gennari, Alessandra, Bracarda, Sergio, Procopio, Giuseppe, and Porta, Camillo

Subjects
urothelial cancer [COVID-19, cancer patients, genitourinary cancers, bladder cancer, SARS-CoV-2, renal cancer]
Abstract

BACKGROUND: Considering the growing genitourinary (GU) cancer population undergoing systemic treatment with immune checkpoint inhibitors (ICIs) in the context of the COVID-19 pandemic, we planned a clinical audit in 24 Italian institutions treating GU malignancies. OBJECTIVE: The primary objective was investigating the clinical impact of COVID-19 in GU cancer patients undergoing ICI-based therapy during the first outbreak of SARS-CoV-2 contagion in Italy. DESIGN, SETTING, AND PARTICIPANTS: The included centers were 24 Oncology Departments. Two online forms were completed by the responsible Oncology Consultants, respectively, for metastatic renal cell carcinoma (mRCC) and metastatic urothelial carcinoma (mUC) patients receiving at least one administration of ICIs between 31 January 2020 and 30 June 2020. RESULTS AND LIMITATION: In total, 287 mRCC patients and 130 mUC patients were included. The COVID-19 incidence was, respectively, 3.5%, with mortality 1%, in mRCC patients and 7.7%, with mortality 3.1%, in mUC patients. In both groups, 40% of patients developing COVID-19 permanently discontinued anticancer treatment. The pre-test SARS-CoV-2 probability in the subgroup of patients who underwent nasal/pharyngeal swab ranged from 14% in mRCC to 26% in mUC. The main limitation of the work was its nature of audit: data were not recorded at the single-patient level. CONCLUSION: GU cancer patients undergoing active treatment with ICIs have meaningful risk factors for developing severe events from COVID-19 and permanent discontinuation of therapy after the infection. Treatment delays due to organizational issues during the pandemic were unlikely to affect the treatment outcome in this population.

Published
2021

26. Fatigue Induced by Repeated Changes of Direction in Élite Female Football (Soccer) Players: Impact on Lower Limb Biomechanics and Implications for ACL Injury Prevention

Author

Zago, Matteo, primary, David, Sina, additional, Bertozzi, Filippo, additional, Brunetti, Claudia, additional, Gatti, Alice, additional, Salaorni, Francesca, additional, Tarabini, Marco, additional, Galvani, Christel, additional, Sforza, Chiarella, additional, and Galli, Manuela, additional

Published
2021
Full Text
View/download PDF

27. GU-CA-COVID: a clinical audit among Italian genitourinary oncologists during the first COVID-19 outbreak

Author

Bersanelli, Melissa, primary, Buti, Sebastiano, additional, Rizzo, Mimma, additional, Cortellini, Alessio, additional, Cattrini, Carlo, additional, Massari, Francesco, additional, Masini, Cristina, additional, Vitale, Maria Giuseppa, additional, Fornarini, Giuseppe, additional, Caffo, Orazio, additional, Atzori, Francesco, additional, Gatti, Alice, additional, Macrini, Serena, additional, Mucciarini, Claudia, additional, Galli, Luca, additional, Morelli, Franco, additional, Stellato, Marco, additional, Fanelli, Martina, additional, Corti, Francesca, additional, Zucali, Paolo Andrea, additional, Toscani, Ilaria, additional, Dalla Volta, Alberto, additional, Gernone, Angela, additional, Baldessari, Cinzia, additional, La Torre, Leonardo, additional, Zara, Diego, additional, Gennari, Alessandra, additional, Bracarda, Sergio, additional, Procopio, Giuseppe, additional, and Porta, Camillo, additional

Published
2021
Full Text
View/download PDF

30. Graph Partitioning and Sparse Matrix Ordering using Reinforcement Learning and Graph Neural Networks.

Author

Gatti, Alice, Zhixiong Hu, Smidt, Tess, Ng, Esmond G., and Ghysels, Pieter

Subjects
*REINFORCEMENT learning, *SPARSE matrices, *CONVOLUTIONAL neural networks, *REPRESENTATIONS of graphs, *FACTORIZATION, *SPARSE graphs, *SCIENCE education
Abstract

We present a novel method for graph partitioning, based on reinforcement learning and graph convolutional neural networks. Our approach is to recursively partition coarser representations of a given graph. The neural network is implemented using SAGE graph convolution layers, and trained using an advantage actor critic (A2C) agent. We present two variants, one for finding an edge separator that minimizes the normalized cut or quotient cut, and one that finds a small vertex separator. The vertex separators are then used to construct a nested dissection ordering to permute a sparse matrix so that its triangular factorization will incur less fill-in. The partitioning quality is compared with partitions obtained using METIS and SCOTCH, and the nested dissection ordering is evaluated in the sparse solver SuperLU. Our results show that the proposed method achieves similar partitioning quality as METIS, SCOTCH and spectral partitioning. Furthermore, the method generalizes across different classes of graphs, and works well on a variety of graphs from the SuiteSparse sparse matrix collection. [ABSTRACT FROM AUTHOR]

Published
2022

31. Tutorat et compétences de communication

Author

GATTI, Alice-Anne, BLARY, Aude-Hélène, École supérieure du professorat et de l'éducation - Aix Marseille (ESPE AMU), Aix Marseille Université (AMU), and Jérémy Castera

Subjects
Baccalauréat professionnel, Soins et services à la personne, Communication, [SHS.EDU]Humanities and Social Sciences/Education, Interactions, Tutorat, Tutelage, Rôle, Accompagnement
Abstract

This report finds its origin in the observation of the activities implemented (operated) within the framework of the courts (courses, prices, yards) of biology of a sixth year of high school ASSP. We realized that many pupil of this class feels (experiences) difficulties of understanding in biology. Furthermore it seems that the skills of communication in the reference table of the high school diploma Support (Accompaniment) Care and human services are not necessarily to work within the framework of the training(formation) during the courts (courses, prices, yards) on the high school. We thus set up the tutelage between peers because he allows to individualize the transmission of the knowledges, to take into account more the difficulties of each, to answer the difficulties of understanding but also to work the skills in communication. Indeed by activating the expression of the knowledge and the exchange the tutelage thus allows to organize the mental activity and to structure and to develop so its capacities of communication. This shape of tutelage can be formalized or not and we thus are to ask in what the diverse forms of tutelage allow to develop the skills of communications specific to the pupils of the Tub(Ferry,High school diploma) ASSP? To verify this hypothesis we thus built a questionnaire of self-assessment of the skills in communication allowing to see the global evolution and by sub-skill (sub-competence) of communication to refine the understanding of the impact of the diverse forms of tutelage. We subjected (submitted) this questionnaire upstream and downstream to the implementation of the device(plan). The results (profits) show us contrary to our hypotheses of departure that the formal tutelage does not improve the global skills in communication and that the reduction is essentially due to the sub-skills "production and search (research) for feedback of understanding" and "capacities to detect incoherence". The informal tutelage allows to improve the global skills and more specifically the sub-skills "métacognition" and the capacities to detect incoherence. Both train(form) some tutelage improve the sub-skill (sub-competence) "perception (collection) of one in the group". Certainly that the too stiff frame of the formal tutelage locks every pupil into a role (guardian or tutored) to the detriment of the relation between peers. It stays in an asymmetric relation which does not facilitate the interactions and thus the development of the skills.; Ce mémoire trouve son origine dans l’observation des activités mises en œuvre dans le cadre des cours de biologie d’une classe de première ASSP. Nous nous sommes rendu compte que beaucoup d’élève de cette classe éprouve des difficultés de compréhension en biologie. De plus il apparait que les compétences de communication dans le référentiel du baccalauréat Accompagnement Soins et services à la personne ne sont pas forcément travailler dans le cadre de la formation pendant les cours au lycée. Nous avons donc mis en place le tutorat entre pairs car il permet d’individualiser la transmission des savoirs, de prendre davantage en compte les difficultés de chacun, de répondre aux difficultés de compréhension mais aussi de travailler les compétences en communication. En effet en activant l’expression du savoir et l’échange le tutorat permet donc d’organiser l’activité mentale et de structurer et de développer ainsi ses capacités de communication. Cette forme de tutorat peut être formalisé ou non et nous nous sommes donc demander en quoi les diverses formes de tutorat permettent de développer les compétences de communications spécifiques aux élèves du Bac ASSP ? Pour vérifier cette hypothèse nous avons donc construit un questionnaire d’autoévaluation des compétences en communication permettant de voir l’évolution globale et par sous-compétence de communication pour affiner la compréhension de l’impact des diverses formes de tutorat. Nous avons soumis ce questionnaire en amont et en aval de la mise en place du dispositif. Les résultats nous montrent contrairement à nos hypothèses de départ que le tutorat formel n’améliore pas les compétences globales en communication et que la baisse est essentiellement due aux sous-compétences « production et recherche de feedback de compréhension » et « capacités à détecter des incohérences ». Le tutorat informel permet d’améliorer les compétences globales et plus spécifiquement les sous-compétences « métacognition » et capacités à détecter des incohérences. Les deux forment du tutorat améliore la sous-compétence « perception de soi dans le groupe ». Certainement que le cadre trop rigide du tutorat formel enferme chaque élève dans un rôle (tuteur ou tutoré) au détriment de la relation entre pairs. Il reste dans une relation asymétrique qui ne facilite pas les interactions et donc le développement des compétences.

Published
2017

Catalog

Books, media, physical & digital resources
See catalog results