Search

This paper presents the development of a dashboard designed specifically for teachers in English as a Foreign Language (EFL) writing education. Leveraging LLMs, the dashboard facilitates the analysis of student interactions with an essay writing system, which integrates ChatGPT for real-time feedback. The dashboard aids teachers in monitoring student behavior, identifying noneducational interaction with ChatGPT, and aligning instructional strategies with learning objectives. By combining insights from NLP and Human-Computer Interaction (HCI), this study demonstrates how a human-centered approach can enhance the effectiveness of teacher dashboards, particularly in ChatGPT-integrated learning., Comment: EMNLP 2024 Workshop CustomNLP4U. arXiv admin note: text overlap with arXiv:2405.19691

While ChatGPT has significantly impacted education by offering personalized resources for students, its integration into educational settings poses unprecedented risks, such as inaccuracies and biases in AI-generated content, plagiarism and over-reliance on AI, and privacy and security issues. To help teachers address such risks, we conducted a two-phase iterative design process that comprises surveys, interviews, and prototype demonstration involving six EFL (English as a Foreign Language) teachers, who integrated ChatGPT into semester-long English essay writing classes. Based on the needs identified during the initial survey and interviews, we developed a prototype of Prompt Analytics Dashboard (PAD) that integrates the essay editing history and chat logs between students and ChatGPT. Teacher's feedback on the prototype informs additional features and unmet needs for designing future PAD, which helps them (1) analyze contextual analysis of student behaviors, (2) design an overall learning loop, and (3) develop their teaching skills.

The integration of generative AI in education is expanding, yet empirical analyses of large-scale and real-world interactions between students and AI systems still remain limited. Addressing this gap, we present RECIPE4U (RECIPE for University), a dataset sourced from a semester-long experiment with 212 college students in English as Foreign Language (EFL) writing courses. During the study, students engaged in dialogues with ChatGPT to revise their essays. RECIPE4U includes comprehensive records of these interactions, including conversation logs, students' intent, students' self-rated satisfaction, and students' essay edit histories. In particular, we annotate the students' utterances in RECIPE4U with 13 intention labels based on our coding schemes. We establish baseline results for two subtasks in task-oriented dialogue systems within educational contexts: intent detection and satisfaction estimation. As a foundational step, we explore student-ChatGPT interaction patterns through RECIPE4U and analyze them by focusing on students' dialogue, essay data statistics, and students' essay edits. We further illustrate potential applications of RECIPE4U dataset for enhancing the incorporation of LLMs in educational frameworks. RECIPE4U is publicly available at https://zeunie.github.io/RECIPE4U/., Comment: arXiv admin note: text overlap with arXiv:2309.13243

In the context of English as a Foreign Language (EFL) writing education, LLM-as-a-tutor can assist students by providing real-time feedback on their essays. However, challenges arise in assessing LLM-as-a-tutor due to differing standards between educational and general use cases. To bridge this gap, we integrate pedagogical principles to assess student-LLM interaction. First, we explore how LLMs can function as English tutors, providing effective essay feedback tailored to students. Second, we propose three metrics to evaluate LLM-as-a-tutor specifically designed for EFL writing education, emphasizing pedagogical aspects. In this process, EFL experts evaluate the feedback from LLM-as-a-tutor regarding quality and characteristics. On the other hand, EFL learners assess their learning outcomes from interaction with LLM-as-a-tutor. This approach lays the groundwork for developing LLMs-as-a-tutor tailored to the needs of EFL learners, advancing the effectiveness of writing education in this context.

The integration of generative AI in education is expanding, yet empirical analyses of large-scale, real-world interactions between students and AI systems still remain limited. In this study, we present ChEDDAR, ChatGPT & EFL Learner's Dialogue Dataset As Revising an essay, which is collected from a semester-long longitudinal experiment involving 212 college students enrolled in English as Foreign Langauge (EFL) writing courses. The students were asked to revise their essays through dialogues with ChatGPT. ChEDDAR includes a conversation log, utterance-level essay edit history, self-rated satisfaction, and students' intent, in addition to session-level pre-and-post surveys documenting their objectives and overall experiences. We analyze students' usage patterns and perceptions regarding generative AI with respect to their intent and satisfaction. As a foundational step, we establish baseline results for two pivotal tasks in task-oriented dialogue systems within educational contexts: intent detection and satisfaction estimation. We finally suggest further research to refine the integration of generative AI into education settings, outlining potential scenarios utilizing ChEDDAR. ChEDDAR is publicly available at https://github.com/zeunie/ChEDDAR., Comment: The new version of this paper is on arXiv as arXiv:2403.08272

Combining the {\sc Cloudy} photoionization code with updated stellar population synthesis results, we simultaneously model the MIR $\neiii/\neii$ vs. $\oiv/\neiii$, the MIR-FIR $\neiii/\neii$ vs. $\oiv/\oiii$ and the classical BPT diagnostic diagrams. We focus on the properties of optically classified \hii\,galaxies that lie in the normal star forming zone in the MIR diagnostic diagram. We find that a small fraction of our models lie in this zone, but most of them correspond to the lowest explored metallicity, \zstar\,=\,0.0002, at age $\sim1$ Gyr. This value of \zstar\,is, by far, lower than the values derived for these galaxies from optical emission lines, suggesting that the far-UV emission produced by post-AGB stars (a.k.a. HOLMES, hot low-mass evolved stars) is NOT the source of ionization. Instead, shock models can easily reproduce this part of the MIR diagram. We suggest that it is likely that some of these galaxies have been misclassified and that in them, shocks, produced by a weak AGN-outflow, could be an important source of ionizaton. Using a subset of our models, we derive a new demarcation line for the maximal contribution of retired galaxies in the BPT diagram. This demarcation line allows for a larger contamination from the neighbouring AGN-dominated region. Considering the importance of disentangling the different ionising mechanisms in weak or deeply obscured systems, new observational efforts to classify galaxies both in the optical and IR are required to better constrain this kind of models and understand their evolutionary paths., Comment: Accepted for publication in MNRAS

The integration of generative AI in the field of education is actively being explored. In particular, ChatGPT has garnered significant interest, offering an opportunity to examine its effectiveness in English as a foreign language (EFL) education. To address this need, we present a novel learning platform called RECIPE (Revising an Essay with ChatGPT on an Interactive Platform for EFL learners). Our platform features two types of prompts that facilitate conversations between ChatGPT and students: (1) a hidden prompt for ChatGPT to take an EFL teacher role and (2) an open prompt for students to initiate a dialogue with a self-written summary of what they have learned. We deployed this platform for 213 undergraduate and graduate students enrolled in EFL writing courses and seven instructors. For this study, we collect students' interaction data from RECIPE, including students' perceptions and usage of the platform, and user scenarios are examined with the data. We also conduct a focus group interview with six students and an individual interview with one EFL instructor to explore design opportunities for leveraging generative AI models in the field of EFL education.

Radiotherapy inverse planning often requires planners to modify parameters in the treatment planning system's objective function to produce clinically acceptable plans. Due to the manual steps in this process, plan quality can vary depending on the planning time available and the planner's skills. This study investigates two hyperparameter-tuning methods for automated inverse planning. Because this framework does not train a model on previously-optimized plans, it can be readily adapted to practice pattern changes, and plan quality is not limited by that of a training cohort. We selected 10 patients who received lung SBRT using manually-generated clinical plans. We used random sampling (RS) and Bayesian optimization (BO) to tune parameters using linear-quadratic utility functions based on 11 clinical goals. Normalizing all plans to have PTV D95 equal to 48 Gy, we compared plan quality for the automatically-generated and manually-generated plans. We also investigated the impact of iteration count on the automatically-generated plans, comparing planning time and plan utility for RS and BO plans with and without stopping criteria. Without stopping criteria, the median planning time was 1.9 and 2.3 hours for RS and BO plans. The OAR doses in the RS and BO plans had a median percent difference (MPD) of 48.7% and 60.4% below clinical dose limits and an MPD of 2.8% and 3.3% below clinical plan doses. With stopping criteria, the utility decreased by an MPD of 5.3% and 3.9% for RS and BO plans, but the median planning time was reduced to 0.5 and 0.7 hours, and the OAR doses still had an MPD of 42.9% and 49.7% below clinical dose limits and an MPD of 0.3% and 1.8% below clinical plan doses. This study demonstrates that hyperparameter-tuning approaches to automated inverse planning can reduce active planning time with plan quality that is similar to or better than manually-generated plans., Comment: 22 pages, 4 figures

Radiotherapy is used to treat cancer patients by damaging DNA of tumor cells using ionizing radiation. Photons are the most widely used radiation type for therapy, having been put into use soon after the first discovery of X-rays in 1895. However, there are emerging interests and developments of other radiation modalities such as protons and carbon ions, owing to their unique biological and physical characteristics that distinguish these modalities from photons. Current attempts to determine an optimal radiation modality or an optimal combination of multiple modalities are empirical and in the early stage of development. In this paper, we propose a mathematical framework to optimize full radiation dose distributions and fractionation schedules of multiple radiation modalities, aiming to maximize the damage to the tumor while limiting the damage to the normal tissue to the corresponding tolerance level. This formulation gives rise to a non-convex, mixed integer program and we propose a bilevel optimization algorithm, to efficiently solve it. The upper level problem is to optimize the fractionation schedule using the dose distribution optimized in the lower level. We demonstrate the feasibility of our novel framework and algorithms in a simple 2-dimensional phantom with two different radiation modalities, where clinical intuition can be easily drawn. The results of our numerical simulations agree with the clinical intuition, validating our approach and showing the promise of the framework for further clinical investigation., Comment: 23 pages, 4 figures

Fluence map optimization for intensity-modulated radiation therapy planning can be formulated as a large-scale inverse problem with competing objectives and constraints associated with the tumors and organs-at-risk. Unfortunately, clinically relevant dose-volume constraints are nonconvex, so standard algorithms for convex problems cannot be directly applied. While prior work focused on convex approximations for these constraints, we propose a novel relaxation approach to handle nonconvex dose-volume constraints. We develop efficient, provably convergent algorithms based on partial minimization, and show how to adapt them to handle maximum-dose constraints and infeasible problems. We demonstrate our approach using the CORT dataset, and show that it is easily adaptable to radiation treatment planning with dose-volume constraints for multiple tumors and organs-at-risk., Comment: 38 pages, 18 figures

There are several different modalities, e.g., surgery, chemotherapy, and radiotherapy, that are currently used to treat cancer. It is common practice to use a combination of these modalities to maximize clinical outcomes, which are often measured by a balance between maximizing tumor damage and minimizing normal tissue side effects due to treatment. However, multi-modality treatment policies are mostly empirical in current practice, and are therefore subject to individual clinicians' experiences and intuition. We present a novel formulation of optimal multi-modality cancer management using a finite-horizon Markov decision process approach. Specifically, at each decision epoch, the clinician chooses an optimal treatment modality based on the patient's observed state, which we define as a combination of tumor progression and normal tissue side effect. Treatment modalities are categorized as (1) Type 1, which has a high risk and high reward, but is restricted in the frequency of administration during a treatment course, (2) Type 2, which has a lower risk and lower reward than Type 1, but may be repeated without restriction, and (3) Type 3, no treatment (surveillance), which has the possibility of reducing normal tissue side effect at the risk of worsening tumor progression. Numerical simulations using various intuitive, concave reward functions show the structural insights of optimal policies and demonstrate the potential applications of using a rigorous approach to optimizing multi-modality cancer management., Comment: 15 pages, 11 figures

We build a simple physical model to study the high-redshift active galactic Nucleus (AGN) evolution within the co-evolution framework of central black holes (BHs) and their host galaxies. The correlation between the circular velocity of a dark halo $V_c$ and the velocity dispersion of a galaxy $\sigma$ is used to link the dark matter halo mass and BH mass. The dark matter halo mass function is converted to the BH mass function for any given redshift. The high-redshift optical AGN luminosity functions (LFs) are constructed. At $z\sim 4$, the flattening feature is not shown at the faint end of the optical AGN LF. This is consistent with observational results. If the optical AGN LF at $z\sim 6$ can be reproduced in the case in which central BHs have the Eddington-limited accretion, it is possible for the AGN lifetime to have a small value of $2\times 10^5$ yrs. The X-ray AGN LFs and X-ray AGN number counts are also calculated at $2.03$, respectively, using the same parameters adopted in the calculation for the optical AGN LF at $z\sim 4$. It is estimated that about 30 AGNs per $\rm{deg}^2$ at $z>6$ can be detected with a flux limit of $3\times 10^{-17}~\rm{erg~cm^{-2}~s^{-1}}$ in the $0.5-2$ keV band. Additionally, the cosmic reionization is also investigated. The ultraviolet photons emitted from the high-redshift AGNs mainly contribute to the cosmic reionization, and the central BHs of the high-redshift AGNs have a mass range of $10^6-10^8M_\odot$. We also discuss some uncertainties in both the AGN LFs and AGN number counts originating from the $M_{\rm{BH}}-\sigma$ relation, Eddington ratio, AGN lifetime, and X-ray attenuation in our model., Comment: 2016, ApJ, 828, 96

Purpose: Current inverse planning methods for IMRT are limited because they are not designed to explore the trade-offs between the competing objectives between the tumor and normal tissues. Our goal was to develop an efficient multiobjective optimization algorithm that was flexible enough to handle any form of objective function and that resulted in a set of Pareto optimal plans. Methods: We developed a hierarchical evolutionary multiobjective algorithm designed to quickly generate a diverse Pareto optimal set of IMRT plans that meet all clinical constraints and reflect the trade-offs in the plans. The top level of the hierarchical algorithm is a multiobjective evolutionary algorithm (MOEA). The genes of the individuals generated in the MOEA are the parameters that define the penalty function minimized during an accelerated deterministic IMRT optimization that represents the bottom level of the hierarchy. The MOEA incorporates clinical criteria to restrict the search space through protocol objectives and then uses Pareto optimality among the fitness objectives to select individuals. Results: Acceleration techniques implemented on both levels of the hierarchical algorithm resulted in short, practical runtimes for optimizations. The MOEA improvements were evaluated for example prostate cases with one target and two OARs. The modified MOEA dominated 11.3% of plans using a standard genetic algorithm package. By implementing domination advantage and protocol objectives, small diverse populations of clinically acceptable plans that were only dominated 0.2% by the Pareto front could be generated in a fraction of an hour. Conclusions: Our MOEA produces a diverse Pareto optimal set of plans that meet all dosimetric protocol criteria in a feasible amount of time. It optimizes not only beamlet intensities but also objective function parameters on a patient-specific basis.

We present a wide field survey of satellite galaxies in M106 (NGC 4258) covering a $1.7\degr \times 2\degr$ field around M106 using Canada-France-Hawaii Telescope/MegaCam. We find 16 satellite galaxy candidates of M106. Eight of these galaxies are found to be dwarf galaxies that are much smaller and fainter than the remaining galaxies. Four of these galaxies are new findings. Surface brightness profiles of 15 out of 16 satellite galaxies can be represented well by an exponential disk profile with varying scale length. We derive the surface number density distribution of these satellite galaxies. The central number density profile (d $<100$ kpc) is well fitted by a power-law with a power index of $-2.1\pm0.5$, similar to the expected power index of isothermal distribution. The luminosity function of these satellites is represented well by the Schechter function with a faint end slope of $-1.19^{+0.03}_{-0.06}$. Integrated photometric properties (total luminosity, total colour, and disk scale length) and the spatial distribution of these satellite galaxies are found to be roughly similar to those of the Milky Way and M31., Comment: Accepted by MNRAS

We report a moderate-depth (70 ksec), contiguous 0.7 sq.deg, Chandra survey, in the Lockman Hole Field of the Spitzer/SWIRE Legacy Survey coincident with a completed, ultra-deep VLA survey with deep optical and near-infrared imaging in-hand. The primary motivation is to distinguish starburst galaxies and AGN, including the significant, highly obscured (log N_H >23) subset. Chandra has detected 775 X-ray sources to a limiting broad band (0.3-8 keV) flux ~4E-16 erg/cm^2/s. We present the X-ray catalog, fluxes, hardness ratios and multi-wavelength fluxes. The log N vs. log S agrees with those of previous surveys covering similar flux ranges. The Chandra and Spitzer flux limits are well matched: 771 (99%) of the X-ray sources have IR or optical counterparts, and 333 have MIPS 24 um detections. There are 4 optical-only X-ray sources and 4 with no visible optical/IR counterpart. The very deep (~2.7 uJy rms) VLA data yields 251 (> 4 sigma) radio counterparts, 44% of the X-ray sources in the field. We confirm that the tendency for lower X-ray flux sources to be harder is primarily due to absorption. As expected, there is no correlation between observed IR and X-ray flux. Optically bright, Type 1 and red AGN lie in distinct regions of the IR vs X-ray flux plots, demonstrating the wide range of SEDs in this sample and providing the potential for classification/source selection. The classical definition of radio-loudness, R_L, is not effective at selecting strong radio sources for red and relatively optically faint AGN. Using the 24 um to radio flux ratio (q_24) results in the usual ~10% radio-loud AGN (13 of 147)., Comment: 43 pages, 25 figures, 3 included latex tables, latex source Accepted by ApJS

We estimate the reddening and distance of the nearest starburst galaxy IC 10 using deep near infrared $JHK_{S}$ photometry obtained with the Multi-Object InfraRed Camera and Spectrograph (MOIRCS) on the Subaru telescope. We estimate the foreground reddening toward IC 10 using $UBV$ photometry of IC 10 from the Local Group Survey, obtaining $E(B-V)=0.52\pm 0.04$ mag. We derive the total reddening including the internal reddening, $E(B-V)=0.98\pm 0.06$ mag, using $UBV$ photometry of early-type stars in IC 10 and comparing $JHK_{S}$ photometry of red giant branch stars in IC 10 and the SMC. Using the 2MASS point source catalog of 20 Galactic globular clusters, we derive a relation between the metallicity [Fe/H]$_{CG97}$ and the slope of the red giant branch in the $K_{S}- (J-K_{S})$ color-magnitude diagram. The mean metallicity of the red giant branch stars in IC 10 is estimated to be [Fe/H]$_{CG97}=-1.08\pm0.28$. The magnitude of the tip of the red giant branch (TRGB) of IC 10 in the $K_{S}$ band is measured to be $K_{S,TRGB}=18.28\pm0.01$. Based on the TRGB method, we estimate the distance modulus of IC 10 to be $(m-M)_{0}=24.27\pm0.03{\rm (random)}\pm0.18{\rm (systematic)}$, corresponding to the distance of $d=715\pm10\pm60$ kpc. This confirms that IC 10 is a member of the Local Group., Comment: 35 pages, 11 figures, To appear in the Astrophysical Journal, 2009

We present the Chandra Multiwavelength Project (ChaMP) X-ray point source catalog with ~6,800 X-ray sources detected in 149 Chandra observations covering \~10 deg^2. The full ChaMP catalog sample is seven times larger than the initial published ChaMP catalog. The exposure time of the fields in our sample ranges from 0.9 to 124 ksec, corresponding to a deepest X-ray flux limit of f_{0.5-8.0} = 9 x 10^{-16} erg/cm2/sec. The ChaMP X-ray data have been uniformly reduced and analyzed with ChaMP-specific pipelines, and then carefully validated by visual inspection. The ChaMP catalog includes X-ray photometric data in 8 different energy bands as well as X-ray spectral hardness ratios and colors. To best utilize the ChaMP catalog, we also present the source reliability, detection probability and positional uncertainty. To quantitatively assess those parameters, we performed extensive simulations. In particular, we present a set of empirical equations: the flux limit as a function of effective exposure time, and the positional uncertainty as a function of source counts and off axis angle. The false source detection rate is ~1% of all detected ChaMP sources, while the detection probability is better than ~95% for sources with counts >30 and off axis angle <5 arcmin. The typical positional offset between ChaMP X-ray source and their SDSS optical counterparts is 0.7+-0.4 arcsec, derived from ~900 matched sources., Comment: 60 pages, 21 figures, accepted for publication in ApJS, Full resolution version is available at http://hea-www.cfa.harvard.edu/CHAMP/RESULTS_PAPERS/ChaMP_xcat.pdf

We present the Chandra Multiwavelength Project (ChaMP) X-ray point source number counts and the cosmic X-ray background (CXRB) flux densities in multiple energy bands. From the ChaMP X-ray point source catalog, ~5,500 sources are selected covering 9.6 deg^2 in sky area. To quantitatively characterize the sensitivity and completeness of the ChaMP sample, we perform extensive simulations. We also include the ChaMP+CDFs (Chandra Deep Fields) number counts to cover large flux ranges from 2x10^{-17} to 2.4x10^{-12} (0.5-2 keV) and from 2x10^{-16} to 7.1x10^{-12} (2-8 keV) erg/cm^2/sec. The ChaMP and the ChaMP+CDFs differential number counts are well fitted with a broken power law. The best fit faint and bright power indices are 1.49^{+0.02}_{-0.02} and 2.36^{+0.05}_{-0.05} (0.5-2 keV), and 1.58^{+0.01}_{-0.01} and 2.59^{+0.06}_{-0.05} (2-8 keV), respectively. We detect breaks in the differential number counts and they appear at different fluxes in different energy bands. Assuming a single power law model for a source spectrum, we find that the same population(s) of soft X-ray sources causes the break in the differential number counts for all energy bands. We measure the resolved CXRB flux densities from the ChaMP and the ChaMP+CDFs number counts with and without bright target sources. Adding the known unresolved CXRB to the ChaMP+CDF resolved CXRB, we also estimate total CXRB flux densities. The fractions of the resolved CXRB without target sources are 78^{+1}_{-1}% and 81^{+2}_{-2}% in the 0.5-2 keV and 2-8 keV bands, respectively, somewhat lower, though generally consistent with earlier numbers since their large errors. These fractions increase by ~1% when target sources are included., Comment: 54 pages, 21 figures, accepted for publication in ApJ, Full resolution version is available at http://hea-www.cfa.harvard.edu/CHAMP/RESULTS_PAPERS/ChaMP_ncounts.pdf

We have determined the distance to M33 using the tip of the red giant branch (TRGB) and the red clump (RC), from the VI photometry of stars in ten regions of M33 based on HST/WFPC2 images. The regions used in this study are located at R=2.6 - 17.8 arcmin from the center of M33. The distance modulus to M33 obtained in this study, for an adopted foreground reddening of E(B-V)=0.04, is (m-M)_{0,TRGB}=24.81+/-0.04(random)+0.15/-0.11(systematic) from the TRGB, and (m-M)_{0,RC}=24.80+/-0.04(random)+/-0.05(systematic) from the RC, showing an excellent agreement between the two (corresponding to a distance of 916+/-17(random) kpc and 912+/-17(random) kpc, respectively). These results are \~0.3 mag larger than the Cepheid distances based on the same HST/WFPC2 data and ground-based data. This difference is considered partially due to the uncertainty in the estimates of the total reddening for Cepheids in M33., Comment: 17 pages, 11 figures, uses emulateapj5.sty, Accepted for publication in the Astronomical Journal

We have determined the distance to M33 using single epoch I-band observations of Cepheids based on HST/WFPC2 images of five fields in M33. Combining the HST I-band photometry and the periods determined from the ground-based observations (DIRECT) for 21 Cepheids with log P>0.8 in the sample of 32 Cepheids, we derive a distance modulus of (m-M)_0=24.52+/-0.14(random)+/-0.13(systematic) for an adopted total reddening of M33, E(B-V)=0.20+/-0.04 (E(V-I)=0.27+/-0.05) given by Freedmand et al.(2001), the reddening to the LMC, E(B-V)=0.10, and the distance to the LMC, (m-M)_0=18.50. If the total reddening to M33 of E(B-V)=0.10+/-0.09 given by Freedman, Wilson, and Madore(1991) is used, the Cepheid distance modulus based on the I-band photometry will be increased by 0.20. Metallicity effect on the Cepheid distance to M33 is estimated to be small, delta(m-M)_Z=0.01 to 0.06, which leads to (m-M)_0=24.53 to 24.58 after this metallicity effect correction. Using the Wesenheit W_I, an extinction-free parameter, we derive a similar value, (m-M)_0=24.52+/-0.15(random)+/-0.11(systematic). These results are in reasonable agreement with those based on the ground-based multi-epoch BVRI observations of brighter Cepheids in M33, and are ~0.3 smaller than those based on the tip of the red giant branch and the red clump. It is needed to estimate better the reddening to Cepheids in M33., Comment: 9 pages, 6 figures (1 color), uses emulateapj5.sty, Accepted for publication in the Astrophysical Journal