Search

The tendency of Large Language Models (LLMs) to generate hallucinations raises concerns regarding their reliability. Therefore, confidence estimations indicating the extent of trustworthiness of the generations become essential. However, current LLM confidence estimations in languages other than English remain underexplored. This paper addresses this gap by introducing a comprehensive investigation of Multilingual Confidence estimation (MlingConf) on LLMs, focusing on both language-agnostic (LA) and language-specific (LS) tasks to explore the performance and language dominance effects of multilingual confidence estimations on different tasks. The benchmark comprises four meticulously checked and human-evaluate high-quality multilingual datasets for LA tasks and one for the LS task tailored to specific social, cultural, and geographical contexts of a language. Our experiments reveal that on LA tasks English exhibits notable linguistic dominance in confidence estimations than other languages, while on LS tasks, using question-related language to prompt LLMs demonstrates better linguistic dominance in multilingual confidence estimations. The phenomena inspire a simple yet effective native-tone prompting strategy by employing language-specific prompts for LS tasks, effectively improving LLMs' reliability and accuracy on LS tasks., Comment: Comments: This work was intended as a replacement of arXiv:2402.13606 and any subsequent updates will appear there

Long-term memory plays a critical role in personal interaction, considering long-term memory can better leverage world knowledge, historical information, and preferences in dialogues. Our research introduces PerLTQA, an innovative QA dataset that combines semantic and episodic memories, including world knowledge, profiles, social relationships, events, and dialogues. This dataset is collected to investigate the use of personalized memories, focusing on social interactions and events in the QA task. PerLTQA features two types of memory and a comprehensive benchmark of 8,593 questions for 30 characters, facilitating the exploration and application of personalized memories in Large Language Models (LLMs). Based on PerLTQA, we propose a novel framework for memory integration and generation, consisting of three main components: Memory Classification, Memory Retrieval, and Memory Synthesis. We evaluate this framework using five LLMs and three retrievers. Experimental results demonstrate that BERT-based classification models significantly outperform LLMs such as ChatGLM3 and ChatGPT in the memory classification task. Furthermore, our study highlights the importance of effective memory integration in the QA task.

The tendency of Large Language Models (LLMs) to generate hallucinations raises concerns regarding their reliability. Therefore, confidence estimations indicating the extent of trustworthiness of the generations become essential. However, current LLM confidence estimations in languages other than English remain underexplored. This paper addresses this gap by introducing a comprehensive investigation of Multilingual Confidence estimation (MlingConf) on LLMs, focusing on both language-agnostic (LA) and language-specific (LS) tasks to explore the performance and language dominance effects of multilingual confidence estimations on different tasks. The benchmark comprises four meticulously checked and human-evaluate high-quality multilingual datasets for LA tasks and one for the LS task tailored to specific social, cultural, and geographical contexts of a language. Our experiments reveal that on LA tasks English exhibits notable linguistic dominance in confidence estimations than other languages, while on LS tasks, using question-related language to prompt LLMs demonstrates better linguistic dominance in multilingual confidence estimations. The phenomena inspire a simple yet effective native-tone prompting strategy by employing language-specific prompts for LS tasks, effectively improving LLMs' reliability and accuracy on LS tasks., Comment: Comments: n pages; Previously this version appeared as arXiv:2410.12478 which was submitted as a new work by accident

The rapid advancements in artificial intelligence (AI) are catalyzing transformative changes in atomic modeling, simulation, and design. AI-driven potential energy models have demonstrated the capability to conduct large-scale, long-duration simulations with the accuracy of ab initio electronic structure methods. However, the model generation process remains a bottleneck for large-scale applications. We propose a shift towards a model-centric ecosystem, wherein a large atomic model (LAM), pre-trained across multiple disciplines, can be efficiently fine-tuned and distilled for various downstream tasks, thereby establishing a new framework for molecular modeling. In this study, we introduce the DPA-2 architecture as a prototype for LAMs. Pre-trained on a diverse array of chemical and materials systems using a multi-task approach, DPA-2 demonstrates superior generalization capabilities across multiple downstream tasks compared to the traditional single-task pre-training and fine-tuning methodologies. Our approach sets the stage for the development and broad application of LAMs in molecular and materials simulation research.

Prior study has shown that pretrained language models (PLM) can boost the performance of text-based recommendation. In contrast to previous works that either use PLM to encode user history as a whole input text, or impose an additional aggregation network to fuse multi-turn history representations, we propose a unified local- and global-attention Transformer encoder to better model two-level contexts of user history. Moreover, conditioned on user history encoded by Transformer encoders, our framework leverages Transformer decoders to estimate the language perplexity of candidate text items, which can serve as a straightforward yet significant contrastive signal for user-item text matching. Based on this, our framework, UniTRec, unifies the contrastive objectives of discriminative matching scores and candidate text perplexity to jointly enhance text-based recommendation. Extensive evaluation shows that UniTRec delivers SOTA performance on three text-based recommendation tasks. Code is available at https://github.com/Veason-silverbullet/UniTRec., Comment: ACL-2023 Short Paper

Predicting cross-immunity between viral strains is vital for public health surveillance and vaccine development. Traditional neural network methods, such as BiLSTM, could be ineffective due to the lack of lab data for model training and the overshadowing of crucial features within sequence concatenation. The current work proposes a less data-consuming model incorporating a pre-trained gene sequence model and a mutual information inference operator. Our methodology utilizes gene alignment and deduplication algorithms to preprocess gene sequences, enhancing the model's capacity to discern and focus on distinctions among input gene pairs. The model, i.e., DNA Pretrained Cross-Immunity Protection Inference model (DPCIPI), outperforms state-of-the-art (SOTA) models in predicting hemagglutination inhibition titer from influenza viral gene sequences only. Improvement in binary cross-immunity prediction is 1.58% in F1, 2.34% in precision, 1.57% in recall, and 1.57% in Accuracy. For multilevel cross-immunity improvements, the improvement is 2.12% in F1, 3.50% in precision, 2.19% in recall, and 2.19% in Accuracy. Our study highlights the potential of pre-trained gene models in revolutionizing gene sequence-related prediction tasks. With more gene sequence data being harnessed and larger models trained, we foresee a significant impact of pre-trained models on clinical and public health applications.

Terahertz (THz) communications open a new frontier for the wireless network thanks to their dramatically wider available bandwidth compared to the current micro-wave and forthcoming millimeter-wave communications. However, due to the short length of THz waves, they also suffer from severe path attenuation and poor diffraction. To compensate the THz-induced propagation loss, this paper proposes to combine two promising techniques, viz., massive multiple input multiple output (MIMO) and intelligent reflecting surface (IRS), in THz multi-user communications, considering their significant beamforming and aperture gains. Nonetheless, channel estimation and low-cost beamforming turn out to be two main obstacles to realizing this combination, due to the passivity of IRS for sending/receiving pilot signals and the large-scale use of expensive RF chains in massive MIMO. In view of these limitations, this paper first develops a cooperative beam training scheme to facilitate the channel estimation with IRS. In particular, we design two different hierarchical codebooks for the proposed training procedure, which are able to balance between the robustness against noise and searching complexity. Based on the training results, we further propose two cost-efficient hybrid beamforming (HB) designs for both single-user and multi-user scenarios, respectively. Simulation results demonstrate that the proposed joint beam training and HB scheme is able to achieve close performance to the optimal fully digital beamforming (FDB) which is implemented even under perfect channel state information (CSI).

Intelligent reflecting surface (IRS) is envisioned as a promising technology to broaden signal coverage and enhance transmission in terahertz (THz) communications. Due to the passivity of IRS, the channel measurement can not be achieved by traditional pilot manner and the subsequent cooperative transmission design remains an open problem. This paper investigates the channel estimation and transmission solutions for massive multiple input multiple output (MIMO) IRS-assisted THz system. The channel estimation is realized by beam training and the quantization error is analyzed for evaluating performance. In addition, a novel hierarchical search codebook design is proposed as a low-complexity basis of beam training. Based on above foundations, we propose a cooperative channel estimation procedure to tactfully acquire the channel knowledge. Finally, by leveraging obtained channel information, the designs of IRS and transceivers are directly provided in closed form without reconstructing the full channel matrix or additional optimization. Simulation and numerical results are presented to illustrate the minimum signal to noise ratio (SNR) required for beam training and the efficacy of the proposed transmission solutions., Comment: 7 pages, 11 figures, accepted by IEEE ICC 2020