Large language models (LLMs) excel in many tasks but struggle to accurately quantify uncertainty in their generated responses. This limitation makes it challenging to detect misinformation and ensure reliable decision-making. Existing uncertainty quantification (UQ) methods for LLMs are primarily prompt-wise rather than response-wise, often requiring multiple response samples, which incurs high computational costs. Moreover, LLMs have been shown to be overconfident, particularly when using reasoning steps to derive their answers. In this work, we propose CoT-UQ, a response-wise UQ framework that integrates LLMs' inherent reasoning capabilities through Chain-of-Thought (CoT) into the UQ process. CoT-UQ captures critical information during inference by extracting keywords from each reasoning step and assessing their importance to the final answer. This key reasoning information is then aggregated to produce a final uncertainty estimate. We conduct extensive experiments based on LLaMA Family with model sizes varying from 8B to 13B across logical and mathematical reasoning tasks. Experimental results demonstrate that CoT-UQ significantly outperforms existing UQ methods, achieving an average improvement of 5.9% AUROC compared to current UQ methods. The code is available at: https://github.com/ZBox1005/CoT-UQ.

Large language models (LLMs) have demonstrated remarkable in-context learning (ICL) abilities. However, existing theoretical analysis of ICL primarily exhibits two limitations: (a) Limited i.i.d. Setting. Most studies focus on supervised function learning tasks where prompts are constructed with i.i.d. input-label pairs. This i.i.d. assumption diverges significantly from real language learning scenarios where prompt tokens are interdependent. (b) Lack of Emergence Explanation. Most literature answers what ICL does from an implicit optimization perspective but falls short in elucidating how ICL emerges and the impact of pre-training phase on ICL. In our paper, to extend (a), we adopt a more practical paradigm, auto-regressive next-token prediction (AR-NTP), which closely aligns with the actual training of language models. Specifically, within AR-NTP, we emphasize prompt token-dependency, which involves predicting each subsequent token based on the preceding sequence. To address (b), we formalize a systematic pre-training and ICL framework, highlighting the layer-wise structure of sequences and topics, alongside a two-level expectation. In conclusion, we present data-dependent, topic-dependent and optimization-dependent PAC-Bayesian generalization bounds for pre-trained LLMs, investigating that ICL emerges from the generalization of sequences and topics. Our theory is supported by experiments on numerical linear dynamic systems, synthetic GINC and real-world language datasets.

Large Language Models (LLMs) have exhibited exceptional performance in software engineering yet face challenges in adapting to continually evolving code knowledge, particularly regarding the frequent updates of third-party library APIs. This limitation, stemming from static pre-training datasets, often results in non-executable code or implementations with suboptimal safety and efficiency. To this end, this paper introduces CODESYNC, a data engine for identifying outdated code patterns and collecting real-time code knowledge updates from Python third-party libraries. Building upon CODESYNC, we develop CODESYNCBENCH, a comprehensive benchmark for assessing LLMs' ability to stay synchronized with code evolution, which covers real-world updates for 220 APIs from six Python libraries. Our benchmark offers 3,300 test cases across three evaluation tasks and an update-aware instruction tuning dataset consisting of 2,200 training samples. Extensive experiments on 14 state-of-the-art LLMs reveal that they struggle with dynamic code evolution, even with the support of advanced knowledge updating methods (e.g., DPO, ORPO, and SimPO). We believe that our benchmark can offer a strong foundation for the development of more effective methods for real-time code knowledge updating in the future. The experimental code and dataset are publicly available at: https://github.com/Lucky-voyage/Code-Sync.

Many inference scaling methods work by breaking a problem into smaller steps (or groups of tokens), then sampling and choosing the best next step. However, these steps and their sizes are usually predetermined based on human intuition or domain knowledge. This paper introduces dynamic decomposition, a method that automatically and adaptively splits solution and reasoning traces into steps during inference. This approach improves computational efficiency by focusing more resources on difficult steps, breaking them down further and prioritizing their sampling. Experiments on coding and math benchmarks (APPS, MATH, and LiveCodeBench) show that dynamic decomposition performs better than static methods, which rely on fixed steps like token-level, sentence-level, or single-step decompositions. These results suggest that dynamic decomposition can enhance many inference scaling techniques.

Light curves serve as a valuable source of information on stellar formation and evolution. With the rapid advancement of machine learning techniques, it can be effectively processed to extract astronomical patterns and information. In this study, we present a comprehensive evaluation of deep-learning and large language model (LLM) based models for the automatic classification of variable star light curves, based on large datasets from the Kepler and K2 missions. Special emphasis is placed on Cepheids, RR Lyrae, and eclipsing binaries, examining the influence of observational cadence and phase distribution on classification precision. Employing AutoDL optimization, we achieve striking performance with the 1D-Convolution+BiLSTM architecture and the Swin Transformer, hitting accuracies of 94\% and 99\% correspondingly, with the latter demonstrating a notable 83\% accuracy in discerning the elusive Type II Cepheids-comprising merely 0.02\% of the total dataset.We unveil StarWhisper LightCurve (LC), an innovative Series comprising three LLM-based models: LLM, multimodal large language model (MLLM), and Large Audio Language Model (LALM). Each model is fine-tuned with strategic prompt engineering and customized training methods to explore the emergent abilities of these models for astronomical data. Remarkably, StarWhisper LC Series exhibit high accuracies around 90\%, significantly reducing the need for explicit feature engineering, thereby paving the way for streamlined parallel data processing and the progression of multifaceted multimodal models in astronomical applications. The study furnishes two detailed catalogs illustrating the impacts of phase and sampling intervals on deep learning classification accuracy, showing that a substantial decrease of up to 14\% in observation duration and 21\% in sampling points can be realized without compromising accuracy by more than 10\%.

Open-weight large language models (LLMs) have significantly advanced performance in the Natural Language to SQL (NL2SQL) task. However, their effectiveness diminishes when dealing with large database schemas, as the context length increases. To address this limitation, we present SQLong, a novel and efficient data augmentation framework designed to enhance LLM performance in long-context scenarios for the NL2SQL task. SQLong generates augmented datasets by extending existing database schemas with additional synthetic CREATE TABLE commands and corresponding data rows, sampled from diverse schemas in the training data. This approach effectively simulates long-context scenarios during finetuning and evaluation. Through experiments on the Spider and BIRD datasets, we demonstrate that LLMs finetuned with SQLong-augmented data significantly outperform those trained on standard datasets. These imply SQLong's practical implementation and its impact on improving NL2SQL capabilities in real-world settings with complex database schemas.

Understanding molecules is key to understanding organisms and driving advances in drug discovery, requiring interdisciplinary knowledge across chemistry and biology. Although large molecular language models have achieved notable success in interpreting molecular structures, their instruction datasets are limited to the specific knowledge from task-oriented datasets and do not fully cover the fundamental characteristics of molecules, hindering their abilities as general-purpose molecular assistants. To address this issue, we propose Mol-LLaMA, a large molecular language model that grasps the general knowledge centered on molecules via multi-modal instruction tuning. To this end, we design key data types that encompass the fundamental features of molecules, incorporating essential knowledge from molecular structures. In addition, to improve understanding of molecular features, we introduce a module that integrates complementary information from different molecular encoders, leveraging the distinct advantages of different molecular representations. Our experimental results demonstrate that Mol-LLaMA is capable of comprehending the general features of molecules and generating relevant responses to users' queries with detailed explanations, implying its potential as a general-purpose assistant for molecular analysis. Our project page is at https://mol-llama.github.io/.

Human expertise in chemistry and biomedicine relies on contextual molecular understanding, a capability that large language models (LLMs) can extend through fine-grained alignment between molecular structures and text. Recent multimodal learning advances focus on cross-modal alignment, but existing molecule-text models ignore complementary information in different molecular views and rely on single-view representations, limiting molecular understanding. Moreover, na\"ive multi-view alignment strategies face two challenges: (1) separate aligned spaces with inconsistent mappings between molecule and text embeddings, and that (2) existing loss objectives fail to preserve complementary information for fine-grained alignment. This can limit the LLM's ability to fully understand the molecular properties. To address these issues, we propose MV-CLAM, a novel framework that aligns multi-view molecular representations into a unified textual space using a multi-query transformer (MQ-Former). Our approach ensures cross-view consistency while a token-level contrastive loss preserves diverse molecular features across textual queries. MV-CLAM enhances molecular reasoning, improving retrieval and captioning accuracy. The source code of MV-CLAM is available in https://github.com/sumin124/mv-clam.git.

In this study, we delve into the hidden threats posed to text watermarking by users with cross-lingual knowledge. While most research focuses on watermarking methods for English, there is a significant gap in evaluating these methods in cross-lingual contexts. This oversight neglects critical adversary scenarios involving cross-lingual users, creating uncertainty regarding the effectiveness of cross-lingual watermarking. We assess four watermarking techniques across four linguistically rich languages, examining watermark resilience and text quality across various parameters and attacks. Our focus is on a realistic scenario featuring adversaries with cross-lingual expertise, evaluating the adequacy of current watermarking methods against such challenges.

Researchers have made notable progress in applying Large Language Models (LLMs) to solve math problems, as demonstrated through efforts like GSM8k, ProofNet, AlphaGeometry, and MathOdyssey. This progress has sparked interest in their potential use for tutoring students in mathematics. However, the reliability of LLMs in tutoring contexts -- where correctness and instructional quality are crucial -- remains underexplored. Moreover, LLM problem-solving capabilities may not necessarily translate into effective tutoring support for students. In this work, we present two novel approaches to evaluate the correctness and quality of LLMs in math tutoring contexts. The first approach uses an intelligent tutoring system for college algebra as a testbed to assess LLM problem-solving capabilities. We generate benchmark problems using the tutor, prompt a diverse set of LLMs to solve them, and compare the solutions to those generated by the tutor. The second approach evaluates LLM as tutors rather than problem solvers. We employ human evaluators, who act as students seeking tutoring support from each LLM. We then assess the quality and correctness of the support provided by the LLMs via a qualitative coding process. We applied these methods to evaluate several ChatGPT models, including 3.5 Turbo, 4, 4o, o1-mini, and o1-preview. Our findings show that when used as problem solvers, LLMs generate correct final answers for 85.5% of the college algebra problems tested. When employed interactively as tutors, 90% of LLM dialogues show high-quality instructional support; however, many contain errors -- only 56.6% are entirely correct. We conclude that, despite their potential, LLMs are not yet suitable as intelligent tutors for math without human oversight or additional mechanisms to ensure correctness and quality.