相关论文: When Hindsight is Not 20/20: Testing Limits on Ref…

There is considerable confusion about the role of Large Language Models (LLMs) in planning and reasoning tasks. On one side are over-optimistic claims that LLMs can indeed do these tasks with just the right prompting or self-verification…

We evaluate the ability of Large Language Models (LLMs) to discern and express their internal knowledge state, a key factor in countering factual hallucination and ensuring reliable application of LLMs. We observe a robust self-awareness of…

Large Language Models, such as Generative Pre-trained Transformer 3 (aka. GPT-3), have been developed to understand language through the analysis of extensive text data, allowing them to identify patterns and connections between words.…

Large language models (LLMs) have become common decision-support tools across educational and professional contexts, raising questions about how their outputs shape human critical thinking. Prior work suggests that the amount of AI…

This paper investigates the reliability of explanations generated by large language models (LLMs) when prompted to explain their previous output. We evaluate two kinds of such self-explanations - extractive and counterfactual - using three…

While Small Language Models (SLMs) have demonstrated promising performance on an increasingly wide array of commonsense reasoning benchmarks, current evaluation practices rely almost exclusively on the accuracy of their final answers,…

Autoprompting is the process of automatically selecting optimized prompts for language models, which has been gaining popularity with the rapid advancement of prompt engineering, driven by extensive research in the field of large language…

Hallucination remains a critical challenge in large language models (LLMs), hindering the development of reliable multimodal LLMs (MLLMs). Existing solutions often rely on human intervention or underutilize the agent's ability to…

As Large Language Models become integral to decision-making, optimism about their power is tempered with concern over their errors. Users may over-rely on LLM advice that is confidently stated but wrong, or under-rely due to mistrust.…

Large Language Models (LLMs) often exhibit knowledge disparities across languages. Encouraging LLMs to \textit{abstain} when faced with knowledge gaps is a promising strategy to reduce hallucinations in multilingual settings. Current…

Large Reasoning Models (LRMs) excel at multi-step reasoning but often suffer from inefficient reasoning processes like overthinking and overshoot, where excessive or misdirected reasoning increases computational cost and degrades…

The emergence of Large Language Models (LLMs) has revealed a growing need for human-AI collaboration, especially in creative decision-making scenarios where trust and reliance are paramount. Through human studies and model evaluations on…

Recent advancements in large language models (LLMs), such as DeepSeek-R1 and OpenAI-o1, have demonstrated the significant effectiveness of test-time scaling, achieving substantial performance gains across various benchmarks. These advanced…

Q-learning excels in learning from feedback within sequential decision-making tasks but often requires extensive sampling to achieve significant improvements. While reward shaping can enhance learning efficiency, non-potential-based methods…

Current reasoning paradigms for LLMs include chain-of-thought, ReAct, and post-hoc self-critique. These paradigms rely on two assumptions that fail on long-horizon, multi-stage tasks. As a result, errors accumulate silently across reasoning…

Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in various perception and reasoning tasks. Despite this success, ensuring their reliability in practical deployment necessitates robust confidence…

Large language models (LLMs) suffer from high inference latency due to the auto-regressive decoding process. Speculative decoding accelerates inference by generating multiple draft tokens using a lightweight model and verifying them in…

Chain-of-thought (CoT) has proven to improve the reasoning capability of large language models (LLMs). However, due to the complexity of multimodal scenarios and the difficulty in collecting high-quality CoT data, CoT reasoning in…

Although preference optimization methods have improved reasoning performance in Large Language Models (LLMs), they often lack transparency regarding why one reasoning outcome is preferred over another. This limitation is especially critical…

Self-improving large language models (LLMs) -- i.e., to improve the performance of an LLM by fine-tuning it with synthetic data generated by itself -- is a promising way to advance the capabilities of LLMs while avoiding extensive…