Related papers: Think Just Enough: Sequence-Level Entropy as a Con…

Large Language Models (LLMs) have shown impressive performance in mathematical reasoning tasks when guided by Chain-of-Thought (CoT) prompting. However, they tend to produce highly confident yet incorrect outputs, which poses significant…

While large language models (LLMs) such as ChatGPT and PaLM have demonstrated remarkable performance in various language understanding and generation tasks, their capabilities in complex reasoning and intricate knowledge utilization still…

Language prediction is constrained by informational entropy intrinsic to language, such that there exists a limit to how accurate any language model can become and equivalently a lower bound to language compression. The most efficient…

Both performance and efficiency are crucial factors for sequence labeling tasks in many real-world scenarios. Although the pre-trained models (PTMs) have significantly improved the performance of various sequence labeling tasks, their…

Reinforcement learning has become the standard for improving reasoning in large language models, yet evidence increasingly suggests that RL does not teach new strategies; it redistributes probability mass over solutions the base model…

Selective prediction systems can mitigate harms resulting from language model hallucinations by abstaining from answering in high-risk cases. Uncertainty quantification techniques are often employed to identify such cases, but are rarely…

This project develops a self correcting framework for large language models (LLMs) that detects and mitigates hallucinations during multi-step reasoning. Rather than relying solely on final answer correctness, our approach leverages fine…

This paper presents a class of new fast non-trainable entropy-based confidence estimation methods for automatic speech recognition. We show how per-frame entropy values can be normalized and aggregated to obtain a confidence measure per…

Large language models (LLMs) have demonstrated outstanding performance across various tasks, yet they still exhibit limitations such as hallucination, unfaithful reasoning, and toxic content. One potential approach to mitigate these issues…

The scarcity of high-quality, logically sound data is a critical bottleneck for advancing the mathematical reasoning of Large Language Models (LLMs). Our work confronts this challenge by turning decades of automated theorem proving research…

Unlike human reasoning in abstract conceptual spaces, large language models (LLMs) typically reason by generating discrete tokens, which potentially limit their expressive power. The recent work Soft Thinking has shown that LLMs' latent…

The use of Large Language Models (LLMs) for reasoning and planning tasks has drawn increasing attention in Artificial Intelligence research. Despite their remarkable progress, these models still exhibit limitations in multi-step inference…

Large reasoning models (LRMs) are proficient at generating explicit, step-by-step reasoning sequences before producing final answers. However, such detailed reasoning can introduce substantial computational overhead and latency,…

Standard chain-of-thought reasoning generates a solution in a single forward pass, committing irrevocably to each token and lacking a mechanism to recover from early errors. We introduce Inference-Time Rethinking, a generative framework…

Large reasoning models (LRMs) have exhibited remarkable reasoning capabilities through inference-time scaling, but this progress has also introduced considerable redundancy and inefficiency into their reasoning processes, resulting in…

We investigate whether the success of a zero-shot Chain-of-Thought (CoT) process can be predicted before completion. We discover that a probing classifier, based on LLM representations, performs well \emph{even before a single token is…

Scaling training compute, measured in FLOPs, has long been shown to improve the accuracy of large language models, yet training remains resource-intensive. Prior work shows that increasing test-time compute (TTC)-for example through…

Uncertainty estimation remains a key challenge when adapting pre-trained language models to downstream classification tasks, with overconfidence often observed for difficult inputs. While predictive entropy provides a strong baseline for…

Token-level Chain-of-Thought (CoT) prompting has become a standard way to elicit multi-step reasoning in large language models (LLMs), especially for mathematical word problems. However, generating long intermediate traces increases output…

Chain-of-Thought (CoT) prompting helps Large Language Models (LLMs) tackle complex reasoning by eliciting explicit step-by-step rationales. However, CoT's verbosity increases latency and memory usage and may propagate early errors across…