Related papers: Reliable Control-Point Selection for Steering Reas…

Do language models make decisions under uncertainty like humans do, and what role does chain-of-thought (CoT) reasoning play in the underlying decision process? We introduce an active probabilistic reasoning task that cleanly separates…

Reasoning-enhanced large language models (RLLMs), whether explicitly trained for reasoning or prompted via chain-of-thought (CoT), have achieved state-of-the-art performance on many complex reasoning tasks. However, we uncover a surprising…

Predictive safety filters enable the integration of potentially unsafe learning-based control approaches and humans into safety-critical systems. In addition to simple constraint satisfaction, many control problems involve additional…

Large language models (LLMs) are increasingly used to generate multiple-choice questions (MCQs), where correct answers should ideally be uniformly distributed across options. However, we observe that LLMs exhibit systematic position biases…

Language model (LM) "reasoning", commonly described as Chain-of-Thought or test-time scaling, often improves benchmark performance, but the dynamics underlying this process remain poorly understood. We study these dynamics through the lens…

This work characterizes large language models' chain-of-thought generation as a structured trajectory through representation space. We show that mathematical reasoning traverses functionally ordered, step-specific subspaces that become…

Model steering, which involves intervening on hidden representations at inference time, has emerged as a lightweight alternative to finetuning for precisely controlling large language models. While steering efficacy has been widely studied,…

STEM education researchers are often interested in identifying moments of students' mechanistic reasoning for deeper analysis, but have limited capacity to search through many team conversation transcripts to find segments with a high…

As Large Language Models (LLMs) expand in capability and application scope, their trustworthiness becomes critical. A vital risk is intrinsic deception, wherein models strategically mislead users to achieve their own objectives. Existing…

Large language models (LLMs) have demonstrated impressive capabilities in various reasoning tasks, aided by techniques like chain-of-thought prompting that elicits verbalized reasoning. However, LLMs often generate text with obvious…

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…

Recent advances in explainable recommendations have explored the integration of language models to analyze natural language rationales for user-item interactions. Despite their potential, existing methods often rely on ID-based…

Large language models (LLMs) can perform reasoning computations both internally within their latent space and externally by generating explicit token sequences like chains of thought. Significant progress in enhancing reasoning abilities…

Large Language Models (LLMs) have achieved remarkable success in tasks requiring complex reasoning, such as code generation, mathematical problem solving, and algorithmic synthesis -- especially when aided by reasoning tokens and…

Self-training approach for large language models (LLMs) improves reasoning abilities by training the models on their self-generated rationales. Previous approaches have labeled rationales that produce correct answers for a given question as…

Chain-of-Thought (CoT) has become a cornerstone of reasoning in large language models, yet its effectiveness is constrained by the limited expressiveness of discrete token sampling. Recent latent reasoning approaches attempt to alleviate…

Best-of-$N$ reasoning improves the accuracy of language models in solving complex tasks by sampling multiple candidate solutions and then selecting the best one based on some criteria. A critical bottleneck for this strategy is the output…

Recent works have shown that chain-of-thought (CoT) prompting can elicit language models to solve complex reasoning tasks, step-by-step. However, prompt-based CoT methods are dependent on very large models such as GPT-3 175B which are…

While reasoning-based large language models excel at complex tasks through an internal, structured thinking process, a concerning phenomenon has emerged that such a thinking process can aggregate social stereotypes, leading to biased…

Human reasoning involves different strategies, each suited to specific problems. Prior work shows that large language model (LLMs) tend to favor a single reasoning strategy, potentially limiting their effectiveness in diverse reasoning…