Related papers: Reflective Confidence: Correcting Reasoning Flaws …
Although contemporary large language models (LMs) demonstrate impressive question-answering capabilities, their answers are typically the product of a single call to the model. This entails an unwelcome degree of opacity and compromises…
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…
Reward models play a fundamental role in aligning large language models with human preferences. Existing methods predominantly follow two paradigms: scalar discriminative preference models, which are efficient but lack interpretability, and…
Large language models (LLMs) often improve their performance in downstream tasks when they generate Chain of Thought reasoning text before producing an answer. We investigate how LLMs recover from errors in Chain of Thought. Through…
Reward Models (RMs) are critical components in the Reinforcement Learning from Human Feedback (RLHF) pipeline, directly determining the alignment quality of Large Language Models (LLMs). Recently, Generative Reward Models (GRMs) have…
Recent advancements in Large Language Models (LLMs) have significantly improved their problem-solving capabilities. However, these models still struggle when faced with complex multi-step reasoning tasks. In this paper, we propose the…
Large language models (LLMs) have been increasingly used to interact with external environments (e.g., games, compilers, APIs) as goal-driven agents. However, it remains challenging for these language agents to quickly and efficiently learn…
Test-time scaling via explicit reasoning trajectories significantly boosts large language model (LLM) performance but often triggers overthinking. To explore this, we analyze reasoning through two lenses: Reasoning Length Dynamics, which…
While slow-thinking large language models (LLMs) exhibit reflection-like reasoning, commonly referred to as the "aha moment:, their ability to generate informative critiques and refine prior solutions remains limited. In this paper, we…
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…
Reflection is widely recognized as a cornerstone of student development, fostering critical thinking, self-regulation, and deep conceptual understanding. Traditionally, reflective skills have been cultivated through structured feedback,…
The ability to reason is one of the most fundamental capabilities of large language models (LLMs), enabling a wide range of downstream tasks through sophisticated problem-solving. A critical aspect of this is code reasoning, which involves…
Large Reasoning Models (LRMs) like DeepSeek-R1 and OpenAI-o1 have demonstrated remarkable reasoning capabilities, raising important questions about their biases in LLM-as-a-judge settings. We present a comprehensive benchmark comparing…
Large Language Models (LLMs) have emerged as a groundbreaking technology with their unparalleled text generation capabilities across various applications. Nevertheless, concerns persist regarding the accuracy and appropriateness of their…
Mitigating hallucinations in Large Language Models (LLMs) is critical for their reliable deployment. Existing methods typically fine-tune LLMs to abstain from answering questions beyond their knowledge scope. However, these methods often…
In-context learning with large language models (LLMs) excels at adapting to various tasks rapidly. However, its success hinges on carefully selecting demonstrations, which remains an obstacle in practice. Current approaches to this problem…
Recently, large language models (LLMs) enhanced by self-reflection have achieved promising performance on machine translation. The key idea is guiding LLMs to generate translation with human-like feedback. However, existing self-reflection…
For Large Language Models (LLMs) to be reliably deployed, models must effectively know when not to answer: abstain. Reasoning models, in particular, have gained attention for impressive performance on complex tasks. However, reasoning…
Large reasoning models (LRMs) have demonstrated impressive capabilities in domains like mathematics and program synthesis. Despite their strong performance, LRMs often exhibit overthinking -- excessive and redundant reasoning steps that…
Recent advancements in large language models (LLMs) have catalyzed the rise of reasoning-intensive inference paradigms, where models perform explicit step-by-step reasoning before generating final answers. While such approaches improve…