Related papers: STaR: Bootstrapping Reasoning With Reasoning
When writing and talking, people sometimes pause to think. Although reasoning-focused works have often framed reasoning as a method of answering questions or completing agentic tasks, reasoning is implicit in almost all written text. For…
The reasoning abilities of large language models (LLMs) have improved with chain-of-thought (CoT) prompting, allowing models to solve complex tasks stepwise. However, training CoT capabilities requires detailed reasoning data, which is…
Traditional language model-based theorem proving assumes that by training on a sufficient amount of formal proof data, a model will learn to prove theorems. Our key observation is that a wealth of informal information that is not present in…
Table reasoning with large language models (LLMs) plays a critical role in building intelligent systems capable of understanding and analyzing tabular data. Despite recent progress, existing methods still face key limitations: their…
Generating step-by-step "chain-of-thought" rationales has proven effective for improving the performance of large language models on complex reasoning tasks. However, applying such techniques to structured tasks, such as text-to-SQL,…
As AI systems are being integrated more rapidly into diverse and complex real-world environments, the ability to perform holistic reasoning over an implicit query and an image to localize a target is becoming increasingly important.…
Large Language Models (LLMs) have achieved impressive performance across a range of natural language processing tasks. However, recent advances demonstrate that further gains particularly in complex reasoning tasks require more than merely…
Common self-improvement approaches for large language models (LLMs), such as STaR, iteratively fine-tune LLMs on self-generated solutions to improve their problem-solving ability. However, these approaches discard the large amounts of…
Self-taught reasoners (STaRs) enhance the mathematical reasoning abilities of large language models (LLMs) by leveraging self-generated responses for self-training. Recent studies have incorporated reward models to guide response selection…
Large language models (LLMs) demonstrate strong chain-of-thought (CoT) reasoning abilities, while smaller models (<= 3B parameters) significantly underperform on multi-step reasoning tasks. Based on empirical analyses of the Qwen-2.5 model…
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…
In the absence of extensive human-annotated data for complex reasoning tasks, self-improvement -- where models are trained on their own outputs -- has emerged as a primary method for enhancing performance. However, the critical factors…
Self-Taught Reasoners (STaR), synonymously known as Rejection sampling Fine-Tuning (RFT), is an integral part of the training pipeline of self-improving reasoning Language Models (LMs). The self-improving mechanism often employs random…
Large reasoning models (LRMs) achieve state-of-the-art performance by generating long chains-of-thought, but often waste computation on redundant reasoning after the correct answer has already been reached. We introduce Early-Stopping for…
Multimodal large language models excel across diverse domains but struggle with complex visual reasoning tasks. To enhance their reasoning capabilities, current approaches typically rely on explicit search or post-training techniques.…
Multi-hop Question Generation is the task of generating questions which require the reader to reason over and combine information spread across multiple passages using several reasoning steps. Chain-of-thought rationale generation has been…
Large language models (LLMs) can achieve highly effective performance on various reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting as demonstrations. However, the reasoning chains of demonstrations generated by…
Extensive work has shown that the performance and interpretability of commonsense reasoning can be improved via knowledge-augmented reasoning methods, where the knowledge that underpins the reasoning process is explicitly verbalized and…
The internalization of chain-of-thought processes into hidden states has emerged as a highly efficient paradigm for scaling test-time compute. However, existing activation steering methods rely on static control vectors that fail to adapt…
When prompting language models to complete a task, users often leave important aspects unsaid. While asking questions could resolve this ambiguity (GATE; Li et al., 2023), models often struggle to ask good questions. We explore a language…