Related papers: Rethinking Dense Sequential Chains: Reasoning Lang…

We revisit test-time scaling for language model reasoning and ask a fundamental question: at equal token budget and compute, is it better to run multiple independent chains in parallel, or to run fewer chains that iteratively refine through…

Autoregressive (AR) language models enforce a fixed left-to-right generation order, creating a fundamental limitation when the required output structure conflicts with natural reasoning (e.g., producing answers before explanations due to…

Modern language models (LMs) exhibit strong deductive reasoning capabilities, yet standard evaluations emphasize correctness while overlooking a key aspect of reasoning: efficiency. In real-world reasoning scenarios, much of the available…

Chain-of-thought (CoT) decoding enables language models to improve reasoning performance at the cost of high generation latency in decoding. Recent proposals have explored variants of contemplation tokens, a term we introduce that refers to…

To augment language models with the ability to reason, researchers usually prompt or finetune them to produce chain of thought reasoning steps before producing the final answer. However, although people use natural language to reason…

Large reasoning models achieve high accuracy through extended chain-of-thought but generate 5--8 more tokens than necessary, applying verbose reasoning uniformly regardless of problem difficulty. We propose Hint Tuning, a data-efficient…

Chain-of-thought (CoT) reasoning has been proposed as a transparency mechanism for large language models in safety-critical deployments, yet its effectiveness depends on faithfulness (whether models accurately verbalize the factors that…

Chain-of-thought prompting has demonstrated remarkable performance on various natural language reasoning tasks. However, it tends to perform poorly on tasks which requires solving problems harder than the exemplars shown in the prompts. To…

Recent large language models achieve strong reasoning performance by generating detailed chain-of-thought traces, but this often leads to excessive token use and high inference latency. Existing efficiency approaches typically focus on…

Recent advances in reasoning-focused Large Language Models (LLMs) have introduced Chain-of-Thought (CoT) traces - intermediate reasoning steps generated before a final answer. These traces, as in DeepSeek R1, guide inference and train…

Current frontier large-language models rely on reasoning to achieve state-of-the-art performance. Many existing interpretability are limited in this area, as standard methods have been designed to study single forward passes of a model…

Chain-of-Thought (CoT) prompting has emerged as a foundational technique for eliciting reasoning from Large Language Models (LLMs), yet the robustness of this approach to corruptions in intermediate reasoning steps remains poorly…

Large language models (LLMs) increasingly solve difficult problems by producing "reasoning traces" before emitting a final response. However, it remains unclear how accuracy and decision commitment evolve along a reasoning trajectory, and…

Large language models excel on static benchmarks, but their ability as self-learning agents in dynamic environments remains unclear. We evaluate three prompting strategies: self-reflection, heuristic mutation, and planning across dynamic…

Reasoning language models have demonstrated remarkable capabilities on challenging tasks by generating elaborate chain-of-thought (CoT) solutions. However, such lengthy generation shifts the inference bottleneck from compute-bound to…

Prompt Engineering has garnered significant attention for enhancing the performance of large language models across a multitude of tasks. Techniques such as the Chain-of-Thought not only bolster task performance but also delineate a clear…

Chain-of-Thought (CoT) reasoning has become a foundation for eliciting multi-step reasoning in large language models, but recent studies show that its benefits do not scale monotonically with chain length: while longer CoT generally enables…

Ranking responses for a given dialogue context is a popular benchmark in which the setup is to re-rank the ground-truth response over a limited set of $n$ responses, where $n$ is typically 10. The predominance of this setup in conversation…

Chain-of-thought prompting (e.g., "Let's think step-by-step") primes large language models to verbalize rationalization for their predictions. While chain-of-thought can lead to dramatic performance gains, benefits appear to emerge only for…

Recently, diffusion models have garnered significant interest in the field of text processing due to their many potential advantages compared to conventional autoregressive models. In this work, we propose Diffusion-of-Thought (DoT), a…