English
Related papers

Related papers: Reasoning with Sampling: Cutting at Decision Point…

200 papers

Reasoning models have demonstrated remarkable progress in solving complex and logic-intensive tasks by generating extended Chain-of-Thoughts (CoTs) prior to arriving at a final answer. Yet, the emergence of this "slow-thinking" paradigm,…

Computation and Language · Computer Science 2025-09-30 Sicheng Feng , Gongfan Fang , Xinyin Ma , Xinchao Wang

As predictive algorithms grow in popularity, using the same dataset to both train and test a new model has become routine across research, policy, and industry. Sample-splitting attains valid inference on model properties by using separate…

Econometrics · Economics 2025-11-27 Bruno Fava

Recent progress in large language models has led to the emergence of reasoning models, which have shown strong performance on complex tasks through specialized fine-tuning procedures. While these methods reliably improve pass@1 accuracy,…

Machine Learning · Computer Science 2026-05-19 Ngoc-Hieu Nguyen , Parshin Shojaee , Phuc Minh Nguyen , Nan Zhang , Chandan K Reddy , Khoa D Doan , Rui Zhang

Large reasoning models (LRMs) substantially outperform their base LLM counterparts on challenging reasoning benchmarks, yet it remains poorly understood where base models go wrong during token-by-token generation and how to narrow this gap…

Artificial Intelligence · Computer Science 2026-05-19 Changshuo Shen , Leheng Sheng , Yuxin Chen , An Zhang , Xiang Wang

Large reasoning models (LRMs) typically solve reasoning-intensive tasks by generating long chain-of-thought (CoT) traces, leading to substantial inference overhead. We identify a reproducible inference-time phenomenon, termed…

Computation and Language · Computer Science 2026-02-03 Jie Deng , Shining Liang , Jun Li , Hongzhi Li , Yutao Xie

Long samples of text from neural language models can be of poor quality. Truncation sampling algorithms--like top-$p$ or top-$k$ -- address this by setting some words' probabilities to zero at each step. This work provides framing for the…

Computation and Language · Computer Science 2022-10-28 John Hewitt , Christopher D. Manning , Percy Liang

Despite the remarkable advances in language modeling, current mainstream decoding methods still struggle to generate texts that align with human texts across different aspects. In particular, sampling-based methods produce less-repetitive…

Computation and Language · Computer Science 2024-06-06 Haozhe Ji , Pei Ke , Hongning Wang , Minlie Huang

Recent advances in large language models (LLMs) have enabled automatic generation of chain-of-thought (CoT) reasoning, leading to strong performance on tasks such as math and code. However, when reasoning steps reflect social stereotypes…

Computation and Language · Computer Science 2025-09-23 Xuyang Wu , Jinming Nian , Ting-Ruen Wei , Zhiqiang Tao , Hsin-Tai Wu , Yi Fang

Reasoning LLMs often spend substantial tokens on long intermediate reasoning traces (e.g., chain-of-thought) when solving new problems. We propose to summarize and store reusable reasoning skills distilled from extensive deliberation and…

Artificial Intelligence · Computer Science 2026-04-28 Guangxiang Zhao , Qilong Shi , Xusen Xiao , Xiangzheng Zhang , Tong Yang , Lin Sun

Pre-trained language models (LMs) are able to perform complex reasoning without explicit fine-tuning. To understand how pre-training with a next-token prediction objective contributes to the emergence of such reasoning capability, we…

Machine Learning · Computer Science 2024-06-24 Xinyi Wang , Alfonso Amayuelas , Kexun Zhang , Liangming Pan , Wenhu Chen , William Yang Wang

The inherent capabilities of a language model (LM) and the reasoning strategies it employs jointly determine its performance in reasoning tasks. While test-time scaling is regarded as an effective approach to tackling complex reasoning…

Computation and Language · Computer Science 2025-05-27 Zhihong Pan , Kai Zhang , Yuze Zhao , Yupeng Han

Large reasoning models achieve strong performance on complex tasks by generating extended chains of thought, but they often "overthink": continuing to reason long after they have enough information to answer correctly. This wastes…

Computation and Language · Computer Science 2025-12-08 Ömer Faruk Akgül , Yusuf Hakan Kalaycı , Rajgopal Kannan , Willie Neiswanger , Viktor Prasanna

When artificial neural networks have demonstrated exceptional practical success in a variety of domains, investigations into their theoretical characteristics, such as their approximation power, statistical properties, and generalization…

Machine Learning · Statistics 2023-10-06 Shijin Gong , Xinyu Zhang

Recent work has shown that distilling reasoning traces from a larger teacher model via supervised finetuning outperforms reinforcement learning with the smaller student model alone (Guo et al. 2025). However, there has not been a systematic…

Computation and Language · Computer Science 2025-07-03 Yang Li , Youssef Emad , Karthik Padthe , Jack Lanchantin , Weizhe Yuan , Thao Nguyen , Jason Weston , Shang-Wen Li , Dong Wang , Ilia Kulikov , Xian Li

Compute-efficient training of language models has become an important issue. We consider data pruning for data-efficient training of LLMs. In this work, we consider a data pruning method based on information entropy. We propose that the…

Artificial Intelligence · Computer Science 2024-12-13 Minsang Kim , Seungjun Baek

Reasoning models have demonstrated exceptional performance in tasks such as mathematics and logical reasoning, primarily due to their ability to engage in step-by-step thinking during the reasoning process. However, this often leads to…

Artificial Intelligence · Computer Science 2025-10-23 Yuqiao Tan , Shizhu He , Kang Liu , Jun Zhao

Latent reasoning represents a new development in Transformer language models that has shown potential in compressing reasoning lengths compared to chain-of-thought reasoning. By directly passing the information-rich previous final latent…

Machine Learning · Computer Science 2025-11-27 Alex Ning , Yen-Ling Kuo , Gabe Gomes

We study the task of prompting large-scale language models to perform multi-step reasoning. Existing work shows that when prompted with a chain of thoughts (CoT), sequences of short sentences describing intermediate reasoning steps towards…

Computation and Language · Computer Science 2023-01-31 Yao Fu , Hao Peng , Ashish Sabharwal , Peter Clark , Tushar Khot

Large Reasoning Language Models (LRLMs) demonstrate impressive capabilities on complex tasks by utilizing long Chain-of-Thought reasoning. However, they are prone to overthinking, which generates redundant reasoning steps that degrade both…

Computation and Language · Computer Science 2026-03-17 Weixin Guan , Liang Li , Jiapeng Liu , Bing Li , Peng Fu , Chengyang Fang , Xiaoshuai Hao , Can Ma , Weiping Wang

Fine-tuning pretrained language models can improve task performance while subtly altering the evidence a model relies on. We propose a training-time interpretability view that tracks token-level attributions across finetuning epochs. We…

Artificial Intelligence · Computer Science 2026-01-21 Sahil Rajesh Dhayalkar