English
Related papers

Related papers: Certified Self-Consistency: Statistical Guarantees…

200 papers

Test-time training (TTT) has recently emerged as a promising method to improve the reasoning abilities of large language models (LLMs), in which the model directly learns from test data without access to labels. However, this reliance on…

Machine Learning · Computer Science 2026-03-17 Vanshaj Khattar , Md Rafi ur Rashid , Moumita Choudhury , Jing Liu , Toshiaki Koike-Akino , Ming Jin , Ye Wang

Self-supervised learning (SSL) is often deployed under changing information, such as shorter histories, missing features, or partially observed images. In these settings, predictions from coarse and refined views should be coherent: before…

Machine Learning · Computer Science 2026-05-13 Moritz Gögl , Hanwen Xing , Christopher Yau

Increasing test-time computation is a straightforward approach to enhancing the quality of responses in Large Language Models (LLMs). While Best-of-N sampling and Self-Consistency with majority voting are simple and effective, they require…

Machine Learning · Computer Science 2025-03-04 Chengsong Huang , Langlin Huang , Jixuan Leng , Jiacheng Liu , Jiaxin Huang

Test-time Reinforcement Learning (TTRL) has shown promise in adapting foundation models for complex tasks at test-time, resulting in large performance improvements. TTRL leverages an elegant two-phase sampling strategy: first,…

Machine Learning · Computer Science 2025-11-11 Peyman Hosseini , Ondrej Bohdal , Taha Ceritli , Ignacio Castro , Matthew Purver , Mete Ozay , Umberto Michieli

Reinforcement learning (RL) is central to improving reasoning in large language models (LLMs) but typically requires ground-truth rewards. Test-Time Reinforcement Learning (TTRL) removes this need by using majority-vote rewards, but relies…

Machine Learning · Computer Science 2025-10-06 Aleksei Arzhantsev , Otmane Sakhi , Flavian Vasile

Large Language Models (LLMs) have shown impressive performance in mathematical reasoning tasks when guided by Chain-of-Thought (CoT) prompting. However, they tend to produce highly confident yet incorrect outputs, which poses significant…

Machine Learning · Computer Science 2025-06-11 Zhenjiang Mao , Artem Bisliouk , Rohith Reddy Nama , Ivan Ruchkin

A standard technique for scaling inference-time reasoning is Self-Consistency, whereby multiple candidate answers are sampled from an LLM and the most common answer is selected. More recently, it has been shown that weighted majority voting…

Artificial Intelligence · Computer Science 2026-05-11 James Petullo , Sonny George , Dylan Cashman , Nianwen Xue

Self-consistency decoding enhances LLMs' performance on reasoning tasks by sampling diverse reasoning paths and selecting the most frequent answer. However, it is computationally expensive, as sampling many of these (lengthy) paths is…

Computation and Language · Computer Science 2025-09-30 Amir Taubenfeld , Tom Sheffer , Eran Ofek , Amir Feder , Ariel Goldstein , Zorik Gekhman , Gal Yona

Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability. Yet, outcome-based reward often incentivizes models to be overconfident, leading to…

Machine Learning · Computer Science 2026-04-28 Liaoyaqi Wang , Chunsheng Zuo , William Jurayj , Benjamin Van Durme , Anqi Liu

Large Language Models (LLMs) increasingly rely on long-form, multi-step reasoning to solve complex tasks such as mathematical problem solving and scientific question answering. Despite strong performance, existing confidence estimation…

Computation and Language · Computer Science 2026-01-21 Zhenjiang Mao , Anirudhh Venkat , Artem Bisliouk , Akshat Kothiyal , Sindhura Kumbakonam Subramanian , Saithej Singhu , Ivan Ruchkin

In-Context Reinforcement Learning (ICRL) enables Large Language Models (LLMs) to learn online from external rewards directly within the context window. However, a central challenge in ICRL is reward estimation, as models typically lack…

Computation and Language · Computer Science 2026-04-02 Wenxuan Jiang , Yuxin Zuo , Zijian Zhang , Xuecheng Wu , Zining Fan , Wenxuan Liu , Li Chen , Xiaoyu Li , Xuezhi Cao , Xiaolong Jin , Ninghao Liu

Test-time scaling improves large language models' (LLMs) performance by allocating more compute budget during inference. To achieve this, existing methods often require intricate modifications to prompting and sampling strategies. In this…

Computation and Language · Computer Science 2025-11-04 Junqi Jiang , Tom Bewley , Salim I. Amoukou , Francesco Leofante , Antonio Rago , Saumitra Mishra , Francesca Toni

Self-Consistency, a widely-used decoding strategy, significantly boosts the reasoning capabilities of Large Language Models (LLMs). However, it depends on the plurality voting rule, which focuses on the most frequent answer while…

Computation and Language · Computer Science 2025-09-18 Siyuan Huang , Zhiyuan Ma , Jintao Du , Changhua Meng , Weiqiang Wang , Zhouhan Lin

Continuous-time reinforcement learning (CTRL) provides a natural framework for sequential decision-making in dynamic environments where interactions evolve continuously over time. While CTRL has shown growing empirical success, its ability…

Machine Learning · Computer Science 2025-12-04 Runze Zhao , Yue Yu , Ruhan Wang , Chunfeng Huang , Dongruo Zhou

Accurately gauging the confidence level of Large Language Models' (LLMs) predictions is pivotal for their reliable application. However, LLMs are often uncalibrated inherently and elude conventional calibration techniques due to their…

Current techniques for post-training Large Language Models (LLMs) rely either on costly human supervision or on external verifiers to boost performance on tasks such as mathematical reasoning and code generation. However, as LLMs improve…

Computation and Language · Computer Science 2026-01-21 Mukesh Ghimire , Aosong Feng , Liwen You , Youzhi Luo , Fang Liu , Xuan Zhu

Self-consistency (SC) is a widely used test-time inference technique for improving performance in chain-of-thought reasoning. It involves generating multiple responses, or samples from a large language model (LLM) and selecting the most…

Machine Learning · Computer Science 2025-11-18 Austin Feng , Marius Alonso , Ambroise Odonnat

A popular approach for improving the correctness of output from large language models (LLMs) is Self-Consistency - poll the LLM multiple times and output the most frequent solution. Existing Self-Consistency techniques always generate a…

Computation and Language · Computer Science 2023-11-17 Pranjal Aggarwal , Aman Madaan , Yiming Yang , Mausam

Large language models (LLMs) have exhibited remarkable ability in code generation. However, generating the correct solution in a single attempt still remains a challenge. Prior works utilize verification properties in software engineering…

Computation and Language · Computer Science 2024-07-03 Baizhou Huang , Shuai Lu , Weizhu Chen , Xiaojun Wan , Nan Duan

Recent advancements in Large Language Models have yielded significant improvements in complex reasoning tasks such as mathematics and programming. However, these models remain heavily dependent on annotated data and exhibit limited…

Machine Learning · Computer Science 2025-09-01 Jia Liu , ChangYi He , YingQiao Lin , MingMin Yang , FeiYang Shen , ShaoGuo Liu