English
Related papers

Related papers: Asking LLMs to Verify First is Almost Free Lunch

200 papers

Intrinsic self-correct was a method that instructed large language models (LLMs) to verify and correct their responses without external feedback. Unfortunately, the study concluded that the LLMs could not self-correct reasoning yet. We find…

Computation and Language · Computer Science 2024-10-04 Zhenyu Wu , Qingkai Zeng , Zhihan Zhang , Zhaoxuan Tan , Chao Shen , Meng Jiang

While LLM-based agents are able to tackle a wide variety of code reasoning questions, the answers are not always correct. This prevents the agent from being useful in situations where high precision is desired: (1) helping a software…

Software Engineering · Computer Science 2025-11-17 Meghana Sistla , Gogul Balakrishnan , Pat Rondon , José Cambronero , Michele Tufano , Satish Chandra

Large Language Models (LLMs) can generate useful code, but often the code they generate cannot be trusted to be sound. In this paper, we present VerMCTS, an approach to begin to resolve this issue by generating verified programs in Dafny…

Recent work on reinforcement learning with verifiable rewards (RLVR) has shown that large language models (LLMs) can be substantially improved using outcome-level verification signals, such as unit tests for code or exact-match checks for…

Computation and Language · Computer Science 2026-01-27 Massimiliano Pronesti , Anya Belz , Yufang Hou

Large language models (LLMs) demonstrate their promise in tackling complicated practical challenges by combining action-based policies with chain of thought (CoT) reasoning. Having high-quality prompts on hand, however, is vital to the…

Machine Learning · Computer Science 2024-03-01 Xue Yan , Yan Song , Xinyu Cui , Filippos Christianos , Haifeng Zhang , David Henry Mguni , Jun Wang

Large language models (LLMs) have shown increasing competence in solving mathematical reasoning problems. However, many open-source LLMs still struggle with errors in calculation and semantic understanding during intermediate reasoning…

Computation and Language · Computer Science 2024-12-18 Vernon Y. H. Toh , Deepanway Ghosal , Soujanya Poria

Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. However, current training recipes lack robust CoT reasoning data, relying on datasets dominated by short…

Artificial Intelligence · Computer Science 2024-10-22 Ruohong Zhang , Bowen Zhang , Yanghao Li , Haotian Zhang , Zhiqing Sun , Zhe Gan , Yinfei Yang , Ruoming Pang , Yiming Yang

Previous works have demonstrated the effectiveness of Chain-of-Thought (COT) prompts and verifiers in guiding Large Language Models (LLMs) through the space of reasoning. However, most such studies either use a fine-tuned verifier or rely…

Computation and Language · Computer Science 2025-01-24 Jishnu Ray Chowdhury , Cornelia Caragea

Existing informal language-based (e.g., human language) Large Language Models (LLMs) trained with Reinforcement Learning (RL) face a significant challenge: their verification processes, which provide crucial training signals, are neither…

Computation and Language · Computer Science 2025-10-14 Chuanhao Yan , Fengdi Che , Xuhan Huang , Xu Xu , Xin Li , Yizhi Li , Xingwei Qu , Jingzhe Shi , Chenghua Lin , Yaodong Yang , Binhang Yuan , Hang Zhao , Yu Qiao , Bowen Zhou , Jie Fu

One of the most pressing societal issues is the fight against false news. The false claims, as difficult as they are to expose, create a lot of damage. To tackle the problem, fact verification becomes crucial and thus has been a topic of…

Computation and Language · Computer Science 2022-07-01 Pawan Kumar Sahu , Saksham Aggarwal , Taneesh Gupta , Gyanendra Das

Formal Property Verification (FPV), using SystemVerilog Assertions (SVA), is crucial for ensuring the completeness of design with respect to the specification. However, writing SVA is a laborious task and has a steep learning curve. In this…

Hardware Architecture · Computer Science 2024-11-26 Mohammad Shahidzadeh , Behnam Ghavami , Steve Wilton , Lesley Shannon

While chain-of-thought (CoT) prompting improves reasoning in large language models, its effectiveness in vision-language models (VLMs) remains limited due to over-reliance on textual cues and memorized knowledge. To investigate the visual…

Computer Vision and Pattern Recognition · Computer Science 2025-04-09 Charles Corbière , Simon Roburin , Syrielle Montariol , Antoine Bosselut , Alexandre Alahi

Claim verification is essential in combating misinformation, and large language models (LLMs) have recently emerged in this area as powerful tools for assessing the veracity of claims using external knowledge. Existing LLM-based methods for…

Artificial Intelligence · Computer Science 2025-05-20 Zhi Zheng , Wee Sun Lee

Despite the strong performance of large language models (LLMs) in tasks like mathematical reasoning, their practical use is limited by high computational demands and proprietary restrictions. Chain-of-thought (CoT) and program-of-thought…

Computation and Language · Computer Science 2024-11-11 Mohammad Ghiasvand Mohammadkhani

During reasoning in vision-language models (VLMs), false positive (FP) reasoning occurs when a model produces the correct answer but follows an incorrect reasoning path, resulting in undermined reasoning reliability. Existing approaches…

Computer Vision and Pattern Recognition · Computer Science 2025-11-06 Ben Zhang , LuLu Yu , Lei Gao , QuanJiang Guo , Jing Liu , Hui Gao

Test-time scaling (TTS), which involves dynamic allocation of compute during inference, offers a promising way to improve reasoning in large language models. While existing TTS methods work well, they often rely on long decoding paths or…

Computation and Language · Computer Science 2025-05-26 Aradhye Agarwal , Ayan Sengupta , Tanmoy Chakraborty

Self-improvement at scale has been a longstanding goal for reasoning models, and there are two natural places to do it: at test time, through verification-refinement (V-R) loops; and at training time, through self-training methods. Both are…

Machine Learning · Computer Science 2026-05-29 Chen Henry Wu , Aditi Raghunathan

One way to enhance the reasoning capability of Large Language Models (LLMs) is to conduct Supervised Fine-Tuning (SFT) using Chain-of-Thought (CoT) annotations. This approach does not show sufficiently strong generalization ability,…

Computation and Language · Computer Science 2024-12-16 Trung Quoc Luong , Xinbo Zhang , Zhanming Jie , Peng Sun , Xiaoran Jin , Hang Li

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…

Machine Learning · Computer Science 2024-08-15 Arian Hosseini , Xingdi Yuan , Nikolay Malkin , Aaron Courville , Alessandro Sordoni , Rishabh Agarwal

In recent years, Large language models (LLMs) have garnered significant attention due to their superior performance in complex reasoning tasks. However, recent studies may diminish their reasoning capabilities markedly when problem…

Computation and Language · Computer Science 2025-05-26 Ming Jiang , Tingting Huang , Biao Guo , Yao Lu , Feng Zhang