English
Related papers

Related papers: Stratified Certification for k-Induction

200 papers

Training language models to solve complex mathematical problems benefits from curriculum learning progressively training on simpler subproblems. However, existing decomposition methods are often heuristic, offering no guarantees that…

Artificial Intelligence · Computer Science 2026-02-10 Kaleem Ullah Qasim , Jiashu Zhang , Hao Li , Muhammad Kafeel Shaheen

Computational methods to aid journalists in the task often require adapting a model to specific domains and generating explanations. However, most automated fact-checking methods rely on three-class datasets, which do not accurately reflect…

Computation and Language · Computer Science 2024-10-08 Jing Yang , Anderson Rocha

Large Language Models (LLMs) often rely on test-time scaling via parallel decoding (for example, 512 samples) to boost reasoning accuracy, but this incurs substantial compute. We introduce CoRefine, a confidence-guided self-refinement…

Artificial Intelligence · Computer Science 2026-02-10 Chen Jin , Ryutaro Tanno , Tom Diethe , Philip Teare

Delayed separation of survival curves is a common occurrence in confirmatory studies in immuno-oncology. Many novel statistical methods that aim to efficiently capture potential long-term survival improvements have been proposed in recent…

Methodology · Statistics 2022-01-26 Dominic Magirr , José L. Jiménez

Even for domain experts, it is a non-trivial task to verify a scientific claim by providing supporting or refuting evidence rationales. The situation worsens as misinformation is proliferated on social media or news websites, manually or…

Computation and Language · Computer Science 2025-05-19 Xiangci Li , Gully Burns , Nanyun Peng

Multi-hop QA benchmarks frequently reward Large Language Models (LLMs) for spurious correctness, masking ungrounded or flawed reasoning steps. To shift toward rigorous reasoning, we propose SAFE, a dynamic benchmarking framework that…

Computation and Language · Computer Science 2026-04-03 Daeyong Kwon , Soyoung Yoon , Seung-won Hwang

Supervised Fine-Tuning (SFT) is a standard approach for injecting domain knowledge into Large Language Models (LLMs). However, relying on validation perplexity to monitor training is often insufficient, as it confounds stylistic mimicry…

Computation and Language · Computer Science 2026-01-08 Soheil Zibakhsh Shabgahi , Pedram Aghazadeh , Farinaz Koushanfar

As foundation models continue to scale, the size of trained models grows exponentially, presenting significant challenges for their evaluation. Current evaluation practices involve curating increasingly large datasets to assess the…

Machine Learning · Statistics 2025-05-08 Ganghua Wang , Zhaorun Chen , Bo Li , Haifeng Xu

Many procedures for SAT-related problems, in particular for those requiring the complete enumeration of satisfying truth assignments, rely their efficiency and effectiveness on the detection of (possibly small) partial assignments…

Logic in Computer Science · Computer Science 2025-05-27 Roberto Sebastiani

Fact-checking real-world claims, particularly numerical claims, is inherently complex that require multistep reasoning and numerical reasoning for verifying diverse aspects of the claim. Although large language models (LLMs) including…

Computation and Language · Computer Science 2025-09-29 Primakov Chungkham , V Venktesh , Vinay Setty , Avishek Anand

Large language models (LLMs) have demonstrated significant potential in formal theorem proving, yet state-of-the-art performance often necessitates prohibitive test-time compute via massive roll-outs or extended context windows. In this…

Machine Learning · Computer Science 2026-04-22 Guchan Li , Rui Tian , Hongning Wang

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

Quantification is the machine learning task of estimating test-data class proportions that are not necessarily similar to those in training. Apart from its intrinsic value as an aggregate statistic, quantification output can also be used to…

Machine Learning · Computer Science 2016-06-06 Aykut Firat

The success of Deep Learning and its potential use in many safety-critical applications has motivated research on formal verification of Neural Network (NN) models. Despite the reputation of learned NN models to behave as black boxes and…

Artificial Intelligence · Computer Science 2018-05-23 Rudy Bunel , Ilker Turkaslan , Philip H. S. Torr , Pushmeet Kohli , M. Pawan Kumar

Step-by-step verifiers -- also known as process reward models (PRMs) -- are a key ingredient for test-time scaling. PRMs require step-level supervision, making them expensive to train. This work aims to build data-efficient PRMs as…

Machine Learning · Computer Science 2025-12-09 Muhammad Khalifa , Rishabh Agarwal , Lajanugen Logeswaran , Jaekyeom Kim , Hao Peng , Moontae Lee , Honglak Lee , Lu Wang

Teaching language models to use tools is an important milestone towards building general assistants, but remains an open problem. While there has been significant progress on learning to use specific tools via fine-tuning, language models…

Computation and Language · Computer Science 2024-03-14 Dheeraj Mekala , Jason Weston , Jack Lanchantin , Roberta Raileanu , Maria Lomeli , Jingbo Shang , Jane Dwivedi-Yu

The reasoning capabilities of large language models (LLMs) have been significantly improved through reinforcement learning (RL). Nevertheless, LLMs still struggle to consistently verify their own reasoning traces. This raises the research…

Machine Learning · Computer Science 2025-11-20 Xiaoxuan Wang , Bo Liu , Song Jiang , Jingzhou Liu , Jingyuan Qi , Xia Chen , Baosheng He

The complexity of software in embedded systems has increased significantly over the last years so that software verification now plays an important role in ensuring the overall product quality. In this context, SAT-based bounded model…

Software Engineering · Computer Science 2009-11-20 Lucas Cordeiro , Bernd Fischer , Joao Marques-Silva

Reinforcement learning with verifiable rewards (RLVR) has demonstrated promising potential to enhance the reasoning capabilities of large language models (LLMs) in domains such as mathematics and coding. However, its applications on…

Computation and Language · Computer Science 2026-05-19 Zhonghang Yuan , Zhefan Wang , Fang Hu , Zihong Chen , Jinzhe Li , Gang Li , Jie Ying , Huanjun Kong , Songyang Zhang , Nanqing Dong

Deep learning has emerged as an effective approach for creating modern software systems, with neural networks often surpassing hand-crafted systems. Unfortunately, neural networks are known to suffer from various safety and security issues.…

Machine Learning · Computer Science 2021-01-19 Guy Amir , Haoze Wu , Clark Barrett , Guy Katz