VerifyBench: A Systematic Benchmark for Evaluating Reasoning Verifiers Across Domains

• URL: http://arxiv.org/abs/2507.09884v3
• Date: Sat, 26 Jul 2025 11:17:08 GMT
• Title: VerifyBench: A Systematic Benchmark for Evaluating Reasoning Verifiers Across Domains
• Authors: Xuzhao Li, Xuchen Li, Shiyu Hu, Yongzhen Guo, Wentao Zhang,
• Abstract summary: Large language models rely on reinforcement learning to enhance their reasoning capabilities through feedback.<n>Existing research focuses on building better verifiers, yet a systematic evaluation of different types of verifiers' performance remains lacking.<n>We construct 4,000 expert-level questions covering mathematics, physics, chemistry, and biology.<n>Each question is equipped with reference answers and diverse responses.
• Score: 19.579511315215424
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) increasingly rely on reinforcement learning (RL) to enhance their reasoning capabilities through feedback. A critical challenge is verifying the consistency of model-generated responses and reference answers, since these responses are often lengthy, diverse, and nuanced. Rule-based verifiers struggle with complexity, prompting the use of model-based verifiers. However, specialized verifiers lack flexibility, while general LLM judges can be inconsistent. Existing research primarily focuses on building better verifiers, yet a systematic evaluation of different types of verifiers' performance across domains remains lacking, severely constraining the reliable development of Reinforcement Learning with Verifiable Reward (RLVR). To address this, we propose VerifyBench--a cross-domain comprehensive benchmark for systematically evaluating verifiers. We construct 4,000 expert-level questions covering mathematics, physics, chemistry, and biology. Each question is equipped with reference answers and diverse responses. The reliability of the evaluation is ensured through a rigorous annotation process conducted by a multidisciplinary expert team. We design a four-dimensional experimental framework to comprehensively compare the performance boundaries of specialized verifiers and general LLMs under combined conditions of extracted answers vs. complete responses, and short vs. long outputs. Our evaluation uncovers fundamental trade-offs in verifiers: while specialized verifiers achieve leading accuracy, they exhibit deficiencies in recall; general models show stronger inclusivity but unstable precision. More importantly, we discover verifiers' high sensitivity to input structure and inherent limitations in cross-domain generalization, providing critical insights into the bottlenecks of current verifier technology.

Related papers

• Multimodal Fact-Level Attribution for Verifiable Reasoning [80.60864342985748]
  Multimodal large language models (MLLMs) are increasingly used for real-world tasks involving multi-step reasoning and long-form generation.<n>Existing multimodal grounding benchmarks and evaluation methods fail to assess attribution in complex multimodal reasoning.<n>We introduce MuRGAt, a benchmark for evaluating fact-level multimodal attribution in settings that require reasoning beyond direct observation.
  arXiv  Detail & Related papers  (2026-02-12T03:10:02Z)
• Towards Comprehensive Stage-wise Benchmarking of Large Language Models in Fact-Checking [64.97768177044355]
  Large Language Models (LLMs) are increasingly deployed in real-world fact-checking systems.<n>We present FactArena, a fully automated arena-style evaluation framework.<n>Our analyses reveal significant discrepancies between static claim-verification accuracy and end-to-end fact-checking competence.
  arXiv  Detail & Related papers  (2026-01-06T02:51:56Z)
• FAIR-RAG: Faithful Adaptive Iterative Refinement for Retrieval-Augmented Generation [0.0]
  We introduce FAIR-RAG, a novel agentic framework that transforms the standard RAG pipeline into a dynamic, evidence-driven reasoning process.<n>We conduct experiments on challenging multi-hop QA benchmarks, including HotpotQA, 2WikiMultiHopQA, and MusiQue.<n>Our work demonstrates that a structured, evidence-driven refinement process with explicit gap analysis is crucial for unlocking reliable and accurate reasoning in advanced RAG systems.
  arXiv  Detail & Related papers  (2025-10-25T15:59:33Z)
• Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense [36.71358559780692]
  HERO is a reinforcement learning framework that integrates verifier signals with reward-model scores in a structured way.<n> HERO consistently outperforms RM-only and verifier-only baselines, with strong gains on both verifiable and hard-to-verify tasks.
  arXiv  Detail & Related papers  (2025-10-08T17:09:41Z)
• Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics [89.1999907891494]
  We present WebDetective, a benchmark of hint-free multi-hop questions paired with a controlled Wikipedia sandbox.<n>Our evaluation of 25 state-of-the-art models reveals systematic weaknesses across all architectures.<n>We develop an agentic workflow, EvidenceLoop, that explicitly targets the challenges our benchmark identifies.
  arXiv  Detail & Related papers  (2025-10-01T07:59:03Z)
• Curse of Knowledge: When Complex Evaluation Context Benefits yet Biases LLM Judges [72.3356133063925]
  The paradigm of large language models (LLMs) as judges has emerged as a scalable solution, yet prior work primarily focuses on simple settings.<n>Our in-depth analysis offers crucial insights for improving the accuracy and verifiability of evaluation signals.
  arXiv  Detail & Related papers  (2025-09-03T15:48:33Z)
• Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Models [1.0138329337410974]
  Large Language Models (LLMs) are trained on vast and diverse internet corpora that often include inaccurate or misleading content.<n>This review systematically analyzes how LLM-generated content is evaluated for factual accuracy.
  arXiv  Detail & Related papers  (2025-08-05T19:20:05Z)
• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
  We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
  arXiv  Detail & Related papers  (2025-08-05T17:55:24Z)
• ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering [42.238086712267396]
  ComposeRAG is a novel modular abstraction that decomposes RAG pipelines into atomic, composable modules.<n>It consistently outperforms strong baselines in both accuracy and grounding fidelity.<n>Its verification-first design reduces ungrounded answers by over 10% in low-quality retrieval settings.
  arXiv  Detail & Related papers  (2025-05-30T21:10:30Z)
• Don't Take the Premise for Granted: Evaluating the Premise Critique Ability of Large Language Models [11.379764847748378]
  Large language models (LLMs) often uncritically accept flawed or contradictory premises, leading to inefficient reasoning and unreliable outputs.<n>This emphasizes the significance of possessing the textbfPremise Critique Ability for LLMs, defined as the capacity to proactively identify and articulate errors in input premises.<n>We introduce the textbfPremise Critique Bench (PCBench), designed by incorporating four error types across three difficulty levels, paired with multi-faceted evaluation metrics.
  arXiv  Detail & Related papers  (2025-05-29T17:49:44Z)
• VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models [55.39064621869925]
  OpenAI o1 and DeepSeek-R1 have achieved remarkable performance in the domain of reasoning.<n>A key component of their training is the incorporation of verifiable rewards within reinforcement learning.<n>Existing reward benchmarks do not evaluate reference-based reward systems.
  arXiv  Detail & Related papers  (2025-05-21T17:54:43Z)
• Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards [67.86091419220816]
  Large Language Models (LLMs) show great promise in complex reasoning.<n>A prevalent issue is superficial self-reflection'', where models fail to robustly verify their own outputs.<n>We introduce RISE (Reinforcing Reasoning with Self-Verification), a novel online RL framework designed to tackle this.
  arXiv  Detail & Related papers  (2025-05-19T17:59:31Z)
• SAS-Bench: A Fine-Grained Benchmark for Evaluating Short Answer Scoring with Large Language Models [36.10798324093408]
  SAS-Bench is a benchmark for large language models (LLMs) based Short Answer Scoring tasks.<n>It provides fine-grained, step-wise scoring, expert-annotated error categories, and a diverse range of question types.<n>We also release an open-source dataset containing 1,030 questions and 4,109 student responses, each annotated by domain experts.
  arXiv  Detail & Related papers  (2025-05-12T05:43:21Z)
• AlignRAG: Leveraging Critique Learning for Evidence-Sensitive Retrieval-Augmented Reasoning [61.28113271728859]
  RAG has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>Standard RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>In this work, we reinterpret RAG as Retrieval-Augmented Reasoning and identify a central but underexplored problem: textitReasoning Misalignment.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)
• Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains [92.36624674516553]
  Reinforcement learning with verifiable rewards (RLVR) has demonstrated significant success in enhancing mathematical reasoning and coding performance of large language models (LLMs)<n>We investigate the effectiveness and scalability of RLVR across diverse real-world domains including medicine, chemistry, psychology, economics, and education.<n>We utilize a generative scoring technique that yields soft, model-based reward signals to overcome limitations posed by binary verifications.
  arXiv  Detail & Related papers  (2025-03-31T08:22:49Z)
• Can LLMs Improve Multimodal Fact-Checking by Asking Relevant Questions? [16.559968418625537]
  Large Language Models (LLMs) have been commonly used to automate evidence retrieval and factuality verification at scale.<n>We introduce a framework LRQ-FACT for using LLMs to generate relevant FCQs to facilitate evidence retrieval and enhance fact-checking.
  arXiv  Detail & Related papers  (2024-10-06T20:33:22Z)
• Evaluating the Efficacy of Foundational Models: Advancing Benchmarking Practices to Enhance Fine-Tuning Decision-Making [1.3812010983144802]
  This study evaluates large language models (LLMs) across diverse domains, including cybersecurity, medicine, and finance. The results indicate that model size and types of prompts used for inference significantly influenced response length and quality.
  arXiv  Detail & Related papers  (2024-06-25T20:52:31Z)
• FactCHD: Benchmarking Fact-Conflicting Hallucination Detection [64.4610684475899]
  FactCHD is a benchmark designed for the detection of fact-conflicting hallucinations from LLMs. FactCHD features a diverse dataset that spans various factuality patterns, including vanilla, multi-hop, comparison, and set operation. We introduce Truth-Triangulator that synthesizes reflective considerations by tool-enhanced ChatGPT and LoRA-tuning based on Llama2.
  arXiv  Detail & Related papers  (2023-10-18T16:27:49Z)
• DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection [55.70982767084996]
  A critical yet frequently overlooked challenge in the field of deepfake detection is the lack of a standardized, unified, comprehensive benchmark. We present the first comprehensive benchmark for deepfake detection, called DeepfakeBench, which offers three key contributions. DeepfakeBench contains 15 state-of-the-art detection methods, 9CL datasets, a series of deepfake detection evaluation protocols and analysis tools, as well as comprehensive evaluations.
  arXiv  Detail & Related papers  (2023-07-04T01:34:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.