DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality

• URL: http://arxiv.org/abs/2603.05912v1
• Date: Fri, 06 Mar 2026 05:05:57 GMT
• Title: DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality
• Abstract summary: Existing fact-checkers are primarily designed for general-domain, factoid-style atomic claims.<n>We propose Audit-then-Score (AtS), where benchmark labels and rationales are explicitly revisable.<n>We instantiate AtS as DeepFact-Bench, a versioned DRR factuality benchmark with auditable rationales.
• Score: 49.62610727661819
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Search-augmented LLM agents can produce deep research reports (DRRs), but verifying claim-level factuality remains challenging. Existing fact-checkers are primarily designed for general-domain, factoid-style atomic claims, and there is no benchmark to test whether such verifiers transfer to DRRs. Yet building such a benchmark is itself difficult. We first show that static expert-labeled benchmarks are brittle in this setting: in a controlled study with PhD-level specialists, unassisted experts achieve only 60.8% accuracy on a hidden micro-gold set of verifiable claims. We propose Evolving Benchmarking via Audit-then-Score (AtS), where benchmark labels and rationales are explicitly revisable: when a verifier disagrees with the current benchmark, it must submit evidence; an auditor adjudicates the dispute; and accepted revisions update the benchmark before models are scored. Across four AtS rounds, expert micro-gold accuracy rises to 90.9%, indicating experts are substantially more reliable as auditors than as one-shot labelers. We instantiate AtS as DeepFact-Bench, a versioned DRR factuality benchmark with auditable rationales, and DeepFact-Eval, a document-level verification agent (with a grouped lite variant) that outperforms existing verifiers on DeepFact-Bench and transfers well to external factuality datasets.

Related papers

• The Double Measurement Confound in Agent Benchmarks: De-Scaffolding, Ground-Truth Scoring, and Reliability Beyond the Mean [2.822987192839875]
  Agent benchmarks are increasingly used to compare large language models (LLMs) and guide deployment decisions.<n>We identify a double measurement confound: execution-critical decisions are performed by a fixed scaffold instead of the model, while the scorer evaluates outputs using criteria that may not reflect task correctness.<n>We unify these issues within a measurement-theoretic framework that characterizes when benchmark scores can be interpreted as evidence of model capability.
  arXiv  Detail & Related papers  (2026-09-06T21:23:11Z)
• Benchmarking the Benchmarks: A Validity Audit of Tool-Calling Evaluation [3.079997053226693]
  We present a systematic validity and audit of four major tool-calling benchmark families.<n>Across 496 expert-reviewed benchmark tasks, we find 92 evaluator-human disagreements, corresponding to an 18.5% misalignment rate.<n>We introduce a unified taxonomy of tool-calling evaluation failures, release trace-level audit artifacts and corrected evaluation components, and argue for metrics that separately measure tool invocation, task completion, and outcome verification.
  arXiv  Detail & Related papers  (2026-06-30T21:10:42Z)
• Bayesian control for coding agents [63.64172141184361]
  We propose a cost-sensitive sequential hypothesis testing framework for coding agents.<n>A Bayesian controller maintains a belief over correctness and decides whether to gather more evidence, refine the candidate, verify it, or stop.<n>We show that the belief state yields an interpretable correctness score that outperforms token-probability and raw tool-success baselines for uncertainty quantification.
  arXiv  Detail & Related papers  (2026-06-23T11:41:32Z)
• Automated Benchmark Auditing for AI Agents and Large Language Models [46.03841647776303]
  Auto Benchmark Audit (ABA) is an agentic framework that systematically audits individual benchmark tasks.<n>We run ABA on a collection of frontier LLM benchmarks and previous NeurIPS publications, totaling 168 benchmarks across nine domains.<n>ABA identifies critical issues including ambiguous task design, execution environment conflicts, and incorrect ground truths in over 25.7% of the evaluated tasks.
  arXiv  Detail & Related papers  (2026-05-25T17:44:21Z)
• Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents? [61.49434544687523]
  We introduce REFLECT, a meta-evaluation benchmark targeting fine-grained failure detection in agentic environments.<n> REFLECT defines a detailed taxonomy of process- and outcome-level failure modes, instantiated by performing controlled and localized interventions.<n>Our experiments show that even the best-performing models achieve overall accuracies below 55% across reasoning, tool-use, and report-quality failures.
  arXiv  Detail & Related papers  (2026-05-18T23:55:08Z)
• BenchGuard: Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks [26.58983143152204]
  BenchGuard is the first automated auditing framework for task-oriented, execution-based agent benchmarks.<n>It identifies 12 author-confirmed issues in ScienceAgentBench and 83.3% of expert-identified issues on the BIXBench Verified-50 subset.<n>A full audit of 50 complex bioinformatics tasks costs under USD 15, making automated benchmark auditing a practical and valuable complement to human review.
  arXiv  Detail & Related papers  (2026-04-27T19:51:25Z)
• Silicon Bureaucracy and AI Test-Oriented Education: Contamination Sensitivity and Score Confidence in LLM Benchmarks [43.45152572188735]
  We propose an audit framework for analyzing contamination sensitivity and score confidence in language models.<n>We find widespread but heterogeneous above-baseline gains under noisy conditions.<n>These results suggest that similar benchmark scores may carry substantially different levels of confidence.
  arXiv  Detail & Related papers  (2026-03-23T07:03:07Z)
• Guideline-Grounded Evidence Accumulation for High-Stakes Agent Verification [60.18369393468405]
  Existing verifiers usually underperform owing to a lack of domain knowledge and limited calibration.<n>GLEAN compiles expert-curated protocols into trajectory-informed, well-calibrated correctness signals.<n>We empirically validate GLEAN with agentic clinical diagnosis across three diseases from the MIMIC-IV dataset.
  arXiv  Detail & Related papers  (2026-03-03T09:36:43Z)
• FIRE-Bench: Evaluating Agents on the Rediscovery of Scientific Insights [63.32178443510396]
  We introduce FIRE-Bench (Full-cycle Insight Rediscovery Evaluation), a benchmark that evaluates agents through the rediscovery of established findings.<n>Even the strongest agents achieve limited rediscovery success (50 F1), exhibit high variance across runs, and display recurring failure modes in experimental design, execution, and evidence-based reasoning.
  arXiv  Detail & Related papers  (2026-02-02T23:21:13Z)
• RULERS: Locked Rubrics and Evidence-Anchored Scoring for Robust LLM Evaluation [15.787947727055611]
  We introduce RULERS, a compiler-executor framework that transforms natural language rubrics into executable specifications.<n>RULERS operates by compiling criteria into versioned immutable bundles, enforcing structured decoding with deterministic evidence verification, and applying lightweight Wasserstein-based post-hoc calibration.
  arXiv  Detail & Related papers  (2026-01-13T15:31:42Z)
• PaperAudit-Bench: Benchmarking Error Detection in Research Papers for Critical Automated Peer Review [54.141490756509306]
  We introduce PaperAudit-Bench, which consists of two components: PaperAudit-Dataset, an error dataset, and PaperAudit-Review, an automated review framework.<n>Experiments on PaperAudit-Bench reveal large variability in error detectability across models and detection depths.<n>We show that the dataset supports training lightweight LLM detectors via SFT and RL, enabling effective error detection at reduced computational cost.
  arXiv  Detail & Related papers  (2026-01-07T04:26:12Z)
• DEER: A Comprehensive and Reliable Benchmark for Deep-Research Expert Reports [49.217247659479476]
  deep research systems can generate expert-level reports via multi-step reasoning and evidence-based synthesis.<n>Existing benchmarks often lack systematic criteria for expert reporting.<n>We introduce DEER, a benchmark for evaluating expert-level deep research reports.
  arXiv  Detail & Related papers  (2025-12-19T16:46:20Z)
• VerifyBench: A Systematic Benchmark for Evaluating Reasoning Verifiers Across Domains [19.579511315215424]
  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.
  arXiv  Detail & Related papers  (2025-07-14T03:45:24Z)
• TrendFact: A Benchmark for Explainable Hotspot Perception in Fact-Checking with Natural Language Explanation [9.221637941193606]
  We introduce TrendFact, the first benchmark capable of evaluating hotspot perception ability (HPA) and all fact-checking tasks.<n> TrendFact consists of 7,643 curated samples sourced from trending platforms and professional fact-checking datasets.<n>We also propose FactISR, a reasoning framework that integrates dynamic evidence augmentation with influence score-based iterative self-reflection.
  arXiv  Detail & Related papers  (2024-10-19T15:25:19Z)
• 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)

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.