# Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers

arXiv: https://arxiv.org/abs/2506.13342 · HTML: https://mlsanity.com/paper/2506.13342/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 40 references that are in the map.
- First posted on arXiv 16 Jun 2025.

## Builds on (most cited first, 30 of 36)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [InternLM2 Technical Report](https://mlsanity.com/paper/2403.17297/) (2024)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [Evaluating Verifiability in Generative Search Engines](https://mlsanity.com/paper/2304.09848/) (2023)
- [RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models](https://mlsanity.com/paper/2401.00396/) (2023)
- [MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents](https://mlsanity.com/paper/2404.10774/) (2024)
- [Measuring Attribution in Natural Language Generation Models](https://mlsanity.com/paper/2112.12870/) (2021)
- [Fine-tuning Language Models for Factuality](https://mlsanity.com/paper/2311.08401/) (2023)
- [What Will it Take to Fix Benchmarking in Natural Language Understanding?](https://mlsanity.com/paper/2104.02145/) (2021)
- [HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification](https://mlsanity.com/paper/2011.03088/) (2020)
- [Are We Done with MMLU?](https://mlsanity.com/paper/2406.04127/) (2024)
- [Long-form factuality in large language models](https://mlsanity.com/paper/2403.18802/) (2024)
- [We're Afraid Language Models Aren't Modeling Ambiguity](https://mlsanity.com/paper/2304.14399/) (2023)
- [WiCE: Real-World Entailment for Claims in Wikipedia](https://mlsanity.com/paper/2303.01432/) (2023)
- [VERISCORE: Evaluating the factuality of verifiable claims in long-form text generation](https://mlsanity.com/paper/2406.19276/) (2024)
- [Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors](https://mlsanity.com/paper/2205.12854/) (2022)
- [ExpertQA: Expert-Curated Questions and Attributed Answers](https://mlsanity.com/paper/2309.07852/) (2023)
- [TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization](https://mlsanity.com/paper/2402.13249/) (2024)
- [A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains](https://mlsanity.com/paper/2402.00559/) (2024)
- [Do Large Language Model Benchmarks Test Reliability?](https://mlsanity.com/paper/2502.03461/) (2025)
- [The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Input](https://mlsanity.com/paper/2501.03200/) (2025)
- [FLAME: Factuality-Aware Alignment for Large Language Models](https://mlsanity.com/paper/2405.01525/) (2024)
- [Understanding Retrieval Augmentation for Long-Form Question Answering](https://mlsanity.com/paper/2310.12150/) (2023)
- [AmbiFC: Fact-Checking Ambiguous Claims with Evidence](https://mlsanity.com/paper/2104.00640/) (2021)

## Built on by (most cited first, 13 of 13)

- [Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents](https://mlsanity.com/paper/2605.06635/) (2026)
- [MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination](https://mlsanity.com/paper/2603.24579/) (2026)
- [FaithLens: Detecting and Explaining Faithfulness Hallucination](https://mlsanity.com/paper/2512.20182/) (2025)
- [SEVA: Self-Evolving Verification Agent with Process Reward for Fact Attribution](https://mlsanity.com/paper/2606.29713/) (2026)
- [Distill and Align Decomposition for Enhanced Claim Verification](https://mlsanity.com/paper/2602.21857/) (2026)
- [The Gray Zone of Faithfulness: Taming Ambiguity in Unfaithfulness Detection](https://mlsanity.com/paper/2510.21118/) (2025)
- [InFi-Check: Interpretable and Fine-Grained Fact-Checking of LLMs](https://mlsanity.com/paper/2601.06666/) (2026)
- [The Warrant Gap: Claim-Conditioned Re-scoring for Fact-Checking](https://mlsanity.com/paper/2606.24627/) (2026)
- [Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator](https://mlsanity.com/paper/2607.07993/) (2026)
- [Symbolic Augmentation Closes a Canonical-Equivalence Blind Spot in Neural Fact-Checkers](https://mlsanity.com/paper/2607.16212/) (2026)
- [TriQua: Reconciling Granularity and Context in Factuality Evaluation](https://mlsanity.com/paper/2608.05228/) (2026)
- [RAIM: Robust Aggregation of Inexpensive Models for Hallucination Detection](https://mlsanity.com/paper/2609.39229/) (2026)
- [The Same Zero: Why Identical ASR Can Imply Different Guarantees in LLM-Agent Security](https://mlsanity.com/paper/2610.04504/) (2026)

## Abstract (arXiv)

Fact verification is essential for ensuring the reliability of LLM applications. In this study, we evaluate 12 pre-trained LLMs and one specialized fact-verifier, including frontier LLMs and open-weight reasoning LLMs, using a collection of examples from 14 fact-checking benchmarks. We share three findings intended to guide future development of more robust fact verifiers. First, we highlight the importance of addressing annotation errors and ambiguity in datasets, demonstrating that approximately 16% of ambiguous or incorrectly labeled data substantially influences model rankings. Neglecting this issue may result in misleading conclusions during comparative evaluations, and we suggest using a systematic pipeline utilizing LLM-as-a-judge to help identify these issues at scale. Second, we discover that frontier LLMs with few-shot in-context examples, often overlooked in previous works, achieve top-tier performance. We therefore recommend that future studies include comparisons with these simple yet highly effective baselines. Lastly, despite their effectiveness, frontier LLMs incur substantial costs, motivating the development of small, fine-tuned fact verifiers. We show that these small models still have room for improvement, particularly on instances that require complex reasoning. Encouragingly, we demonstrate that augmenting training with synthetic multi-hop reasoning data significantly enhances their capabilities in such instances. We release our code, model, and dataset at https://github.com/just1nseo/verifying-the-verifiers.