mlsanityData to 7 Oct 2026

AEScorer: An Agentic Evidence-Grounded Framework for Graded Factuality Verification

arXiv 2601.03605 ↗First posted 7 Jan 2026cs.CLcited by 0

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

Despite the significant advancements of Large Language Models (LLMs), their factuality remains a critical challenge, creating a growing need for more nuanced factuality verification. Existing factuality verification methods do not capture graded judgments, even though factuality is better understood as a spectrum rather than a binary of right and wrong. To bridge this gap, we focus on graded factuality verification and propose AEScorer, an agentic evidence-grounded framework with two stages: agentic evidence acquisition and graded scoring. AEScorer first gathers and refines external evidence through agentic search, and then predicts a scalar factuality score to distinguish nuanced differences in factual correctness. We further construct GradedVeriBench, a benchmark for graded factuality verification spanning both general and multi-hop question answering. Experimental results on GradedVeriBench show that AEScorer substantially outperforms existing methods across both settings, demonstrating the value of coupling targeted evidence acquisition with graded scoring.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 25 of its 44 references that are in the map. First posted on arXiv 7 Jan 2026.

Builds on

25 of 44 references.

References · 25

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2025Qwen3 Technical Reportcited by 8,195
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  6. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  8. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  9. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  10. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  11. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
  12. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
13 more
  1. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  2. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documentscited by 251
  3. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 204
  4. 2023WiCE: Real-World Entailment for Claims in Wikipediacited by 118
  5. 2024VERISCORE: Evaluating the factuality of verifiable claims in long-form text generationcited by 114
  6. 2025A Comprehensive Survey on Long Context Language Modelingcited by 113
  7. 2025The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMscited by 72
  8. 2023Atomic Inference for NLI with Generated Facts as Atomscited by 16
  9. 2025HalluciNot: Hallucination Detection Through Context and Common Knowledge Verificationcited by 13
  10. 2024FactLens: Benchmarking Fine-Grained Fact Verificationcited by 10
  11. 2025Generative or Discriminative? Revisiting Text Classification in the Era of Transformerscited by 9
  12. 2023A Revisit of Fake News Dataset with Augmented Fact-checking by ChatGPTcited by 4
  13. 2024Learning to Verify Summary Facts with Fine-Grained LLM Feedbackcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026ReflectFact: Self-Reflective Agents for Improving Comprehension and Reasoning in Multi-Hop Fact Verification
  2. 2026Tool-MAD: A Multi-Agent Debate Framework for Fact Verification with Diverse Tool Augmentation and Adaptive Retrieval
  3. 2025MAD-Fact: A Multi-Agent Debate Framework for Long-Form Factuality Evaluation in LLMs
  4. 2026Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies
  5. 2024Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output
  6. 2024Identifying the Achilles' Heel: An Iterative Method for Dynamically Uncovering Factual Errors in Large Language Models
  7. 2026DARE: Dialectical Agentic Reasoning for Structured Knowledge Fact Checking
  8. 2025UrduFactCheck: An Agentic Fact-Checking Framework for Urdu with Evidence Boosting and Benchmarking