mlsanityData to 14 Oct 2026

ThinknCheck: Grounded Claim Verification with Compact, Reasoning-Driven, and Interpretable Models

arXiv 2604.01652 ↗First posted 2 Apr 2026cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

We present ThinknCheck, a 1B-parameter verifier for grounded claim verification that first produces a short, structured rationale and then a binary verdict. We construct LLMAggreFact-Think, a 24.1k reasoning-augmented training set derived from LLMAggreFact, and fine-tune a 4-bit Gemma3 model to follow this format. On LLMAggreFact, ThinknCheck attains 78.1 balanced accuracy (BAcc), surpassing MiniCheck-7B (77.4) with 7x fewer parameters; removing the reasoning step reduces BAcc to 57.5. On SciFact, ThinknCheck reaches 64.7 BAcc, a +14.7 absolute gain over MiniCheck-7B. By contrast, zero-shot chain-of-thought on the base Gemma3-1B harms accuracy relative to direct answers, and preference optimization with a simple format+accuracy reward underperforms supervised reasoning. To probe the latter, we introduce GSMClaims and a domain-specialized variant, ThinknCheck-Science, which improves across benchmarks, including 61.0% accuracy on GSMClaims. Overall, explicit, supervised reasoning enables compact verifiers that are competitive while remaining resource-efficient and interpretable.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 38 references that are in the map. First posted on arXiv 2 Apr 2026.

Builds on

33 of 38 references.

References · 33

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  6. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  7. 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,345
  8. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  9. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,317
  10. 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 812
  11. 2020Fact or Fiction: Verifying Scientific Claimscited by 554
  12. 2021SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarizationcited by 407
21 more
  1. 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 399
  2. 2023Hyena Hierarchy: Towards Larger Convolutional Language Modelscited by 393
  3. 2025SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Modelcited by 335
  4. 2023How Language Model Hallucinations Can Snowballcited by 311
  5. 2023Evaluating Verifiability in Generative Search Enginescited by 303
  6. 2023AlignScore: Evaluating Factual Consistency with a Unified Alignment Functioncited by 288
  7. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 284
  8. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documentscited by 257
  9. 2021QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarizationcited by 236
  10. 2024An Empirical Study of Mamba-based Language Modelscited by 186
  11. 2023WiCE: Real-World Entailment for Claims in Wikipediacited by 120
  12. 2025Small Models Struggle to Learn from Strong Reasonerscited by 113
  13. 2024Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worsecited by 109
  14. 2021MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarizationcited by 104
  15. 2022Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectorscited by 104
  16. 2023ExpertQA: Expert-Curated Questions and Attributed Answerscited by 97
  17. 2025Uncertainty Quantification and Confidence Calibration in Large Language Models: A Surveycited by 95
  18. 2023Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkerscited by 87
  19. 2023MeetingBank: A Benchmark Dataset for Meeting Summarizationcited by 84
  20. 2024A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chainscited by 65
  21. 2023Understanding Retrieval Augmentation for Long-Form Question Answeringcited by 45

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models
  2. 2026DecomposeRL: Learning to Ask Useful, Informative, and Diverse Questions for Semi-Supervised, Traceable Claim Verification
  3. 2025Reasoning-CV: Fine-tuning Powerful Reasoning LLMs for Knowledge-Assisted Claim Verification
  4. 2025STRIVE: Structured Reasoning for Self-Improvement in Claim Verification
  5. 2026What Do Claim Verification Datasets Actually Test? A Reasoning Trace Analysis
  6. 2026ART: Adaptive Reasoning Trees for Explainable Claim Verification
  7. 2025Veri-R1: Toward Precise and Faithful Claim Verification via Online Reinforcement Learning
  8. 2026Claim-Level Reliability Assessment for Efficient Test-Time Reasoning