mlsanityData to 14 Oct 2026

UTS at CheckThat! 2026: Cite-Frame Engineering for Generated Fact-Checking Articles

arXiv 2608.24466 ↗First posted 15 Jul 2026cs.DL cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

CheckThat! 2026 Task 3 asks systems to generate fact-checking articles, graded by an unweighted mean of four sub-metrics (M4). Our UTS submission placed 2nd of 11 teams (M4 = 0.484). The shipped system is a deterministic stub drafter wrapped by two single-lever interventions: a domain-attribution cite frame (HostCite) and a shadow-validated anchor picker (ShadowVal) that use Llama-3.2:1B only as a per-cite validator, never as a body-prose generator. The stack lifts M4 by +0.027 over the stub on the WatClaimCheck validation split, beats the field on entailment and coverage, and follows two design rules our ablation matrix made unambiguous. Scorer conservatism: credit only tokens the references entail - templates pay; LLM prose, reviewer names, and raw evidence all fail. Auxiliary anchor signals are miscalibrated against the Llama judge: every anchor proxy we tried (cross-encoder, length, lead position) picks anchors the judge rejects - gate on the judge itself. The remaining +0.062 gap to the winner sits on citation precision/recall (0.299 vs 0.671), consistent with a selective-emission policy that drops low-confidence cites.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 24 references that are in the map. First posted on arXiv 15 Jul 2026.

Builds on

15 of 24 references.

References · 15

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  4. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  5. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  6. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  7. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  8. 2021A Survey on Automated Fact-Checkingcited by 378
  9. 2020Explainable Automated Fact-Checking for Public Health Claimscited by 211
  10. 2023Efficient Guided Generation for Large Language Modelscited by 200
  11. 2020Generating Fact Checking Explanationscited by 132
  12. 2018Content Selection in Deep Learning Models of Summarizationcited by 64
3 more
  1. 2024JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claimscited by 29
  2. 2025Can LLMs Automate Fact-Checking Article Writing?cited by 7
  3. 2026The CLEF-2026 CheckThat! Lab: Advancing Multilingual Fact-Checkingcited by 3

Built on by

Not cited yet.