Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

CREDENCE: Claim Reduction for Decomposition & Enhanced Credibility -- Semantic Metrics and Convergence Analysis

Phuong Huu Vu Tran, Thuan Duc Mai, Bach Xuan Le

Published

Jun 18, 2026

Citations

0

Trust level

Low

Usefulness score

5/100 (Low)

Extraction confidence

45% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Jun 18, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

Use if you need

A benchmark-and-metrics comparison anchor.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
5/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Decomposing compound sentences into atomic, verifiable claims is a prerequisite for reliable automated fact-checking. Prior work has relied on token-overlap (Jaccard) metrics that systematically underestimate decomposition quality for paraphrastic claims, and has lacked formal termination analysis for the repair loop. We present Credence, a revised claim decomposition and evaluation framework addressing both shortcomings. Our contributions are: (1) Semantic-F1: we use BGE-large cosine similarity fidelity metric that resolves Jaccard's penalisation and improves downstream fact-checking accuracy; (2) Convergence theorems: we formally characterise four properties of the repair pipeline, establishing that rule-based repair is monotone and finitely terminating under an oracle parser assumption; LLM-based self-repair is provably non-monotone and requires an early-exit guard; (3) Three evaluation benchmarks spanning social-media, encyclopaedic, and news domains for cross-domain generalisation measurement; (4) Multi-model benchmarking across four decomposer models (3.8B-12B) and a closed API model. Experiments on SocialClaimSplit, WikiSplitBench, and ClaimDecompBench show that Semantic-F1 outperforms Jaccard-F1 by +15-32pp. EPR ranges from 0.94 to 1.00 on SocialClaimSplit and WikiSplitBench, while ClaimDecompBench includes lower base EPR cases (down to 0.824) due to harder news-domain constructions, and rule-repair reduces the Atomicity Violation Rate (AVR) by 47-100% relative to the base model without degrading fidelity.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"Decomposing compound sentences into atomic, verifiable claims is a prerequisite for reliable automated fact-checking."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"Decomposing compound sentences into atomic, verifiable claims is a prerequisite for reliable automated fact-checking."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Decomposing compound sentences into atomic, verifiable claims is a prerequisite for reliable automated fact-checking."

Benchmarks / Datasets

partial

Wikisplitbench, Claimdecompbench

Useful for quick benchmark comparison.

"Experiments on SocialClaimSplit, WikiSplitBench, and ClaimDecompBench show that Semantic-F1 outperforms Jaccard-F1 by +15-32pp."

Reported Metrics

partial

Accuracy, F1, Safety violation rate

Useful for evaluation criteria comparison.

"Our contributions are: (1) Semantic-F1: we use BGE-large cosine similarity fidelity metric that resolves Jaccard's penalisation and improves downstream fact-checking accuracy; (2) Convergence theorems: we formally characterise four properties of the repair pipeline, establishing that rule-based repair is monotone and finitely terminating under an oracle parser assumption; LLM-based self-repair is provably non-monotone and requires an early-exit guard; (3) Three evaluation benchmarks spanning social-media, encyclopaedic, and news domains for cross-domain generalisation measurement; (4) Multi-model benchmarking across four decomposer models (3.8B-12B) and a closed API model."

Benchmarks and datasets

WikisplitbenchClaimdecompbench

Reported metrics

accuracyf1safety violation rate
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Expertise required
General
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

Decomposing compound sentences into atomic, verifiable claims is a prerequisite for reliable automated fact-checking.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Decomposing compound sentences into atomic, verifiable claims is a prerequisite for reliable automated fact-checking.
  • Prior work has relied on token-overlap (Jaccard) metrics that systematically underestimate decomposition quality for paraphrastic claims, and has lacked formal termination analysis for the repair loop.
  • We present Credence, a revised claim decomposition and evaluation framework addressing both shortcomings.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics, Tool-use evaluation) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Accuracy

Contribution summary

  • We present Credence, a revised claim decomposition and evaluation framework addressing both shortcomings.
  • Our contributions are: (1) Semantic-F1: we use BGE-large cosine similarity fidelity metric that resolves Jaccard's penalisation and improves downstream fact-checking accuracy; (2) Convergence theorems: we formally characterise four…
  • Experiments on SocialClaimSplit, WikiSplitBench, and ClaimDecompBench show that Semantic-F1 outperforms Jaccard-F1 by +15-32pp.

Why it matters for eval

  • We present Credence, a revised claim decomposition and evaluation framework addressing both shortcomings.
  • Our contributions are: (1) Semantic-F1: we use BGE-large cosine similarity fidelity metric that resolves Jaccard's penalisation and improves downstream fact-checking accuracy; (2) Convergence theorems: we formally characterise four…

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    Detected: Wikisplitbench, Claimdecompbench

  • Metric reporting is present

    Detected: accuracy, f1, safety violation rate