Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

ChainCheck: Near-Perfect Evidence-Sufficiency Scores Can Conceal Sensitivity to Construction Artifacts -- Paired Conditional Contrasts that Expose an Evaluation Confound

Hyojung Han, Ryangkyung Kang, Youngeun Kim, Seung-Hun Jeon

Published

Nov 9, 2026

Citations

0

Trust level

Low

Usefulness score

0/100 (Low)

Extraction confidence

35% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Nov 9, 2026

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 secondary eval reference to pair with stronger protocol papers.

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
0/100
Adjacent candidate

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

Abstract

Evidence-sufficiency benchmarks ask whether a model can tell a complete passage set from one whose reasoning chain is broken. When broken sets are made by editing text, near-perfect sufficiency scores--and even positive crossed-control scores--need not demonstrate multi-hop reasoning. We present ChainCheck, an evaluation-validity audit that pairs validator-certified counterfactual cells with artifact-only baselines. In an exploratory crossed control on 2,214 HotpotQA pairs, a language-model scorer that never reads the chain reaches a nominal AUC of 0.997, and a one-string match reaches the maximum of the crossed chain-sensitivity statistic CS4 (0.500), while the 11 evaluated systems score from 0.308 to 0.484; the two statistics are different metrics. We therefore read positive CS4 as operational bridge-consistency sensitivity, not as semantic multi-hop reasoning. Every system is also sensitive to one extra edit, and the edits are detectable according to model-based naturalness ratings. On an independent HotpotQA set of 2,276 pairs, patterns pre-specified on MuSiQue and 2WikiMultiHopQA did not replicate: 5 of 6 trained readouts were edit-dominated, and the reference judge's selectivity interval [-0.007, +0.042] includes zero. Judge scores also depended on batch layout. The MuSiQue and 2Wiki records are public; the HotpotQA records and the fine-tuned checkpoints are not, so external reproduction is partial.

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.

"Evidence-sufficiency benchmarks ask whether a model can tell a complete passage set from one whose reasoning chain is broken."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"Evidence-sufficiency benchmarks ask whether a model can tell a complete passage set from one whose reasoning chain is broken."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Evidence-sufficiency benchmarks ask whether a model can tell a complete passage set from one whose reasoning chain is broken."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Evidence-sufficiency benchmarks ask whether a model can tell a complete passage set from one whose reasoning chain is broken."

Reported Metrics

partial

Auroc

Useful for evaluation criteria comparison.

"Evidence-sufficiency benchmarks ask whether a model can tell a complete passage set from one whose reasoning chain is broken."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

auroc
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

Evidence-sufficiency benchmarks ask whether a model can tell a complete passage set from one whose reasoning chain is broken.

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

Key takeaways

  • Evidence-sufficiency benchmarks ask whether a model can tell a complete passage set from one whose reasoning chain is broken.
  • When broken sets are made by editing text, near-perfect sufficiency scores--and even positive crossed-control scores--need not demonstrate multi-hop reasoning.
  • We present ChainCheck, an evaluation-validity audit that pairs validator-certified counterfactual cells with artifact-only baselines.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • 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

Contribution summary

  • Evidence-sufficiency benchmarks ask whether a model can tell a complete passage set from one whose reasoning chain is broken.
  • When broken sets are made by editing text, near-perfect sufficiency scores--and even positive crossed-control scores--need not demonstrate multi-hop reasoning.

Why it matters for eval

  • We present ChainCheck, an evaluation-validity audit that pairs validator-certified counterfactual cells with artifact-only baselines.

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

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    Detected: auroc