Precision Is Not Faithfulness: Coverage-Aware Evaluation of Grounded Generation with a Complete Oracle

• URL: http://arxiv.org/abs/2606.09376v2
• Date: Tue, 16 Jun 2026 02:01:49 GMT
• Title: Precision Is Not Faithfulness: Coverage-Aware Evaluation of Grounded Generation with a Complete Oracle
• Abstract summary: Reference-free faithfulness metrics verify each atomic claim a model makes against ground truth.<n>We show they share a blind spot: they measure only precision, are the stated claims supported?<n>We make this measurable using Formula 1 telemetry, a domain where strategic ground truth is derived deterministically.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reference-free faithfulness metrics verify each atomic claim a model makes against ground truth, and are increasingly used to evaluate grounded generation. We show they share a blind spot: they measure only precision -- are the stated claims supported? -- and therefore reward abstention, since a model can score near-perfect faithfulness by saying almost nothing. We make this measurable using Formula 1 telemetry, a domain where strategic ground truth is derived deterministically and, crucially, completely: for each decision we know the full set of facts that mattered. This completeness -- absent in open-domain faithfulness benchmarks -- lets us measure recall (coverage of the relevant facts) exactly, alongside precision. On a multilingual (EN/ES/PT) benchmark of 7,253 decision instances spanning 157 races, the most precise frontier model covers under half of the relevant facts and ranks last by F1, so requiring coverage reorders the systems; the same effect reappears in a second complete-oracle domain (NOAA weather forecasts). Fine-tuning small models (1B-7B) on the complete oracle closes the precision-recall gap entirely (F1 ~0.98), beating every zero-shot frontier system regardless of scale. We pair faithfulness with coverage into a single score, validate the metric (controlled perturbation; agreement across a model-free regex extractor and a cross-family LLM extractor, system-level Spearman 1.0), and give a verifier-guided generation method that improves precision and recall without references. We release the benchmark, structured annotations, metric, baselines, and an interactive demo.

Related papers

• TelemetrySuffBench: Is Agent Telemetry Sufficient for Failure-Origin Diagnosis? [1.7077233340294056]
  We introduce TelemetrySuffBench, a benchmark that separates failure detection, fault-origin localization, and safe abstention under insufficient evidence.<n>We evaluate five frontier language models using unified protocols, explicit candidate sets, invalid-output accounting, subgroup analyses, and a frozen blind holdout.
  arXiv  Detail & Related papers  (2026-08-08T03:54:22Z)
• Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness [8.98920719663984]
  Gamut is a benchmark for factual completeness in long-form generation.<n>We construct 1,813 questions grounded in real wearable imagery across 10 diverse domains.
  arXiv  Detail & Related papers  (2026-07-21T17:42:50Z)
• PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception [75.70273182182397]
  PerceptionRubrics is a rubric-based evaluation framework.<n>It addresses the gap between saturated benchmark scores and real-world brittleness.<n>It pairs 1,038 information-dense images with over 10,000 instance-specific rubrics.
  arXiv  Detail & Related papers  (2026-06-26T17:59:15Z)
• Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth [24.21103008618097]
  Chains of thought (CoTs) have become central in interpreting and auditing behaviors of large language models.<n>We develop an automated labeling pipeline that yields ground-truth faithfulness labels at both the step and CoT level.<n>Our experiments show that most metrics perform near chance, exhibit strong prediction biases and degrade on longer CoTs.
  arXiv  Detail & Related papers  (2026-05-24T12:57:01Z)
• What Single-Prompt Accuracy Misses: A Multi-Variant Reliability Audit of Language Models [0.0]
  Single-prompt accuracy is the dominant way to benchmark language models, but it can miss reliability failures that matter.<n>We evaluate a 15-model open-weight corpus, with the main reliability analyses focused on 10 instruct models across five classification and reasoning benchmarks.<n>We find three broad results. First, evaluation design can materially change the conclusion.<n>Second, confidence signals are fragile. On MMLU-Pro, every primary model verbally reports confidence substantially above both its accuracy and its token-probability confidence on the same rows, and verbal parse rate can collapse for a single model on a single prompt variant.
  arXiv  Detail & Related papers  (2026-05-03T20:05:08Z)
• Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models [94.68358825189738]
  We propose a post-training framework for verifiable domains that jointly optimize prediction accuracy and reasoning quality.<n>We evaluate VPS on chess, a controlled testbed where reasoning steps can be deterministically verified against engine signals.<n>VPS preserves accuracy while significantly improving reasoning quality, reducing win-rate error by up to 30% and restoring consistency to near saturation.
  arXiv  Detail & Related papers  (2026-04-03T15:19:46Z)
• Epistemic Observability in Language Models [0.0]
  We find that models report highest confidence precisely when they are fabricating.<n>We prove, under formal assumptions, that this is not a capability gap but an observational one.<n>We construct a tensor interface that escapes the impossibility by exporting computational byproducts.
  arXiv  Detail & Related papers  (2026-03-20T21:59:34Z)
• Certainty-Validity: A Diagnostic Framework for Discrete Commitment Systems [0.0]
  "Machine learning evaluation metrics" assume that all errors are equivalent discrete commitment systems.<n>"ConfidentIncorrect" behavior is where models hallucinate structure in ambiguous data.<n>"Good training" for reasoning systems must be defined not by accuracy but by maximizing the Certainty-Validity Score.
  arXiv  Detail & Related papers  (2026-02-10T21:53:02Z)
• CLUE: Non-parametric Verification from Experience via Hidden-State Clustering [64.50919789875233]
  We show that correctness of a solution is encoded as a geometrically separable signature within the trajectory of hidden activations.<n>ClUE consistently outperforms LLM-as-a-judge baselines and matches or exceeds modern confidence-based methods in reranking candidates.
  arXiv  Detail & Related papers  (2025-10-02T02:14:33Z)
• Judging with Confidence: Calibrating Autoraters to Preference Distributions [56.17041629492863]
  We argue that a reliable autorater must learn to model the full distribution of preferences defined by a target population.<n>We present two learning methods tailored to different data conditions.<n>Our results show that finetuning autoraters with a distribution-matching objective leads to verbalized probability predictions that are better aligned with the target preference distribution.
  arXiv  Detail & Related papers  (2025-09-30T20:36:41Z)
• Claim Extraction for Fact-Checking: Data, Models, and Automated Metrics [0.0]
  We release the FEVERFact dataset, with 17K atomic factual claims extracted from 4K contextualised Wikipedia sentences.<n>For each metric, we implement a scale using a reduction to an already-explored NLP task.<n>We validate our metrics against human grading of generic claims, to see that the model ranking on $F_fact$, our hardest metric, did not change.
  arXiv  Detail & Related papers  (2025-02-07T14:20:45Z)
• Do Automatic Factuality Metrics Measure Factuality? A Critical Evaluation [16.506990103937515]
  We stress test a range of automatic factuality metrics to probe what they actually capture.<n>We find that all metrics show substantial performance drops on the latter.<n>Some metrics are more sensitive to benign, fact-preserving edits than to factual corrections.
  arXiv  Detail & Related papers  (2024-11-25T18:15:15Z)
• Generating Benchmarks for Factuality Evaluation of Language Models [61.69950787311278]
  We propose FACTOR: Factual Assessment via Corpus TransfORmation, a scalable approach for evaluating LM factuality. FACTOR automatically transforms a factual corpus of interest into a benchmark evaluating an LM's propensity to generate true facts from the corpus vs. similar but incorrect statements. We show that: (i) our benchmark scores increase with model size and improve when the LM is augmented with retrieval; (ii) benchmark score and perplexity do not always agree on model ranking; (iii) when perplexity and benchmark score disagree, the latter better reflects factuality in open-ended generation.
  arXiv  Detail & Related papers  (2023-07-13T17:14:38Z)
• Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction [49.15931834209624]
  We present the first benchmark that simulates the evaluation of open information extraction models in the real world.<n>We design and annotate a large-scale testbed in which each example is a knowledge-invariant clique.<n>By further elaborating the robustness metric, a model is judged to be robust if its performance is consistently accurate on the overall cliques.
  arXiv  Detail & Related papers  (2023-05-23T12:05:09Z)
• BUMP: A Benchmark of Unfaithful Minimal Pairs for Meta-Evaluation of Faithfulness Metrics [70.52570641514146]
  We present a benchmark of unfaithful minimal pairs (BUMP) BUMP is a dataset of 889 human-written, minimally different summary pairs. Unlike non-pair-based datasets, BUMP can be used to measure the consistency of metrics.
  arXiv  Detail & Related papers  (2022-12-20T02:17:30Z)
• Exploring validation metrics for offline model-based optimisation with diffusion models [50.404829846182764]
  In model-based optimisation (MBO) we are interested in using machine learning to design candidates that maximise some measure of reward with respect to a black box function called the (ground truth) oracle. While an approximation to the ground oracle can be trained and used in place of it during model validation to measure the mean reward over generated candidates, the evaluation is approximate and vulnerable to adversarial examples. This is encapsulated under our proposed evaluation framework which is also designed to measure extrapolation.
  arXiv  Detail & Related papers  (2022-11-19T16:57:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.