Do LLM Attribution Metrics Transfer? Auditing Retrieval-Augmented Generation Evaluation Across Datasets and Constructs

• URL: http://arxiv.org/abs/2606.23915v1
• Date: Mon, 22 Jun 2026 20:25:36 GMT
• Title: Do LLM Attribution Metrics Transfer? Auditing Retrieval-Augmented Generation Evaluation Across Datasets and Constructs
• Abstract summary: Practice often treats automatic metrics for attribution as interchangeable.<n>We audit eight automatic scorers across three evaluation constructs.<n>A naive "best-on-average" rule for choosing an evaluator fails leave-one-dataset-out.
• Score: 11.997694190254974
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Practice often treats automatic metrics for attribution in LLM retrieval-augmented generation as interchangeable. We audit eight automatic scorers -- lexical, embedding, and BERTScore baselines alongside entailment/grounding-trained models (clean and FEVER NLI, the checker MiniCheck) -- across three evaluation constructs (provenance/topicality, generated-answer attribution, and fact-check entailment), asking whether any scorer transfers: stays within the 95% confidence interval of the best audited scorer on every dataset of a multi-dataset construct. In the construct with the most multi-dataset human-labeled coverage -- generated-answer attribution (AttributionBench's four source datasets, n = 1,610, with independent HAGRID, n = 2,150) -- none does: the per-dataset metric rankings invert (Kendall tau = -0.64, p = 0.031 on AttributedQA vs. LFQA), and an off-the-shelf NLI scorer that is best on short-claim AttributedQA (AUROC 0.90) collapses to AUROC 0.53 (chance) on long-form LFQA, where BERTScore wins (0.91); the flip is not a length or truncation artifact. This instability has a concrete decision cost: a naive "best-on-average" rule for choosing an evaluator fails leave-one-dataset-out (mean held-out regret 0.172 AUROC, worse than fixing one scorer), so metric choice must be validated on the target dataset rather than learned from others. A prompt-based LLM judge avoids the chance-level collapses the automatic scorers suffer (no LFQA collapse) but is not uniformly best, ~100x costlier, and non-deterministic -- relocating, not removing, the validation burden.

Related papers

• Anchoring Bias in LLM-as-a-Judge Systems: Prior Scores Compromise Evaluation Independence [0.7340017786387767]
  We show that prior scores, even when included only as context metadata, anchor judgments and systematically shift ratings toward their values.<n>On categorical industry data with human-labeled ground truth, anchored metadata blocks 48% of error corrections and flips 10.18% of correct judgments toward an assigned wrong label.
  arXiv  Detail & Related papers  (2026-08-26T14:41:24Z)
• Beyond Pass@k: Measuring Reliability and Security of Agentic Code Generation [2.1734195143282693]
  We propose reliability@k, the same estimator applied correctly, with n = independent rollouts and c = fully-passing rollouts per (task, agent) pair.<n>Motivated by evidence that functional correctness does not imply security safety, we additionally propose security-adjusted reliability@k.
  arXiv  Detail & Related papers  (2026-08-11T16:01:15Z)
• Beyond Shapley: An Influence-Based Data Auditing Pipeline for LLM Alignment and Evaluation [2.733105115068754]
  We introduce a scalable, inference-only data valuation pipeline that approximates the Shapley value without iterative model retraining.<n>We demonstrate the pipeline's efficacy in sanitizing two heavily vetted alignment datasets.
  arXiv  Detail & Related papers  (2026-07-24T03:31:44Z)
• What Predicts Correctness in Text-to-SQL? A Selective-Prediction Study [0.0]
  We use AUROC to measure how well each ranks correct queries above incorrect ones.<n>On BIRD and Spider, black-box signals such as string, structural, and execution self-consistency, a schema-relevance score, and query executability all fall between about 0.61 and 0.68 AUROC.<n>We ask whether a verifier can be trained. Fine-tuned verifiers, both encoder and generative, reach about 0.77 to 0.79 AUROC in-distribution but fall to about 0.66 on unseen schemas.
  arXiv  Detail & Related papers  (2026-07-07T20:52:58Z)
• RAPT: Retrieval-Augmented Post-hoc Thresholding for Multi-Label Classification [1.2599533416395765]
  We present RAPT, a deployment-oriented retrieval-augmented score thresholding wrapper.<n>RAPT is a model-agnostic wrapper for document representations for similarity search and per label confidence scores.<n>In industrial setting, RAPT achieved its best predictive performance with metric learners, reaching 0.87 Macro-F1.
  arXiv  Detail & Related papers  (2026-05-15T18:31:04Z)
• Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning [40.342912574072024]
  Large Language Models produce structured outputs such as travel plans or code solutions.<n>Individual reasoning steps may appear correct while the output as a whole violates budgets, fails test cases, or contradicts earlier deductions.<n>We propose a learned quality scorer with deterministic analytical constraint penalties for verifying structured LLM outputs.
  arXiv  Detail & Related papers  (2026-05-15T17:08:27Z)
• VERDI: Single-Call Confidence Estimation for Verification-Based LLM Judges via Decomposed Inference [0.0]
  VERDI (VERification-Decomposed Inference Inference) is a method that extracts confidence from a structured judge.<n> VERDI decomposes each evaluation into sub-checks and derives three structural signals.<n>On three public benchmarks, VERDI achieves AUROC 0.72-0.91 on GPT-4.1-mini and 0.66-0.80 on GPT-5.4-mini.
  arXiv  Detail & Related papers  (2026-05-11T23:39:19Z)
• Calibrated Confidence Estimation for Tabular Question Answering [0.0]
  All models are severely overconfident (smooth ECE 0.35-0.64 versus 0.10-0.15 reported for textual QA)<n>A consistent self-evaluation versus perturbation dichotomy replicates across both benchmarks and all four fully-covered models.<n>A secondary contribution, structure-aware recalibration, improves AUROC by percentage points over standard post-hoc methods.
  arXiv  Detail & Related papers  (2026-04-14T09:16:53Z)
• Confident Rankings with Fewer Items: Adaptive LLM Evaluation with Continuous Scores [25.638175689769934]
  We present a principled extension of IRT-based adaptive testing to continuous bounded scores (ROUGE, BLEU, LLM-as-a-Judge)<n>We introduce an uncertainty aware ranker with adaptive stopping criteria that achieves reliable model ranking while testing as few items as possible.<n>Our method uses 2% of the items while improving ranking correlation by 0.12 over random sampling, with 95% accuracy on confident predictions.
  arXiv  Detail & Related papers  (2026-01-20T11:59:13Z)
• MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark [57.999567012489706]
  We propose a contamination-free and more challenging benchmark called MMLU-CF.<n>This benchmark reassesses LLMs' understanding of world knowledge by averting both unintentional and malicious data leakage.<n>Our evaluation of mainstream LLMs reveals that the powerful GPT-4o achieves merely a 5-shot score of 73.4% and a 0-shot score of 71.9% on the test set.
  arXiv  Detail & Related papers  (2024-12-19T18:58:04Z)
• Self-Evaluation Improves Selective Generation in Large Language Models [54.003992911447696]
  We reformulate open-ended generation tasks into token-level prediction tasks. We instruct an LLM to self-evaluate its answers. We benchmark a range of scoring methods based on self-evaluation.
  arXiv  Detail & Related papers  (2023-12-14T19:09:22Z)
• PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization [63.55408755562274]
  A judge large language model, named PandaLM, is trained to distinguish the superior model given several large language models. PandaLM addresses vital subjective factors such as relative conciseness, clarity, adherence to instructions, comprehensiveness, and formality. PandaLM achieves 93.75% of GPT-3.5's evaluation ability and 88.28% of GPT-4's in terms of F1-score on our test dataset.
  arXiv  Detail & Related papers  (2023-06-08T10:41:56Z)
• LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond [135.8013388183257]
  We propose a new protocol for inconsistency detection benchmark creation and implement it in a 10-domain benchmark called SummEdits. Most LLMs struggle on SummEdits, with performance close to random chance. The best-performing model, GPT-4, is still 8% below estimated human performance.
  arXiv  Detail & Related papers  (2023-05-23T21:50:06Z)
• Sparse Conditional Hidden Markov Model for Weakly Supervised Named Entity Recognition [68.68300358332156]
  We propose the sparse conditional hidden Markov model (Sparse-CHMM) to evaluate noisy labeling functions. Sparse-CHMM is optimized through unsupervised learning with a three-stage training pipeline. It achieves a 3.01 average F1 score improvement on five comprehensive datasets.
  arXiv  Detail & Related papers  (2022-05-27T20:47:30Z)
• TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task [80.38130122127882]
  TACRED is one of the largest, most widely used crowdsourced datasets in Relation Extraction (RE) In this paper, we investigate the questions: Have we reached a performance ceiling or is there still room for improvement? We find that label errors account for 8% absolute F1 test error, and that more than 50% of the examples need to be relabeled.
  arXiv  Detail & Related papers  (2020-04-30T15:07:37Z)

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.