ERRORQUAKE: Heavy-Tailed Error Severity Distributions in Open-Weight Large Language Models

• URL: http://arxiv.org/abs/2606.05170v1
• Date: Wed, 15 Apr 2026 09:22:46 GMT
• Title: ERRORQUAKE: Heavy-Tailed Error Severity Distributions in Open-Weight Large Language Models
• Abstract summary: Hallucination benchmarks report a single error count and treat all errors as equivalent, yet a wrong date and a fabricated court ruling differ by orders of magnitude.<n>We introduce Errorquake-10k, a benchmark scoring each response on a continuous 0-4 severity scale across 8 domains and 5 difficulty tiers.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: At matched accuracy, open-weight LLMs differ substantially in the shape of their error severity distribution -- a difference invisible to the scalar error rate. Hallucination benchmarks report a single error count and treat all errors as equivalent, yet a wrong date and a fabricated court ruling differ by orders of magnitude. We introduce Errorquake-10k, a 10,000-query benchmark scoring each response on a continuous 0-4 severity scale across 8 domains and 5 difficulty tiers, and we fit per-model severity distributions for 21 open-weight models. For each model we estimate a severity distribution index (b, the Gutenberg-Richter upper-tail slope) with 95% bootstrap confidence intervals. Headline: across the 210 model pairs, 85 have disjoint 95% b confidence intervals at matched accuracy (|Delta epsilon| < 0.05) on human-consensus scoring, e.g. deepseek-v3.2 vs. ministral-14b at epsilon = 0.586 and Delta b = 0.47. A 519-item three-rater human validation study confirms measurement reliability (ICC(2,k=3) = 0.85), validates the LLM-judge ranking (rho = 0.89), and confirms the dense-model scaling correlation on human data (rho_s = -0.86). We prove a Non-Reducibility Theorem showing that severity profile and error rate are informationally non-redundant (I(b; model | epsilon) = 1.56 bits; 64.5% of cross-model b variance is unexplained by epsilon). A severity mechanism taxonomy (kappa = 0.83) reveals that error type shifts categorically with severity: low-severity errors are retrievals (71%); high-severity errors are fabrications (39%) -- and this composition differs by model size (p < 0.0001). Severity distribution should be reported alongside accuracy; it carries discriminative information that the error rate cannot.

Related papers

• Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection [66.44527094471619]
  We present RECAL, an unsupervised framework using relation-balanced masked graph learning to better capture rare interaction patterns.<n>On three DARPA E3 datasets, RECAL achieves F1 scores of 99.99%, 99.93%, and 99.99%, outperforming the best baseline on each dataset by 0.88, 0.82, and 0.42 percentage points, respectively.
  arXiv  Detail & Related papers  (2026-09-15T00:31:01Z)
• Operator-on-F complements value-equivalence: a planning-time diagnostic for latent world models [0.0]
  We introduce a complementary diagnostic, operator-on-F, that compares a model's k-step latent pushforward to the environment's on an observable subset F.<n>On a TD-MPC2 size sweep over cheetah-run, reward-prediction error stays within [0.028, 0.091] for every model size.
  arXiv  Detail & Related papers  (2026-07-05T19:09:07Z)
• LLM Doesn't Know What It Doesn't Know: Detecting Epistemic Blind Spots via Cross-Model Attribution Divergence on Clinical Tabular Data [2.1443570696048906]
  Large language models (LLMs) are increasingly applied to structured clinical data.<n>We compare Qwen 2.5 7B and XGBoost on a prediction task via attribution divergence analysis.
  arXiv  Detail & Related papers  (2026-06-17T18:49:44Z)
• Automated Proving of Shannon-Type Entropy Inequalities via Fine-Tuned Language Models and Guided Tree Search [50.16356451328644]
  Proving Shannon-type entropy inequalities is a fundamental task in information theory.<n>We investigate whether small-scale large language models, fine-tuned on atomic proof steps, can automate this process.<n>We show that GPT-5.5 solves 1.7% samples under zero-shot prompting while Psitip solves 33.3% samples.
  arXiv  Detail & Related papers  (2026-06-04T05:43:12Z)
• Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction [51.56484100374058]
  Text detectors amplify a pretrained typicality axis; they do not construct an AI-vs-human boundary.<n>On raw encoders before any task supervision, projecting onto centroid(AI)-centroid(HC3) achieves NYT-vs-HC3 AUROC 0.806/0.944/0.834 across three architectures.<n>On RoBERTa-base, raw projection exceeds fine-tuning; on RoBERTa-base, full fine-tuning reduces discrimination below raw on both fluent-formal populations tested.
  arXiv  Detail & Related papers  (2026-05-20T19:08:38Z)
• 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)
• Verbal Confidence Saturation in 3-9B Open-Weight Instruction-Tuned LLMs: A Pre-Registered Psychometric Validity Screen [0.0]
  We tested whether seven instruction-tuned open-weight models produce verbalised confidence that meets minimal validity criteria.<n>We found Categorical elicitation did not rescue validity.<n> Token-level logprobability did not usefully predict verbalised confidence under the observed variance regime.
  arXiv  Detail & Related papers  (2026-04-24T04:45:21Z)
• The Rotation Gap Is Not An Error: Ternary Structure in IBM Quantum Hardware [0.0]
  Quantum error correction assumes that all syndrome activations represent errors requiring correction.<n>We present evidence from 756 QEC runs across three IBM Eagle r3 processors that this assumption is wrong.<n> Hardware exhibits sub-Poissonian syndrome statistics, indicating that a fraction of syndrome events are not random noise but structured cooperative transitions.
  arXiv  Detail & Related papers  (2026-04-13T18:54:39Z)
• Decomposing LLM Self-Correction: The Accuracy-Correction Paradox and Error Depth Hypothesis [6.901585308625979]
  We decompose self-correction into three sub-capabilities: error detection, error localization, and error correction.<n>Our findings challenge linear assumptions about model capability and self-improvement.
  arXiv  Detail & Related papers  (2025-12-24T21:51:24Z)
• CorBenchX: Large-Scale Chest X-Ray Error Dataset and Vision-Language Model Benchmark for Report Error Correction [11.731590131260424]
  CorBenchX is a suite for automated error detection and correction in chest X-ray reports.<n>We first synthesize a large-scale dataset of 26,326 chest X-ray error reports.<n>We benchmark both open- and closed-source vision-language models.
  arXiv  Detail & Related papers  (2025-05-17T15:39:39Z)
• Classification Error Bound for Low Bayes Error Conditions in Machine Learning [50.25063912757367]
  We study the relationship between the error mismatch and the Kullback-Leibler divergence in machine learning.<n>Motivated by recent observations of low model-based classification errors in many machine learning tasks, we propose a linear approximation of the classification error bound for low Bayes error conditions.
  arXiv  Detail & Related papers  (2025-01-27T11:57:21Z)
• Robust Fine-tuning of Zero-shot Models via Variance Reduction [56.360865951192324]
  When fine-tuning zero-shot models, our desideratum is for the fine-tuned model to excel in both in-distribution (ID) and out-of-distribution (OOD) We propose a sample-wise ensembling technique that can simultaneously attain the best ID and OOD accuracy without the trade-offs.
  arXiv  Detail & Related papers  (2024-11-11T13:13:39Z)
• Proximity-Informed Calibration for Deep Neural Networks [49.330703634912915]
  ProCal is a plug-and-play algorithm with a theoretical guarantee to adjust sample confidence based on proximity. We show that ProCal is effective in addressing proximity bias and improving calibration on balanced, long-tail, and distribution-shift settings.
  arXiv  Detail & Related papers  (2023-06-07T16:40:51Z)
• 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.