RPAM: A Principled Metric for Evaluating Associations in Language Models with High Predictive Validity in Downstream Outputs

• URL: http://arxiv.org/abs/2607.05679v1
• Date: Mon, 06 Jul 2026 22:48:13 GMT
• Title: RPAM: A Principled Metric for Evaluating Associations in Language Models with High Predictive Validity in Downstream Outputs
• Abstract summary: Language models (LMs) exhibit problematic biases, such as stereotypes.<n>Effectively analyzing and mitigating such biases requires accurate and generalizable evaluation methods.<n>We introduce the Relative Probability Association Metric (RPAM), an association evaluation metric for generative LMs.
• Score: 8.688578727646405
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Language models (LMs) exhibit problematic biases, such as stereotypes. Effectively analyzing and mitigating such biases requires accurate and generalizable evaluation methods of the underlying associations. Some existing approaches focus on downstream metrics that analyze associations in generated text. Since generated text content can vary drastically across LMs, such metrics often require specialized evaluation datasets, which limits the generalization of such downstream metrics. In contrast, upstream metrics examine LMs at the fundamental level of embeddings or continuation probabilities, enabling principled association analyses across LMs. Yet, to date, no upstream metric for generative LMs has uncovered a strong relationship with real-world associations, including those measured in generated text. To address this gap, we introduce the Relative Probability Association Metric (RPAM), an association evaluation metric for generative LMs. For three LMs of different quality of language generation and purpose (Mistral-7B-Instruct, Mistral-7B, and GPT-2) and well-studied evaluation datasets (WEAT-WS, Bellezza, WS-353, and SST2), we find a strong relationship between upstream RPAM measurements and corresponding implicit and explicit associations observed in humans, as well as biases measured downstream with LM-specific tasks, outperforming prior record values where applicable.

Related papers

• Every Token Counts: Exact Likert-Scale Distributions for Measuring LLM Attitudes and Biases [0.0]
  We introduce an analytically exact framework for the controlled behavioral evaluation of Large Language Models (LLMs)<n>We replace unstructured prompting with fully crossed factorial experiments to systematically isolate causal main and interaction effects.<n>We derive a multivariate ordinal consensus metric and a distributional ANOVA to process these PMFs analytically.<n>We validate our framework with a case study on consumer ethnocentrism across five LLMs, demonstrating how our approach isolates systemic country-of-origin biases that aggregate benchmarks otherwise obscure.
  arXiv  Detail & Related papers  (2026-08-11T05:20:06Z)
• Multi-Level Contextual Token Relation Modeling for Machine-Generated Text Detection [105.1403233464793]
  Machine-generated texts (MGTs) pose risks such as disinformation and phishing, underscoring the need for reliable detection.<n> Metric-based methods, which extract statistically distinguishable features of MGTs, are often more practical than complex model-based methods.<n>We propose a multi-level contextual token relation modeling framework for MGT detection.
  arXiv  Detail & Related papers  (2026-05-15T15:55:58Z)
• Evaluating Extremely Low-Resource Machine Translation: A Comparative Study of ChrF++ and BLEU Metrics [69.2321983942375]
  This work presents a comparative analysis of BLEU, an n-gram-based metric, and ChrF++, a character-based metric, for MT evaluation in ELRL settings.<n>We examine how each metric responds to translation artifacts, including hallucinations, repetition, source-text copying, and diacritic (textitmatra) variations across three ELRLs: Magahi, Bhojpuri, and Chhattisgarhi.<n>While recent work often relies solely on ChrF++, our findings show that BLEU, despite its lower absolute scores, provides complementary lexical-precision insights that improve interpretability.
  arXiv  Detail & Related papers  (2026-02-19T14:56:42Z)
• A Critical Study of Automatic Evaluation in Sign Language Translation [17.083206782232185]
  It remains unclear to what extent text-based metrics can reliably capture the quality of sign language translation (SLT) outputs.<n>We analyze six metrics, including BLEU, chrF, and ROUGE, as well as BLEURT on the one hand, and large language model (LLM)-based evaluators such as G-Eval and GEMBA zero-shot direct assessment on the other.
  arXiv  Detail & Related papers  (2025-10-29T11:57:03Z)
• LLMs Are Not Scorers: Rethinking MT Evaluation with Generation-Based Methods [0.0]
  We propose a generation-based evaluation paradigm that leverages decoder-only language models to produce high-quality references.<n> Empirical results show that our method outperforms both intra-LLM direct scoring baselines and external non-LLM reference-free metrics from MTME.
  arXiv  Detail & Related papers  (2025-05-22T02:14:38Z)
• Detecting Training Data of Large Language Models via Expectation Maximization [62.28028046993391]
  We introduce EM-MIA, a novel membership inference method that iteratively refines membership scores and prefix scores via an expectation-maximization algorithm.<n> EM-MIA achieves state-of-the-art results on WikiMIA.
  arXiv  Detail & Related papers  (2024-10-10T03:31:16Z)
• Machine Translation Meta Evaluation through Translation Accuracy Challenge Sets [92.38654521870444]
  We introduce ACES, a contrastive challenge set spanning 146 language pairs. This dataset aims to discover whether metrics can identify 68 translation accuracy errors. We conduct a large-scale study by benchmarking ACES on 50 metrics submitted to the WMT 2022 and 2023 metrics shared tasks.
  arXiv  Detail & Related papers  (2024-01-29T17:17:42Z)
• LLMs as Narcissistic Evaluators: When Ego Inflates Evaluation Scores [23.568883428947494]
  We investigate whether prominent LM-based evaluation metrics demonstrate a favorable bias toward their respective underlying LMs in the context of summarization tasks. Our findings unveil a latent bias, particularly pronounced when such evaluation metrics are used in a reference-free manner without leveraging gold summaries. These results underscore that assessments provided by generative evaluation models can be influenced by factors beyond the inherent text quality.
  arXiv  Detail & Related papers  (2023-11-16T10:43:26Z)
• Towards Multiple References Era -- Addressing Data Leakage and Limited Reference Diversity in NLG Evaluation [55.92852268168816]
  N-gram matching-based evaluation metrics, such as BLEU and chrF, are widely utilized across a range of natural language generation (NLG) tasks. Recent studies have revealed a weak correlation between these matching-based metrics and human evaluations. We propose to utilize textitmultiple references to enhance the consistency between these metrics and human evaluations.
  arXiv  Detail & Related papers  (2023-08-06T14:49:26Z)
• 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)
• Bring Your Own Data! Self-Supervised Evaluation for Large Language Models [52.15056231665816]
  We propose a framework for self-supervised evaluation of Large Language Models (LLMs) We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence. We find strong correlations between self-supervised and human-supervised evaluations.
  arXiv  Detail & Related papers  (2023-06-23T17:59:09Z)
• INSTRUCTSCORE: Explainable Text Generation Evaluation with Finegrained Feedback [80.57617091714448]
  We present InstructScore, an explainable evaluation metric for text generation. We fine-tune a text evaluation metric based on LLaMA, producing a score for generated text and a human readable diagnostic report.
  arXiv  Detail & Related papers  (2023-05-23T17:27:22Z)
• TRUE: Re-evaluating Factual Consistency Evaluation [29.888885917330327]
  We introduce TRUE: a comprehensive study of factual consistency metrics on a standardized collection of existing texts from diverse tasks. Our standardization enables an example-level meta-evaluation protocol that is more actionable and interpretable than previously reported correlations. Across diverse state-of-the-art metrics and 11 datasets we find that large-scale NLI and question generation-and-answering-based approaches achieve strong and complementary results.
  arXiv  Detail & Related papers  (2022-04-11T10:14:35Z)

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.