From Token Probabilities to Semantic Constraints: Towards Declarative Probabilistic Evaluation of Language Models

• URL: http://arxiv.org/abs/2609.13520v1
• Date: Fri, 11 Sep 2026 20:42:23 GMT
• Title: From Token Probabilities to Semantic Constraints: Towards Declarative Probabilistic Evaluation of Language Models
• Abstract summary: We propose a declarative probabilistic framework for pre-training evaluation that makes the semantic structure of model behavior explicit.<n>ModelLog specifies evaluation targets as symbolic constraints over token-level predictions and measures how strongly a model's distribution satisfies those constraints.<n>We show that these evaluation scores can also be interpreted as losses, whose gradients reflect logical strength, informativeness, and variable-level sensitivity.
• Score: 6.885801584985341
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While Large Language Models have improved rapidly, many fundamental questions remain about how to evaluate the knowledge and reasoning abilities they acquire, and how such evaluations relate to the learning signals used in pre-training. In this paper, we propose ModelLog, a declarative probabilistic framework for pre-training evaluation that makes the semantic structure of model behavior explicit and provides new formal tools for relating evaluation to learning. ModelLog specifies evaluation targets as symbolic constraints over token-level predictions and measures how strongly a model's distribution satisfies those constraints. We explore the framework through a new suite of tasks targeting negation, mutual exclusivity, and consistency, finding systematic failures that are difficult to characterize through token likelihood or answer accuracy alone. We further show that these evaluation scores can also be interpreted as losses, whose gradients reflect logical strength, informativeness, and variable-level sensitivity. This links evaluation and learning through a shared semantics, suggesting evaluation methods that diagnose model behavior while also helping to clarify the semantic structure of learning.

Related papers

• Models That Know How Evaluations Are Designed Score Safer [38.21092181000792]
  We investigate evaluation meta-knowledge, defined as parametric knowledge about the structural traits that characterize evaluations.<n>Similar to contamination dataset, where benchmark exposure leads to higher performance through memorization, we hypothesize that models trained on texts describing evaluation practices may implicitly learn to recognize and respond to evaluation-like contexts.<n>Our results demonstrate that evaluation meta-knowledge may inflate safety benchmark performance, introducing a novel confounder that is independent of explicit memorization or verbalized evaluation awareness.
  arXiv  Detail & Related papers  (2026-05-27T15:11:35Z)
• Auditing Language Model Unlearning via Information Decomposition [68.48660428111593]
  We introduce an interpretable, information-theoretic framework for auditing unlearning using Partial Information Decomposition (PID)<n>By comparing model representations before and after unlearning, we decompose the mutual information with the forgotten data into distinct components, formalizing the notions of unlearned and residual knowledge.<n>Our work introduces a principled, representation-level audit for unlearning, offering theoretical insight and actionable tools for safer deployment of language models.
  arXiv  Detail & Related papers  (2026-01-21T15:51:19Z)
• Are We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation Protocols [14.961054239793356]
  We introduce a rigorous unlearning evaluation setup, in which forgetting classes exhibit semantic similarity to downstream task classes.<n>We hope our benchmark serves as a standardized protocol for evaluating unlearning algorithms under realistic conditions.
  arXiv  Detail & Related papers  (2025-03-10T07:11:34Z)
• Causality can systematically address the monsters under the bench(marks) [64.36592889550431]
  Benchmarks are plagued by various biases, artifacts, or leakage.<n>Models may behave unreliably due to poorly explored failure modes.<n> causality offers an ideal framework to systematically address these challenges.
  arXiv  Detail & Related papers  (2025-02-07T17:01:37Z)
• Explaining the Unexplained: Revealing Hidden Correlations for Better Interpretability [1.8274323268621635]
  Real Explainer (RealExp) is an interpretability method that decouples the Shapley Value into individual feature importance and feature correlation importance.<n>RealExp enhances interpretability by precisely quantifying both individual feature contributions and their interactions.
  arXiv  Detail & Related papers  (2024-12-02T10:50:50Z)
• A Probabilistic Perspective on Unlearning and Alignment for Large Language Models [48.96686419141881]
  We introduce the first formal probabilistic evaluation framework for Large Language Models (LLMs)<n> Namely, we propose novel metrics with high probability guarantees concerning the output distribution of a model.<n>Our metrics are application-independent and allow practitioners to make more reliable estimates about model capabilities before deployment.
  arXiv  Detail & Related papers  (2024-10-04T15:44:23Z)
• Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models [6.394084132117747]
  We propose a technique that leverages counterfactual generation to evaluate the faithfulness of attribution methods for autoregressive language models.<n>Our technique generates fluent, in-distribution counterfactuals, making the evaluation protocol more reliable.
  arXiv  Detail & Related papers  (2024-08-21T00:17:59Z)
• 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)
• Evaluation Gaps in Machine Learning Practice [13.963766987258161]
  In practice, evaluations of machine learning models frequently focus on a narrow range of decontextualized predictive behaviours. We examine the evaluation gaps between the idealized breadth of evaluation concerns and the observed narrow focus of actual evaluations. By studying these properties, we demonstrate the machine learning discipline's implicit assumption of a range of commitments which have normative impacts.
  arXiv  Detail & Related papers  (2022-05-11T04:00:44Z)
• Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations [97.91630330328815]
  We conduct a crowdsourcing study, where participants interact with deception detection models that have been trained to distinguish between genuine and fake hotel reviews. We observe that for a linear bag-of-words model, participants with access to the feature coefficients during training are able to cause a larger reduction in model confidence in the testing phase when compared to the no-explanation control.
  arXiv  Detail & Related papers  (2021-12-17T18:29:56Z)
• Evaluations and Methods for Explanation through Robustness Analysis [117.7235152610957]
  We establish a novel set of evaluation criteria for such feature based explanations by analysis. We obtain new explanations that are loosely necessary and sufficient for a prediction. We extend the explanation to extract the set of features that would move the current prediction to a target class.
  arXiv  Detail & Related papers  (2020-05-31T05:52:05Z)

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.