The Partial Testimony of Logs: Evaluation of Language Model Generation under Confounded Model Choice

• URL: http://arxiv.org/abs/2605.01311v1
• Date: Sat, 02 May 2026 07:55:55 GMT
• Title: The Partial Testimony of Logs: Evaluation of Language Model Generation under Confounded Model Choice
• Abstract summary: We study a three-source design that combines a large confounded observational log for scale, a small randomized experiment for unconfounded scoring, and an offline simulator.<n>Our main result is an identification theorem showing that the randomized experiment and the simulator are together enough to recover causal model values.
• Score: 22.228743542695835
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Offline evaluation of language models from usage logs is biased when model choice is confounded: the same user-side factors that influence which model is used can also influence how its output is judged, so raw comparisons of logged scores mix self-selected populations rather than estimating a common quantity of interest. A small randomized experiment can break this bias by overriding model choice, but in practice such experiments are scarce and costly. We study a three-source design that combines a large confounded observational log (OBS) for scale, a small randomized experiment (EXP) for unconfounded scoring, and an offline simulator (SIM) that replays candidate models on cached contexts. Our main result is an identification theorem showing that the randomized experiment and the simulator are together enough to recover causal model values; the observational log enters only afterward, to reduce estimation error rather than to make the causal comparison valid. Six estimator families are evaluated in a controlled semi-synthetic validation and in two real-task cached benchmarks for summarization and coding. No family dominates every regime; relative performance depends on the amount of unbiased EXP supervision and on how closely the target reward aligns with OBS-derived structure.

Related papers

• Valid Best-Model Identification for LLM Evaluation via Low-Rank Factorization [17.34147279018477]
  We propose a principled framework that combines MAB with cheap predicted scores without compromising statistical validity.<n>We derive doubly robust estimators of each model's performance that use the low-rank predictions to reduce variance.<n> Empirical results on real-world benchmarks show that our approach reduces the number of required evaluations, yielding meaningful savings in compute and cost.
  arXiv  Detail & Related papers  (2026-05-11T11:43:28Z)
• Model Correlation Detection via Random Selection Probing [62.093777777813756]
  Existing similarity-based methods require access to model parameters or produce scores without thresholds.<n>We introduce Random Selection Probing (RSP), a hypothesis-testing framework that formulates model correlation detection as a statistical test.<n>RSP produces rigorous p-values that quantify evidence of correlation.
  arXiv  Detail & Related papers  (2025-09-29T01:40:26Z)
• Consistency-based Abductive Reasoning over Perceptual Errors of Multiple Pre-trained Models in Novel Environments [5.5855749614100825]
  This paper addresses the hypothesis that leveraging multiple pre-trained models can mitigate this recall reduction.<n>We formulate the challenge of identifying and managing conflicting predictions from various models as a consistency-based abduction problem.<n>Our results validate the use of consistency-based abduction as an effective mechanism to robustly integrate knowledge from multiple imperfect models in challenging, novel scenarios.
  arXiv  Detail & Related papers  (2025-05-25T23:17:47Z)
• Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals [17.368361664470925]
  We show that judge models with an independent, non-fine-tuned relationship to the generator model provide the most reliable label flipping evaluations.<n>We find that the gap between the most effective judge models and the results obtained from the user study remains considerably large.
  arXiv  Detail & Related papers  (2025-05-20T06:12:17Z)
• Model-free Methods for Event History Analysis and Efficient Adjustment (PhD Thesis) [55.2480439325792]
  This thesis is a series of independent contributions to statistics unified by a model-free perspective.<n>The first chapter elaborates on how a model-free perspective can be used to formulate flexible methods that leverage prediction techniques from machine learning.<n>The second chapter studies the concept of local independence, which describes whether the evolution of one process is directly influenced by another.
  arXiv  Detail & Related papers  (2025-02-11T19:24:09Z)
• Rethinking Relation Extraction: Beyond Shortcuts to Generalization with a Debiased Benchmark [53.876493664396506]
  Benchmarks are crucial for evaluating machine learning algorithm performance, facilitating comparison and identifying superior solutions.<n>This paper addresses the issue of entity bias in relation extraction tasks, where models tend to rely on entity mentions rather than context.<n>We propose a debiased relation extraction benchmark DREB that breaks the pseudo-correlation between entity mentions and relation types through entity replacement.<n>To establish a new baseline on DREB, we introduce MixDebias, a debiasing method combining data-level and model training-level techniques.
  arXiv  Detail & Related papers  (2025-01-02T17:01:06Z)
• Estimating Causal Effects from Learned Causal Networks [56.14597641617531]
  We propose an alternative paradigm for answering causal-effect queries over discrete observable variables. We learn the causal Bayesian network and its confounding latent variables directly from the observational data. We show that this emphmodel completion learning approach can be more effective than estimand approaches.
  arXiv  Detail & Related papers  (2024-08-26T08:39:09Z)
• Investigating the Robustness of Counterfactual Learning to Rank Models: A Reproducibility Study [71.04084063541777]
  Counterfactual learning to rank has attracted extensive attention in the IR community.<n>Models can be theoretically unbiased when the user behavior assumption is correct and the propensity estimation is accurate.<n>Their effectiveness is usually empirically evaluated via simulation-based experiments due to a lack of widely available, large-scale, real click logs.
  arXiv  Detail & Related papers  (2024-04-04T10:54:38Z)
• High Precision Causal Model Evaluation with Conditional Randomization [10.23470075454725]
  We introduce a novel low-variance estimator for causal error, dubbed as the pairs estimator. By applying the same IPW estimator to both the model and true experimental effects, our estimator effectively cancels out the variance due to IPW and achieves a smaller variance. Our method offers a simple yet powerful solution to evaluate causal inference models in conditional randomization settings without complicated modification of the IPW estimator itself.
  arXiv  Detail & Related papers  (2023-11-03T13:22:27Z)
• Uncertainty Estimation for Language Reward Models [5.33024001730262]
  Language models can learn a range of capabilities from unsupervised training on text corpora. It is often easier for humans to choose between options than to provide labeled data, and prior work has achieved state-of-the-art performance by training a reward model from such preference comparisons. We seek to address these problems via uncertainty estimation, which can improve sample efficiency and robustness using active learning and risk-averse reinforcement learning.
  arXiv  Detail & Related papers  (2022-03-14T20:13:21Z)
• General Greedy De-bias Learning [163.65789778416172]
  We propose a General Greedy De-bias learning framework (GGD), which greedily trains the biased models and the base model like gradient descent in functional space. GGD can learn a more robust base model under the settings of both task-specific biased models with prior knowledge and self-ensemble biased model without prior knowledge.
  arXiv  Detail & Related papers  (2021-12-20T14:47:32Z)
• On the Discrepancy between Density Estimation and Sequence Generation [92.70116082182076]
  log-likelihood is highly correlated with BLEU when we consider models within the same family. We observe no correlation between rankings of models across different families.
  arXiv  Detail & Related papers  (2020-02-17T20:13:35Z)

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.