Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals

• URL: http://arxiv.org/abs/2505.13972v1
• Date: Tue, 20 May 2025 06:12:17 GMT
• Title: Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals
• Authors: Qianli Wang, Van Bach Nguyen, Nils Feldhus, Luis Felipe Villa-Arenas, Christin Seifert, Sebastian Möller, Vera Schmitt,
• Abstract summary: Judge models are used to evaluate the validity of generated counterfactuals for large language models.<n>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.
• Score: 12.846807471105064
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Counterfactual examples are widely employed to enhance the performance and robustness of large language models (LLMs) through counterfactual data augmentation (CDA). However, the selection of the judge model used to evaluate label flipping, the primary metric for assessing the validity of generated counterfactuals for CDA, yields inconsistent results. To decipher this, we define four types of relationships between the counterfactual generator and judge models. Through extensive experiments involving two state-of-the-art LLM-based methods, three datasets, five generator models, and 15 judge models, complemented by a user study (n = 90), we demonstrate that judge models with an independent, non-fine-tuned relationship to the generator model provide the most reliable label flipping evaluations. Relationships between the generator and judge models, which are closely aligned with the user study for CDA, result in better model performance and robustness. Nevertheless, we find that the gap between the most effective judge models and the results obtained from the user study remains considerably large. This suggests that a fully automated pipeline for CDA may be inadequate and requires human intervention.

Related papers

• Model Utility Law: Evaluating LLMs beyond Performance through Mechanism Interpretable Metric [99.56567010306807]
  Large Language Models (LLMs) have become indispensable across academia, industry, and daily applications.<n>One core challenge of evaluation in the large language model (LLM) era is the generalization issue.<n>We propose Model Utilization Index (MUI), a mechanism interpretability enhanced metric that complements traditional performance scores.
  arXiv  Detail & Related papers  (2025-04-10T04:09:47Z)
• 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)
• Language Model Preference Evaluation with Multiple Weak Evaluators [78.53743237977677]
  GED (Preference Graph Ensemble and Denoise) is a novel approach that leverages multiple model-based evaluators to construct preference graphs.<n>In particular, our method consists of two primary stages: aggregating evaluations into a unified graph and applying a denoising process.<n>We provide theoretical guarantees for our framework, demonstrating its efficacy in recovering the ground truth preference structure.
  arXiv  Detail & Related papers  (2024-10-14T01:57:25Z)
• Direct Judgement Preference Optimization [66.83088028268318]
  We train large language models (LLMs) as generative judges to evaluate and critique other models' outputs. We employ three approaches to collect the preference pairs for different use cases, each aimed at improving our generative judge from a different perspective. Our model robustly counters inherent biases such as position and length bias, flexibly adapts to any evaluation protocol specified by practitioners, and provides helpful language feedback for improving downstream generator models.
  arXiv  Detail & Related papers  (2024-09-23T02:08:20Z)
• A Multi-Armed Bandit Approach to Online Selection and Evaluation of Generative Models [23.91197677628145]
  In this work, we propose an online evaluation and selection framework to find the generative model that maximizes a standard assessment score.<n>Specifically, we develop the MAB-based selection of generative models considering the Fr'echet Distance (FD) and Inception Score (IS) metrics.<n>Our empirical results suggest the efficacy of MAB approaches for the sample-efficient evaluation and selection of deep generative models.
  arXiv  Detail & Related papers  (2024-06-11T16:57:48Z)
• Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models [56.02275285521847]
  We propose to evaluate models using a Panel of LLm evaluators (PoLL) We find that using a PoLL composed of a larger number of smaller models outperforms a single large judge, exhibits less intra-model bias due to its composition of disjoint model families, and does so while being over seven times less expensive.
  arXiv  Detail & Related papers  (2024-04-29T15:33:23Z)
• Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models [3.9052860539161918]
  We propose a simple method for measuring a scale of models' reliance on any identified spurious feature. We assess the robustness towards a large set of known and newly found prediction biases for various pre-trained models and debiasing methods in Question Answering (QA) We find that while existing debiasing methods can mitigate reliance on a chosen spurious feature, the OOD performance gains of these methods can not be explained by mitigated reliance on biased features.
  arXiv  Detail & Related papers  (2023-05-11T14:35:00Z)
• Evaluating Representations with Readout Model Switching [19.907607374144167]
  In this paper, we propose to use the Minimum Description Length (MDL) principle to devise an evaluation metric. We design a hybrid discrete and continuous-valued model space for the readout models and employ a switching strategy to combine their predictions. The proposed metric can be efficiently computed with an online method and we present results for pre-trained vision encoders of various architectures.
  arXiv  Detail & Related papers  (2023-02-19T14:08:01Z)
• Multidimensional Item Response Theory in the Style of Collaborative Filtering [0.8057006406834467]
  This paper presents a machine learning approach to multidimensional item response theory (MIRT) Inspired by collaborative filtering, we define a general class of models that includes many MIRT models. We discuss the use of penalized joint maximum likelihood (JML) to estimate individual models and cross-validation to select the best performing model.
  arXiv  Detail & Related papers  (2023-01-03T00:56:27Z)
• Deep Learning Models for Knowledge Tracing: Review and Empirical Evaluation [2.423547527175807]
  We review and evaluate a body of deep learning knowledge tracing (DLKT) models with openly available and widely-used data sets. The evaluated DLKT models have been reimplemented for assessing and replicability of previously reported results.
  arXiv  Detail & Related papers  (2021-12-30T14:19:27Z)
• Sparse MoEs meet Efficient Ensembles [49.313497379189315]
  We study the interplay of two popular classes of such models: ensembles of neural networks and sparse mixture of experts (sparse MoEs) We present Efficient Ensemble of Experts (E$3$), a scalable and simple ensemble of sparse MoEs that takes the best of both classes of models, while using up to 45% fewer FLOPs than a deep ensemble.
  arXiv  Detail & Related papers  (2021-10-07T11:58:35Z)
• Comparing Test Sets with Item Response Theory [53.755064720563]
  We evaluate 29 datasets using predictions from 18 pretrained Transformer models on individual test examples. We find that Quoref, HellaSwag, and MC-TACO are best suited for distinguishing among state-of-the-art models. We also observe span selection task format, which is used for QA datasets like QAMR or SQuAD2.0, is effective in differentiating between strong and weak models.
  arXiv  Detail & Related papers  (2021-06-01T22:33:53Z)

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.