LookAlike: Consistent Distractor Generation in Math MCQs

• URL: http://arxiv.org/abs/2505.01903v2
• Date: Sat, 07 Jun 2025 18:24:53 GMT
• Title: LookAlike: Consistent Distractor Generation in Math MCQs
• Authors: Nisarg Parikh, Nigel Fernandez, Alexander Scarlatos, Simon Woodhead, Andrew Lan,
• Abstract summary: We propose LookAlike, a method that improves error-distractor consistency via preference optimization.<n>Our two main innovations are: (a) mining synthetic preference pairs from model inconsistencies, and (b) alternating supervised fine-tuning.<n>LookAlike achieves 51.6% accuracy in distractor generation and 57.2% in error generation under LLM-as-a-judge evaluation.
• Score: 42.19039301965107
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) are increasingly used to generate distractors for multiple-choice questions (MCQs), especially in domains like math education. However, existing approaches are limited in ensuring that the generated distractors are consistent with common student errors. We propose LookAlike, a method that improves error-distractor consistency via preference optimization. Our two main innovations are: (a) mining synthetic preference pairs from model inconsistencies, and (b) alternating supervised fine-tuning (SFT) with Direct Preference Optimization (DPO) to stabilize training. Unlike prior work that relies on heuristics or manually annotated preference data, LookAlike uses its own generation inconsistencies as dispreferred samples, thus enabling scalable and stable training. Evaluated on a real-world dataset of 1,400+ math MCQs, LookAlike achieves 51.6% accuracy in distractor generation and 57.2% in error generation under LLM-as-a-judge evaluation, outperforming an existing state-of-the-art method (45.6% / 47.7%). These improvements highlight the effectiveness of preference-based regularization and inconsistency mining for generating consistent math MCQ distractors at scale.

Related papers

• Feature-Wise Mixing for Mitigating Contextual Bias in Predictive Supervised Learning [0.0]
  This paper introduces a feature-wise mixing framework to mitigate contextual bias.<n>It was done by redistributing feature representations across multiple contextual datasets.<n>It achieved an average bias reduction of 43.35% and a statistically significant decrease in mean squared error.
  arXiv  Detail & Related papers  (2025-06-28T23:12:59Z)
• Let the Fuzzy Rule Speak: Enhancing In-context Learning Debiasing with Interpretability [12.287692969438169]
  Large language models (LLMs) often struggle with balanced class accuracy in text classification tasks using in-context learning (ICL)<n>This paper delves deeper into the class accuracy imbalance issue, identifying that it arises because certain classes consistently receive disproportionately high ICL probabilities.<n>We introduce FuRud, a method for sample-level class probability correction.
  arXiv  Detail & Related papers  (2024-12-26T01:56:42Z)
• CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges [21.580762639442913]
  We introduce CalibraEval, a novel label-free method for mitigating selection bias during inference. CalibraEval reformulates debiasing as an optimization task aimed at adjusting observed prediction distributions to align with unbiased prediction distributions. We show that CalibraEval effectively mitigates selection bias and improves performance compared to existing debiasing methods.
  arXiv  Detail & Related papers  (2024-10-20T13:47:39Z)
• Offline Model-Based Optimization by Learning to Rank [26.21886715050762]
  We argue that regression models trained with mean squared error (MSE) are not well-aligned with the primary goal of offline model-based optimization.<n>We propose learning a ranking-based model that leverages learning to rank techniques to prioritize promising designs based on their relative scores.
  arXiv  Detail & Related papers  (2024-10-15T11:15:03Z)
• Subtle Errors Matter: Preference Learning via Error-injected Self-editing [59.405145971637204]
  We propose a novel preference learning framework called eRror-Injected Self-Editing (RISE)<n>RISE injects predefined subtle errors into pivotal tokens in reasoning or steps to construct hard pairs for error mitigation.<n>Experiments validate the effectiveness of RISE, with preference learning on Qwen2-7B-Instruct yielding notable improvements of 3.0% on GSM8K and 7.9% on MATH with only 4.5K training samples.
  arXiv  Detail & Related papers  (2024-10-09T07:43:38Z)
• Uncertainty Aware Learning for Language Model Alignment [97.36361196793929]
  We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios. We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples. Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-06-07T11:37:45Z)
• Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models [102.72940700598055]
  In reasoning tasks, even a minor error can cascade into inaccurate results. We develop a method that avoids introducing external resources, relying instead on perturbations to the input. Our training approach randomly masks certain tokens within the chain of thought, a technique we found to be particularly effective for reasoning tasks.
  arXiv  Detail & Related papers  (2024-03-04T16:21:54Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
  Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
  arXiv  Detail & Related papers  (2022-01-11T23:01:12Z)
• MIO : Mutual Information Optimization using Self-Supervised Binary Contrastive Learning [12.365801596593936]
  We model our pre-training task as a binary classification problem to induce an implicit contrastive effect.<n>Unlike existing methods, the proposed loss function optimize the mutual information in positive and negative pairs.<n>The proposed method outperforms SOTA self-supervised contrastive frameworks on benchmark datasets.
  arXiv  Detail & Related papers  (2021-11-24T17:51:29Z)
• The Interplay between Distribution Parameters and the Accuracy-Robustness Tradeoff in Classification [0.0]
  Adrial training tends to result in models that are less accurate on natural (unperturbed) examples compared to standard models. This can be attributed to either an algorithmic shortcoming or a fundamental property of the training data distribution. In this work, we focus on the latter case under a binary Gaussian mixture classification problem.
  arXiv  Detail & Related papers  (2021-07-01T06:57:50Z)
• Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning [78.83598532168256]
  Marginal-likelihood based model-selection is rarely used in deep learning due to estimation difficulties. Our work shows that marginal likelihoods can improve generalization and be useful when validation data is unavailable.
  arXiv  Detail & Related papers  (2021-04-11T09:50:24Z)

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.