Towards Reward Modeling for AI Tutors in Math Mistake Remediation

• URL: http://arxiv.org/abs/2603.24375v1
• Date: Wed, 25 Mar 2026 14:56:08 GMT
• Title: Towards Reward Modeling for AI Tutors in Math Mistake Remediation
• Abstract summary: We develop and release Bradley-Terry preference models trained on weighted-sum rankings.<n>Using only synthetic data, our best model reaches 0.69 pairwise accuracy on a human preference test.
• Score: 13.755739827287542
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Evaluating the pedagogical quality of AI tutors remains challenging: standard NLG metrics do not determine whether responses identify mistakes, scaffold reasoning, or avoid revealing the answers. For the task of mistake remediation, we derive a hierarchy of pedagogical aspects from human pairwise preferences on MRBench, and synthesize minimally contrastive response pairs that differ along key aspects (e.g., mistake identification and location, targetedness, scaffolding, actionability, clarity, and coherence). We develop and release Bradley-Terry preference models trained on weighted-sum rankings that we automatically create from MRBench, synthetic pairs, and data combinations. Using only synthetic data, our best model reaches 0.69 pairwise accuracy on a human preference test, and combining weighted-sum data with targeted synthetic groups improves accuracy to 0.74, outperforming larger general-purpose reward models while using only a 0.5B-parameter backbone.

Related papers

• Putting HUMANS first: Efficient LAM Evaluation with Human Preference Alignment [53.72927532626824]
  We show that subsets of just 50 examples (0.3% of data) can achieve over 0.93 Pearson correlation with full benchmark scores.<n>To better predict preferences, we trained regression models on these selected subsets, achieving 0.98 correlation.<n>This demonstrates that in regression modeling, well-curated subsets outpredict the full benchmark, showing quality over quantity.
  arXiv  Detail & Related papers  (2026-04-20T00:57:31Z)
• One Model to Critique Them All: Rewarding Agentic Tool-Use via Efficient Reasoning [54.580646706013965]
  Reward models (RMs) play a critical role in aligning large language models with human preferences.<n>We introduce ToolRM, a family of lightweight generative RMs tailored for general tool-use scenarios.<n>To build these models, we propose a novel pipeline that constructs pairwise preference data using rule-based scoring and multidimensional sampling.
  arXiv  Detail & Related papers  (2025-10-30T06:08:27Z)
• LLM Routing with Dueling Feedback [49.67815163970033]
  We study the problem of selecting the best model for each query while balancing user satisfaction, model expertise, and inference cost.<n>We formulate routing as contextual dueling bandits, learning from pairwise preference feedback rather than absolute scores.<n>We introduce Category-Calibrated Fine-Tuning (CCFT), a representation-learning method that derives model embeddings from offline data using contrastive fine-tuning with categorical weighting.
  arXiv  Detail & Related papers  (2025-10-01T12:52:25Z)
• The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains [50.66245575710432]
  We show that paired preference data consisting of individually weak data points can enable gains beyond the strength of each individual data point.<n>Our work shows that models can learn surprisingly well from paired data that might typically be considered weak.
  arXiv  Detail & Related papers  (2025-07-08T17:14:44Z)
• Advancing Tabular Stroke Modelling Through a Novel Hybrid Architecture and Feature-Selection Synergy [0.9999629695552196]
  The present work develops and validates a data-driven and interpretable machine-learning framework designed to predict strokes.<n>Ten routinely gathered demographic, lifestyle, and clinical variables were sourced from a public cohort of 4,981 records.<n>The proposed model achieved an accuracy rate of 97.2% and an F1-score of 97.15%, indicating a significant enhancement compared to the leading individual model.
  arXiv  Detail & Related papers  (2025-05-18T21:46:45Z)
• Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment [35.80989342492335]
  noisy preferences in human feedback can lead to reward misgeneralization.<n>This paper aims to identify how noisy preferences differ from human-aligned preferences in reward modeling.<n>We propose an online Collaborative Reward Modeling framework to achieve robust preference learning.
  arXiv  Detail & Related papers  (2025-05-15T10:58:20Z)
• Grounding Synthetic Data Evaluations of Language Models in Unsupervised Document Corpora [9.871701356351542]
  Language Models (LMs) continue to advance, improving response quality and coherence.<n>A plethora of evaluation benchmarks have been constructed to assess model quality, response appropriateness, and reasoning capabilities.<n>We propose a methodology for automating the construction of fact-based synthetic data model evaluations grounded in document populations.
  arXiv  Detail & Related papers  (2025-05-13T18:50:03Z)
• MindGYM: What Matters in Question Synthesis for Thinking-Centric Fine-Tuning? [51.85759493254735]
  MindGYM is a structured and scalable framework for question synthesis.<n>It infuses high-level reasoning objectives to shape the model's synthesis behavior.<n>It composes more complex multi-hop questions based on QA seeds for deeper reasoning.
  arXiv  Detail & Related papers  (2025-03-12T16:03:03Z)
• 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)
• Chatting Up Attachment: Using LLMs to Predict Adult Bonds [0.0]
  We use GPT-4 and Claude 3 Opus to create agents that simulate adults with varying profiles, childhood memories, and attachment styles. We evaluate our models using a transcript dataset from 9 humans who underwent the same interview protocol, analyzed and labeled by mental health professionals. Our findings indicate that training the models using only synthetic data achieves performance comparable to training the models on human data.
  arXiv  Detail & Related papers  (2024-08-31T04:29:19Z)
• Discover, Explanation, Improvement: An Automatic Slice Detection Framework for Natural Language Processing [72.14557106085284]
  slice detection models (SDM) automatically identify underperforming groups of datapoints. This paper proposes a benchmark named "Discover, Explain, improve (DEIM)" for classification NLP tasks. Our evaluation shows that Edisa can accurately select error-prone datapoints with informative semantic features.
  arXiv  Detail & Related papers  (2022-11-08T19:00:00Z)
• Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation [41.9785159975426]
  State-of-the-art question answering models remain susceptible to a variety of adversarial attacks and are still far from obtaining human-level language understanding. One proposed way forward is dynamic adversarial data collection, in which a human annotator attempts to create examples for which a model-in-the-loop fails. In this work, we investigate several answer selection, question generation, and filtering methods that form a synthetic adversarial data generation pipeline. Models trained on both synthetic and human-generated data outperform models not trained on synthetic adversarial data, and obtain state-of-the-art results on the Adversarial
  arXiv  Detail & Related papers  (2021-04-18T02:00:06Z)

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.