mlsanityData to 14 Oct 2026

Listen, Correct, and Feed Back: Spoken Pedagogical Feedback Generation

arXiv 2604.14177 ↗First posted 28 Mar 2026cs.CL cs.AIcited by 0

On the map: LLM alignment / RLHF / preference optimisation → Process reward models for reasoning

Abstract (arXiv)

Grammatical error correction (GEC) and explanation (GEE) have made rapid progress, but real teaching scenarios also require learner-friendly pedagogical feedback that is actionable, level-appropriate, and encouraging. We introduce SPFG (Spoken Pedagogical Feedback Generation), a dataset built based on the Speak & Improve Challenge 2025 corpus, pairing fluency-oriented transcriptions with GEC targets and human-verified teacher-style feedback, including preferred/rejected feedback pairs for preference learning. We study a transcript-based Spoken Grammatical Error Correction (SGEC) setting and evaluate three instruction-tuned LLMs (Qwen2.5, Llama-3.1, and GLM-4), comparing supervised fine-tuning (SFT) with preference-based alignment (using DPO and KTO) for jointly generating corrections and feedback. Results show that SFT provides the most consistent improvements, while DPO/KTO yield smaller or mixed gains, and that correction quality and feedback quality are weakly coupled. Our implementation is available at https://github.com/Skywalker-Harrison/spfg.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Process reward models for reasoning, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 8 of its 28 references that are in the map. First posted on arXiv 28 Mar 2026.

Builds on

8 of 28 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Improving the Validity of Automatically Generated Feedback via Reinforcement Learning2 Mar

Other references · 7

  1. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  2. 2023CLASS: A Design Framework for building Intelligent Tutoring Systems based on Learning Science principlescited by 48
  3. 2024AutoTutor meets Large Language Models: A Language Model Tutor with Rich Pedagogy and Guardrailscited by 31
  4. 2018Inherent Biases in Reference based Evaluation for Grammatical Error Correction and Text Simplificationcited by 15
  5. 2024Speak & Improve Challenge 2025: Tasks and Baseline Systemscited by 13
  6. 2025Natural Language-based Assessment of L2 Oral Proficiency using LLMscited by 6
  7. 2025Leveraging What's Overfixed: Post-Correction via LLM Grammatical Error Overcorrectioncited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond Reference-Based Evaluation: Reward Models for Meta-Evaluation of Grammatical Error Correction
  2. 2026Towards Pedagogically Aligned LLM Tutors for Math Mistake Remediation
  3. 2024ChatLang-8: An LLM-Based Synthetic Data Generation Framework for Grammatical Error Correction
  4. 2025Harnessing Rule-Based Reinforcement Learning for Enhanced Grammatical Error Correction
  5. 2024Teaching Language Models to Self-Improve by Learning from Language Feedback
  6. 2023Let Me Teach You: Pedagogical Foundations of Feedback for Language Models
  7. 2026LLM Reasoning Predicts When Models Are Right: Evidence from Coding Classroom Discourse
  8. 2026PIVOT: Preference-based Intervention Vectors for Pedagogical Tutor Steering