{"slug": "beyond-direct-answering-aligning-educational-llms-as-socratic-guides-via", "title": "Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning", "summary": "A new two-phase pipeline called HeuristicEdu aligns Qwen2.5-7B toward Socratic tutoring, improving Scaffolding Effectiveness from 30.0% to 63.3% and reducing keyword leakage from 30.0% to 13.3% on held-out questions, according to a preprint on arXiv. The method uses supervised warm-up and Group Relative Policy Optimization with a heuristic reward over cognitive depth, curiosity engagement, and directness, trained on 797 multi-turn Chinese children's science dialogues. The best variant omits the directness penalty, suggesting explicit anti-leakage terms can conflict with gradient-based behavioral alignment.", "body_md": "arXiv:2607.22996v1 Announce Type: new\nAbstract: Large language models (LLMs) deployed in educational settings often behave as direct answerers: they disclose target concepts in the opening turn instead of guiding students through progressive inquiry, as Socratic pedagogy prescribes. We present HeuristicEdu, a two-phase pipeline that aligns Qwen2.5-7B toward Socratic tutoring via supervised warm-up and Group Relative Policy Optimization (GRPO). Training uses SocraticEdu, 797 multi-turn Chinese children's science dialogues reconstructed from a live platform, with a heuristic reward over cognitive depth (R_cog), curiosity engagement (R_eng), and directness (R_dir), together with a K_query correction for student-introduced terms. We introduce Scaffolding Effectiveness (SE) and Conversation Depth (CD) to evaluate outcomes beyond surface fluency. On 30 held-out questions, the best GRPO variant improves SE from 30.0% to 63.3% and lowers keyword leakage from 30.0% to 13.3%. Notably, this best variant omits the directness penalty during optimization, suggesting that explicit anti-leakage terms can conflict with gradient-based behavioral alignment. An unaligned Qwen-72B baseline reaches 0% SE and 96.7% leakage, showing that scale alone does not induce Socratic behavior.", "url": "https://wpnews.pro/news/beyond-direct-answering-aligning-educational-llms-as-socratic-guides-via", "canonical_source": "https://arxiv.org/abs/2607.22996", "published_at": "2026-07-28 04:00:00+00:00", "updated_at": "2026-07-28 04:25:48.376644+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research", "ai-ethics"], "entities": ["HeuristicEdu", "Qwen2.5-7B", "Group Relative Policy Optimization", "GRPO", "SocraticEdu", "Qwen-72B", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/beyond-direct-answering-aligning-educational-llms-as-socratic-guides-via", "markdown": "https://wpnews.pro/news/beyond-direct-answering-aligning-educational-llms-as-socratic-guides-via.md", "text": "https://wpnews.pro/news/beyond-direct-answering-aligning-educational-llms-as-socratic-guides-via.txt", "jsonld": "https://wpnews.pro/news/beyond-direct-answering-aligning-educational-llms-as-socratic-guides-via.jsonld"}}