Teaching a Large Language Model Tutor to Withhold the Answer: A Supervisor Architecture and an Evidence-Driven Method for Tuning Socratic Behavior

• URL: http://arxiv.org/abs/2608.12292v1
• Date: Wed, 12 Aug 2026 17:35:58 GMT
• Title: Teaching a Large Language Model Tutor to Withhold the Answer: A Supervisor Architecture and an Evidence-Driven Method for Tuning Socratic Behavior
• Abstract summary: An effective large language model (LLM) tutor must often decline to give an answer it could easily produce.<n>We report a deployed tutoring system that enforces answer-withholding as a per-turn, machine-checkable contract.<n>We tune the behavior with an automated evaluation that uses no human subjects.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: An effective large language model (LLM) tutor must often decline to give an answer it could easily produce. In a randomized study, students who used an unguarded chatbot scored higher while practicing but lower on a later test taken without it, whereas a Socratically guarded version of the same model kept the practice gain and removed the later loss [4]. Reliable answer-withholding is therefore central to a tutor's value, yet a capable model pressed by a frustrated student does not withhold reliably on a prompt alone. We report a deployed tutoring system that enforces answer-withholding as a per-turn, machine-checkable contract, and a method for tuning that withholding against evidence. A non-LLM policy core, reading only trusted learner state, sets a per-turn ceiling on an eight-rung help ladder; a deterministic detector strips solution code; and a separate LLM judge checks each risky reply against the contract. We tune the behavior with an automated evaluation that uses no human subjects: scripted student personas are driven through the live pipeline and re-scored by a stronger model, and we record each rejection's stated reason so failures are fixed by cause. Doing so revealed an interpretable "over-help ladder," from blatant solution leaks, to naming the exact bug, to over-citing general facts, with each fix exposing the next. The tutor reached full compliance on all four acceptance criteria. We offer the measure, diagnose, and fix loop as a reusable recipe for any LLM agent that must refuse a capability it has.

Related papers

• LLM-as-a-Judge Is Not an Oracle: Why Self-Improving Agents Need Deterministic Guardrails [0.0]
  Self-improving agent pipelines have a problem at their center.<n>An evaluation signal failed in eleven classes: judge bias, harness and metric failures, ground-truth errors, and reward hacking.<n>We describe PROCTOR, a Teacher-Student loop in which a stateful orchestrator holds all tool access, stateless subagents diagnose failures and draft mutations they cannot apply.
  arXiv  Detail & Related papers  (2026-09-02T07:54:23Z)
• H$^2$SD: Hybrid Hindsight Self-Distillation [61.71131241473028]
  Reinforcement learning with verifiable rewards (RLVR) provides reliable outcome supervision for language model reasoning.<n>Existing self-distillation methods add a privileged teacher but typically assign it a fixed role.<n>We introduce Hybrid Hindsight Self-Distillation ($mathrmH2mathrmSD$), which jointly adapts teacher context and update strategy to trajectory correctness.
  arXiv  Detail & Related papers  (2026-07-21T10:47:27Z)
• Consensus as Privileged Context for Label-Free Self-Distillation [12.523025093871304]
  CANON (Consensus-ANchored self-distillatiON) is a label-free training method that turns consensus into dense, token-level supervision.<n>CanON improves pass@1 by up to 12 points, outperforming label-free reinforcement learning by 6 points at a seventh of its compute.
  arXiv  Detail & Related papers  (2026-07-15T09:39:32Z)
• The Correct Answer Trap: Pedagogically-Grounded Detection and Feedback for Hidden Misconceptions [2.6352293843915606]
  We investigate automatic detection of hidden misconceptions using 20,964 real student responses from the Eedi mathematics platform.<n>We present a graduated assessment that separates answer correctness from method validity, and propose a detect-verify-escalate pipeline.<n>Two deployment modes adapt the pipeline: a teacher dashboard where the system filters a review queue, and an autonomous tutor where flags trigger low-cost formative follow-up.
  arXiv  Detail & Related papers  (2026-06-22T11:51:17Z)
• Rethinking Reward Supervision: Rubric-Conditioned Self-Distillation [60.55792673956761]
  We propose textbfRubric-Conditioned Self-Distillation, a framework that incorporates rubrics as structured, fine-grained feedback for on-policy self-distillation.<n>We evaluate on a diverse suite of science reasoning benchmarks and results show that rubric-conditioned self-distillation effectively converts rubric-level criteria into token-level guidance.
  arXiv  Detail & Related papers  (2026-06-17T17:54:04Z)
• Catching The Correct Answer Trap: Characterising AI Tutor Blind Spots When Analysing Student Reasoning [2.6352293843915606]
  We study a failure mode we call the correct answer trap (CAT): models under-detect misconceptions when students reach a correct answer via flawed reasoning.<n>Analysing real student responses from the Eedi mathematics platform, we show that 71% of these failures concentrate in just two question types.
  arXiv  Detail & Related papers  (2026-04-20T10:53:48Z)
• CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution [52.691495954442985]
  CoVerRL is a framework where a single model alternates between generator and verifier roles, with each capability bootstrapping the other.<n> Experiments across Qwen and Llama model families demonstrate that CoVerRL outperforms label-free baselines by 4.7-5.9% on mathematical reasoning benchmarks.<n>Self-verification accuracy improves from around 55% to over 85%, confirming that both capabilities genuinely co-evolve.
  arXiv  Detail & Related papers  (2026-03-18T14:38:55Z)
• Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation [12.503662455234954]
  We show that modern language models produce confident hallucinations even when wrong answers carry catastrophic consequences.<n>We propose Reinforced Hesitation (RH): a modification to Reinforcement Learning from Verifiable Rewards (RLVR) to use ternary rewards instead of binary.
  arXiv  Detail & Related papers  (2025-11-14T17:20:45Z)
• Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning [48.14470449860784]
  Test-time reinforcement learning (TTRL) offers a label-free paradigm for adapting models using only synthetic signals at inference.<n>We introduce Self-Harmony, a framework built on a simple intuition.
  arXiv  Detail & Related papers  (2025-11-03T03:34:34Z)
• Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors [78.53699244846285]
  Large language models (LLMs) present an opportunity to scale high-quality personalized education to all. LLMs struggle to precisely detect student's errors and tailor their feedback to these errors. Inspired by real-world teaching practice where teachers identify student errors and customize their response based on them, we focus on verifying student solutions.
  arXiv  Detail & Related papers  (2024-07-12T10:11:40Z)
• R-Tuning: Instructing Large Language Models to Say `I Don't Know' [66.11375475253007]
  Large language models (LLMs) have revolutionized numerous domains with their impressive performance but still face their challenges. Previous instruction tuning methods force the model to complete a sentence no matter whether the model knows the knowledge or not. We present a new approach called Refusal-Aware Instruction Tuning (R-Tuning) Experimental results demonstrate R-Tuning effectively improves a model's ability to answer known questions and refrain from answering unknown questions.
  arXiv  Detail & Related papers  (2023-11-16T08:45:44Z)

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.