Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interaction

• URL: http://arxiv.org/abs/2510.20411v1
• Date: Thu, 23 Oct 2025 10:29:23 GMT
• Title: Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interaction
• Authors: Suchir Salhan, Hongyi Gu, Donya Rooein, Diana Galvan-Sosa, Gabrielle Gaudeau, Andrew Caines, Zheng Yuan, Paula Buttery,
• Abstract summary: We introduce ContingentChat, a framework that benchmarks and improves multi-turn contingency in a BabyLM trained on 100M words.<n>Experiments with adaptive teacher decoding strategies show limited additional gains.
• Score: 8.154459044756367
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-turn dialogues between a child and a caregiver are characterized by a property called contingency - that is, prompt, direct, and meaningful exchanges between interlocutors. We introduce ContingentChat, a teacher-student framework that benchmarks and improves multi-turn contingency in a BabyLM trained on 100M words. Using a novel alignment dataset for post-training, BabyLM generates responses that are more grammatical and cohesive. Experiments with adaptive teacher decoding strategies show limited additional gains. ContingentChat demonstrates the benefits of targeted post-training for dialogue quality and indicates that contingency remains a challenging goal for BabyLMs.

Related papers

• PedagoSense: A Pedology Grounded LLM System for Pedagogical Strategy Detection and Contextual Response Generation in Learning Dialogues [0.0]
  We introduce PedagoSense, a pedology grounded system that combines a two stage strategy classifier with large language model generation.<n>The system first detects whether a pedagogical strategy is present using a binary classifier, then performs fine grained classification to identify the specific strategy.
  arXiv  Detail & Related papers  (2026-02-01T11:38:18Z)
• GameTalk: Training LLMs for Strategic Conversation [51.29670609281524]
  We introduce textbfGameTalk, a framework for training LLMs to make strategic decisions via multi-turn interactions.<n>Unlike prior work that focuses on single-turn objectives or static action prediction, we train LLMs to optimize a global objective across full conversations.<n>We evaluate this approach on a suite of increasingly complex games, designed to stress different aspects of reasoning, coordination, and opponent modeling.
  arXiv  Detail & Related papers  (2026-01-22T19:18:39Z)
• EduDial: Constructing a Large-scale Multi-turn Teacher-Student Dialogue Corpus [59.693733170193944]
  We present EduDial, a comprehensive multi-turn teacher-student dialogue dataset.<n>EduDial covers 345 core knowledge points and consists of 34,250 dialogue sessions generated through interactions between teacher and student agents.
  arXiv  Detail & Related papers  (2025-10-14T18:18:43Z)
• DialogXpert: Driving Intelligent and Emotion-Aware Conversations through Online Value-Based Reinforcement Learning with LLM Priors [19.83349341267686]
  Large-language-model (LLM) agents excel at reactive dialogue but struggle with proactive, goal-driven interactions.<n>We introduce DialogXpert, which proposes a small, high-quality set of candidate actions per turn.<n>By tracking the user's emotions, DialogXpert tailors each decision to advance the task while nurturing a genuine, empathetic connection.
  arXiv  Detail & Related papers  (2025-05-23T12:12:40Z)
• Contrastive Speaker-Aware Learning for Multi-party Dialogue Generation with LLMs [4.691083532629246]
  Multi-party dialogue generation presents significant challenges due to the complex interplay of multiple speakers and interwoven conversational threads.<n>This paper introduces Speaker-Attentive LLM (SA-LLM), a novel generative model that leverages pre-trained Large Language Models (LLMs) and a speaker-aware contrastive learning strategy to address these challenges.<n>SA-LLM incorporates a speaker-attributed input encoding and a contrastive learning objective to implicitly learn contextual coherence and speaker roles without explicit relation annotations.
  arXiv  Detail & Related papers  (2025-03-11T19:28:12Z)
• Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training [33.57497419019826]
  Action-Based Contrastive Self-Training enables data-efficient dialogue policy learning in multi-turn conversation modeling.<n>We demonstrate ACT's efficacy under in data-efficient tuning scenarios, even when there is no action label available.<n>We also propose evaluating LLMs' ability to function as conversational agents by examining whether they can implicitly recognize and reason about ambiguity in conversation.
  arXiv  Detail & Related papers  (2024-05-31T22:44:48Z)
• Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations [70.7884839812069]
  Large language models (LLMs) have emerged as powerful and general solutions to many natural language tasks. However, many of the most important applications of language generation are interactive, where an agent has to talk to a person to reach a desired outcome. In this work, we explore a new method for adapting LLMs with RL for such goal-directed dialogue.
  arXiv  Detail & Related papers  (2023-11-09T18:45:16Z)
• GRASP: Guiding model with RelAtional Semantics using Prompt [3.1275060062551208]
  We propose a Guiding model with RelAtional Semantics using Prompt (GRASP) We adopt a prompt-based fine-tuning approach and capture relational semantic clues of a given dialogue with an argument-aware prompt marker strategy. In the experiments, GRASP state-of-the-art performance in terms of both F1 and F1c scores on a DialogRE dataset.
  arXiv  Detail & Related papers  (2022-08-26T08:19:28Z)
• Dialogue-oriented Pre-training [70.03028879331339]
  We propose three strategies to simulate the conversation features on general plain text. Dialog-PrLM is fine-tuned on three public multi-turn dialogue datasets.
  arXiv  Detail & Related papers  (2021-06-01T12:02:46Z)
• Structural Pre-training for Dialogue Comprehension [51.215629336320305]
  We present SPIDER, Structural Pre-traIned DialoguE Reader, to capture dialogue exclusive features. To simulate the dialogue-like features, we propose two training objectives in addition to the original LM objectives. Experimental results on widely used dialogue benchmarks verify the effectiveness of the newly introduced self-supervised tasks.
  arXiv  Detail & Related papers  (2021-05-23T15:16:54Z)
• Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues [88.73739515457116]
  We introduce four self-supervised tasks including next session prediction, utterance restoration, incoherence detection and consistency discrimination. We jointly train the PLM-based response selection model with these auxiliary tasks in a multi-task manner. Experiment results indicate that the proposed auxiliary self-supervised tasks bring significant improvement for multi-turn response selection.
  arXiv  Detail & Related papers  (2020-09-14T08:44:46Z)
• Masking Orchestration: Multi-task Pretraining for Multi-role Dialogue Representation Learning [50.5572111079898]
  Multi-role dialogue understanding comprises a wide range of diverse tasks such as question answering, act classification, dialogue summarization etc. While dialogue corpora are abundantly available, labeled data, for specific learning tasks, can be highly scarce and expensive. In this work, we investigate dialogue context representation learning with various types unsupervised pretraining tasks.
  arXiv  Detail & Related papers  (2020-02-27T04:36:52Z)

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.