GLARE: Generative Learning via Adversarial Reward Estimation For Social Dynamics Forecasting

2026-09-10

AI Summary

研究解决了会议动态预测问题，通过引入GLARE方法（一种基于对抗性模仿学习的条件语言生成技术）来生成合理的多轮对话延续，并在新建立的MDFB基准上评估模型性能。

Abstract

Meeting continuation requires tracking the agenda, speaker roles, participant intentions, and disagreement across long multi-party discussions. We introduce the Meeting Dynamic Forecasting Benchmark (MDFB), constructed from 2,207 real-world meetings and 24,794 future-facing queries. Given a transcript prefix and an active question, a model generates a plausible multi-turn continuation in one call. We evaluate utility---progress toward the question---and human-likeness---plausible conversational flow and role consistency---without requiring exact reproduction of the observed future. We further present GLARE, an adaptation of adversarial imitation learning to conditional language generation. A discriminator ranks the observed continuation above samples from the current actor, and its score supplies a KL-regularized policy reward; retraining on current-policy negatives allows the reward landscape to evolve with the actor. GLARE attains average human-evaluated win rates of 0.66 on utility and 0.70 on human-likeness, outperforming SFT and SPIN while remaining below the observed human continuation. We also demonstrate MDFB as a social reasoning arena for comparing general-purpose models, including closed-source systems, through reference-assisted judgments. Together, these studies illustrate the benchmark's use for both task-specific learning and output-based evaluation of meeting behavior.

Problem

• Meeting Dynamics
• Forecasting
• Social Dynamics
• Conversation Modeling

Innovation

• Adversarial Imitation Learning
• Conditional Language Generation
• Meeting Dynamic Forecasting Benchmark
• Social Dynamics Forecasting