mlsanityData to 7 Oct 2026

Phase Transitions in Affective Meaning Divergence: The Hidden Drift Before the Break

arXiv 2605.09043 ↗First posted 9 May 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

One partner says "Fine" meaning "resolution"; the other hears "surrender." The word is shared; the affective uptake is not. We formalize this as affective meaning divergence (AMD), the total-variation distance between interlocutors' anchor-conditioned affect distributions. Building on speech-act theory, common-ground accumulation, and entropy-regularized game theory, we derive a logit best-response map whose dynamics undergo a saddle-node bifurcation: when βα > 4, a monotone increase in AMD-driven load produces an abrupt, hysteretic collapse of repair coordination. On Conversations Gone Awry (CGA-Wiki; N = 652), derailing conversations exhibit critical-slowing-down (CSD) signatures across multiple levels: lexical divergence variance (p < 0.001, d = 0.36), AMD variance (p = 0.001, d = 0.26), and dialog-act repair variance (p = 0.016, d = 0.20), all significant after correction and stronger than toxicity and sentiment baselines. AMD provides a distinct temporal signature, with retrospectively measured variance peaking at the bifurcation point while toxicity variance peaks earlier, and is the only indicator grounded in the theoretical framework. Boundary-condition analysis on CGA-CMV (N = 1,169) yields mixed but directionally consistent evidence.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 39 references that are in the map. First posted on arXiv 9 May 2026.

Builds on

11 of 39 references.

References · 11

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  2. 2020GoEmotions: A Dataset of Fine-Grained Emotionscited by 479
  3. 2018DialogueRNN: An Attentive RNN for Emotion Detection in Conversationscited by 216
  4. 2016Multi-Agent Cooperation and the Emergence of (Natural) Languagecited by 181
  5. 2021Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyondcited by 177
  6. 2020COSMIC: COmmonSense knowledge for eMotion Identification in Conversationscited by 135
  7. 2018Conversations Gone Awry: Detecting Early Signs of Conversational Failurecited by 73
  8. 2019Trouble on the Horizon: Forecasting the Derailment of Online Conversations as they Developcited by 41
  9. 2025Language Models Grow Less Humanlike beyond Phase Transitioncited by 10
  10. 2013Affect Control Processes: Intelligent Affective Interaction using a Partially Observable Markov Decision Processcited by 5
  11. 2021A bifurcation threshold for contact-induced language changecited by 1

Built on by

Not cited yet.