Read the Room Before Your Model Generates

arXiv:2610.18820v2 Announce Type: new Abstract: Large language models (LLMs) generally rely on sampling temperature to regulate the amount of randomness in their outputs. Mainstream methods for selecting temperature typically involve fixed, heuristic global settings and context or token-level calibration, rather than a geometrically interpretable representation of the communicative scenario. In this work, we introduce a simple and interpretable temperature selection framework, the Scenario-Actor, which adapts decoding to the inferred situational characteristics. Scenario-Actor extracts scenario-relevant structures from Transformer hidden states and determines the temperature from scenario embedding, a structured geometric representation of the communicative setting. Empirical results show that on Llama-3.1-8B-Instruct, Scenario-Actor achieves strong goal-completion performance in interactive social scenarios, significant gains on open-ended instruction following, and competitive performance on multi-turn conversation compared to multiple baselines.

Related

• Min-k Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics
• Architectural Sampling: Test-Time Scaling via Computational Diversity in Frozen Vision-Language Models
• Seed Hijacking of LLM Sampling and Quantum Random Number Defense

Source: arXiv cs.AI | 2026-10-15