Paper Detail

Read the Room Before Your Model Generates

Muyao Kong, Zhihao Lin

arxiv Score 5.8

Published 2026-10-13 · First seen 2026-10-14

General AI

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 \textbf{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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{kong2026read,
  title = {Read the Room Before Your Model Generates},
  author = {Muyao Kong and Zhihao Lin},
  year = {2026},
  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 \textbackslash{}textbf\{Scenario-Actor\}, which adapts decoding to the inferred},
  url = {https://arxiv.org/abs/2610.18820},
  keywords = {cs.AI, cs.CL},
  eprint = {2610.18820},
  archiveprefix = {arXiv},
}

Metadata

{}