In alignment-inducing multi-agent settings, LLM agents show decision divergence between public and off-the-record channels rising from a 3% baseline to roughly 40%, consistent across stance, semantic, NLI, and survey measures.
Mind the Gap: How Elicitation Protocols Shape the Stated-Revealed Preference Gap in Language Models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Recent work identifies a stated-revealed (SvR) preference gap in language models (LMs): a mismatch between the values models endorse and the choices they make in context. Existing evaluations rely heavily on binary forced-choice prompting, which entangles genuine preferences with artifacts of the elicitation protocol. We systematically study how elicitation protocols affect SvR correlation across 24 LMs. Allowing neutrality and abstention during stated preference elicitation allows us to exclude weak signals, substantially improving Spearman's rank correlation ($\rho$) between volunteered stated preferences and forced-choice revealed preferences. However, further allowing abstention in revealed preferences drives $\rho$ to near-zero or negative values due to high neutrality rates. Finally, we find that system prompt steering using stated preferences during revealed preference elicitation does not reliably improve SvR correlation on AIRiskDilemmas. Together, our results show that SvR correlation is highly protocol-dependent and that preference elicitation requires methods that account for indeterminate preferences.
years
2026 2verdicts
UNVERDICTED 2representative citing papers
SMADE-IE introduces an adaptive mode selector and Toulmin-style evidence-driven debate to outperform prior zero-shot IE methods on NER, RE, and JERE tasks while reducing token use.
citing papers explorer
-
What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates
In alignment-inducing multi-agent settings, LLM agents show decision divergence between public and off-the-record channels rising from a 3% baseline to roughly 40%, consistent across stance, semantic, NLI, and survey measures.
-
SMADE-IE: Sparse Multi-Agent Framework with Evidence-Driven Debate for Zero-Shot Information Extraction
SMADE-IE introduces an adaptive mode selector and Toulmin-style evidence-driven debate to outperform prior zero-shot IE methods on NER, RE, and JERE tasks while reducing token use.