PrefBench benchmark shows zero-shot LLMs achieve deal rates above 0.99 but seller profits only slightly above random and far below a simple concession heuristic across 7,500 episodes.
Census Bureau
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GT 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
PrefBench: Evaluating Zero-Shot LLM Agents in Hidden-Preference Personalized Pricing Negotiations
PrefBench benchmark shows zero-shot LLMs achieve deal rates above 0.99 but seller profits only slightly above random and far below a simple concession heuristic across 7,500 episodes.