Behavioral profiles from prediction-market traders are partially stable and identifiable but cannot be transmitted via prompts to reduce LLM forecast correlations or improve Brier scores.
Eliciting the priors of large language models using iterated in-context learning.arXiv preprint arXiv:2406.01860
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
PII can be reconstructed from SFT models via prefix attacks, with the new COVA algorithm improving success rates and leakage varying by attacker knowledge and PII type.
LMs systematically inflate expressed certainty during rewriting, affecting up to 75% of outputs with a 1.5-2x bias toward increasing rather than decreasing certainty, and the effect compounds over iterations.
LILO integrates LLMs to translate natural language feedback into preference signals for Gaussian process-based Bayesian optimization, outperforming standard preference BO and LLM-only methods on benchmarks.
citing papers explorer
-
Nous: An Attempt to Extract and Inject the Cognition Behind Prediction-Market Behavior
Behavioral profiles from prediction-market traders are partially stable and identifiable but cannot be transmitted via prompts to reduce LLM forecast correlations or improve Brier scores.
-
Reconstruction of Personally Identifiable Information from Supervised Finetuned Models
PII can be reconstructed from SFT models via prefix attacks, with the new COVA algorithm improving success rates and leakage varying by attacker knowledge and PII type.
-
From `May' to `Is': Certainty Distortion in Language Model Rewriting
LMs systematically inflate expressed certainty during rewriting, affecting up to 75% of outputs with a 1.5-2x bias toward increasing rather than decreasing certainty, and the effect compounds over iterations.
-
LILO: Bayesian Optimization with Natural Language Feedback
LILO integrates LLMs to translate natural language feedback into preference signals for Gaussian process-based Bayesian optimization, outperforming standard preference BO and LLM-only methods on benchmarks.