4 papers
Verifiable Social Reasoning for LLM Assistants
Amir Taubenfeld, Zorik Gekhman, Avigail Grinstein-Dabush +6
LLM assistants are widely used for daily social advice, yet evaluating their social reasoning in such consultation settings remains challenging since (i) it requires setups where t…
Overtrained, Not Misaligned
Joel Schreiber, Ariel Goldstein
Emergent misalignment (EM), where fine-tuning on a narrow task (like insecure code) causes broad misalignment across unrelated domains, was first demonstrated by Betley et al. (202…
Evaluating Alignment of Behavioral Dispositions in LLMs
Amir Taubenfeld, Zorik Gekhman, Lior Nezry +8
As people turn to LLMs for social advice, understanding their behavior in such contexts becomes essential. In this work, we focus on behavioral dispositions: the underlying tendenc…
Knowledge-Certainty Diversity Predicts Human-Human and Human-AI Open-Ended Discussion Synergy and Reveals Pure-AI Discussion Shortfalls
Tom Sheffer, Alon Miron, Asael Sklar +2
Conversations transform individual knowledge into collective insight, enabling collaborators to solve problems more accurately than they could alone. Whether dialogues among large…