conftrace_

behavioral evaluation

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) internal evaluation (1) value-action gap (1) behavior evaluation (1) value inference (1) ethical ai (1) linguistic competence (1) weight merging (1) instruction fine-tuning (1) value alignment (1)

Papers

A Pipeline to Assess Merging Methods via Behavior and Internals EMNLP 2025 Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values? EMNLP 2025