conftrace_

divergence

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

overgeneralization (1) synthetic preference dataset (1) instability (1) annotators (1) llm-as-judges (1) disagreement (1) evaluation (1) verbal feedback (1) gradient regularization (1) large language model (1)

Papers

Diverging Preferences: When do Annotators Disagree and do Models Know? ICML 2025 RLVF: Learning from Verbal Feedback without Overgeneralization ICML 2024 When Will Gradient Regularization Be Harmful? ICML 2024