conftrace_

value probing

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) sequence perplexity (1) demographic prompting (1) internal causal analysis (1) out-of-distribution behaviors (1) counterfactual simulation (1) prompt perturbation (1) alignment evaluation (1) value alignment (1) causal mechanism (1)

Papers

Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors ICML 2025 Revisiting LLM Value Probing Strategies: Are They Robust and Expressive? EMNLP 2025