conftrace_

preference representation

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

adversarial counterfactual (1) behavioral feature (1) review-based recommendation (1) counterfactual distillation (1) probing method (1) multi-dimensional evaluation (1) reward model (1) language model alignment (1) knowledge distillation (1)

Papers

Bidirectional Counterfactual Distillation for Review-Based Recommendation AAAI 2026 Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models AAAI 2026