Similar Items: DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization
- Beyond Negative Rollouts: Positive-Only Policy Optimization with Implicit Negative Gradients
- Misaligned by Reward: Socially Undesirable Preferences in LLMs
- Towards Emotion Consistency Analysis of Large Language Models in Emotional Conversational Contexts
- SC-Taxo: Hierarchical Taxonomy Generation under Semantic Consistency Constraints using Large Language Models
- Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments
- Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe