Papers by Kuan-Ru Liou
Conformal Feedback Alignment: Quantifying Answer-Level Reliability for Robust LLM Alignment (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing uncertainty-aware approaches weight preferences, but ignore reliability of the answers being compared. |
| Approach: | They propose a framework that grounds preference weighting in Conformal Predictions to address this problem. |
| Outcome: | The proposed framework improves alignment robustness and data efficiency across different datasets. |