2 papers
cs.CL2026
Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment
Mengxuan Hu, Vivek V. Datla, Anoop Kumar +4
Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have impro…
cs.CL2025
Confidence-Based Response Abstinence: Improving LLM Trustworthiness via Activation-Based Uncertainty Estimation
Zhiqi Huang, Vivek Datla, Chenyang Zhu +4
We propose a method for confidence estimation in retrieval-augmented generation (RAG) systems that aligns closely with the correctness of large language model (LLM) outputs. Confid…