Co-occurring keywords · papers mentioning both
reinforcement learning from human feedback
(2)
cultural heritage dataset
(1)
human agreement
(1)
speech-to-speech large language model
(1)
semantic acoustic evaluation
(1)
rationale-based supervision
(1)
principle-based alignment
(1)
instruction-following abilities
(1)
iterative mechanism
(1)
response improver
(1)
Papers
SageLM: A Multi-aspect and Explainable Large Language Model for Speech Judgement
AAAI 2026
Self-Boosting Large Language Models with Synthetic Preference Data
ICLR 2025
Increasing the Difficulty of Automatically Generated Questions via Reinforcement Learning with Synthetic Preference for Cost-Effective Cultural Heritage Dataset Generation
EMNLP 2024
SALMON: Self-Alignment with Instructable Reward Models
ICLR 2024