Preprint2024
LearnLM
Unknown
LearnLM enhances Gemini for pedagogical instruction by co-training SFT and RLHF, outperforming leading LLMs in tutoring scenarios.
0Dec 1, 2024Fine TuningReinforcement Learning
arXiv
AI Research
AI & ML Research Papers
A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
All Papers
7 papersPreprint2024
CriticGPT
Unknown
CriticGPT uses RLHF to train a GPT-4-based model that critiques ChatGPT code outputs, helping humans catch bugs more accurately.
0Jun 1, 2024
Preprint2024
Constrained Generative Policy Optimization (Mixture of Judges)
Unknown
Constrained Generative Policy Optimization with Mixture of Judges uses rule-based and LLM judges to constrain RLHF, improving multi-objective optimization and Pareto frontier.
0Sep 1, 2024
Preprint2024
RLHF Workflow
Unknown
Presents a detailed recipe for online iterative RLHF using fully open-source datasets, achieving state-of-the-art performance on conversation and instruction-following benchmarks.
0May 1, 2024Benchmarks
arXiv
Preprint2023
Reward rAnked FineTuning (RAFT)
Unknown
RAFT iteratively fine-tunes generative models on top-ranked samples to align them with a reward function, improving stability and efficiency over RLHF.
0Apr 1, 2023Fine TuningDiffusion Models
Preprint2024
RewardBench
Unknown
A benchmark dataset and code-base designed to evaluate reward models used in RLHF.
0Mar 1, 2024Benchmarks
Preprint2023
LIMA
Unknown
LLaMa fine-tuned on only 1,000 curated examples matches or exceeds state-of-the-art RLHF models.
0May 1, 2023Fine TuningReinforcement Learning