Search Results
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
We apply preference modeling and reinforcement learning from human feedback (RLHF) to finetune language models to act as helpful and harmless assistants.
Safe RLHF: Safe Reinforcement Learning from Human Feedback
However, the inherent tension between the objectives of helpfulness and harmlessness presents a significant challenge during LLM training.
Reinforcement Learning from Human Feedback
Reinforcement learning from human feedback (RLHF) has become an important technical and storytelling tool to deploy the latest machine learning systems.
Online Iterative Reinforcement Learning from Human Feedback with General Preference Model
We investigate Reinforcement Learning from Human Feedback (RLHF) in the context of a general preference oracle.
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
We provide our own analysis of the data and find a variety of harmful outputs, which range from offensive language to more subtly harmful non-violent unethical outputs.
Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback
Okapi introduces instruction and response-ranked data in 26 diverse languages to facilitate the experiments and development of future multilingual LLM research.
OPT: Open Pre-trained Transformer Language Models
Large language models, which are often trained for hundreds of thousands of compute days, have shown remarkable capabilities for zero- and few-shot learning.
Ranked #2 on
Stereotypical Bias Analysis
on CrowS-Pairs
MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions
However, token-level RLHF suffers from the credit assignment problem over long sequences, where delayed rewards make it challenging for the model to discern which actions contributed to successful outcomes.
TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback
These human preference data, however, are labeled at the sequence level, creating a mismatch between sequence-level preference labels and tokens, which are autoregressively generated from the language model.
Multi-turn Reinforcement Learning from Preference Human Feedback
Reinforcement Learning from Human Feedback (RLHF) has become the standard approach for aligning Large Language Models (LLMs) with human preferences, allowing LLMs to demonstrate remarkable abilities in various tasks.
