Reinforcement learning on a reward model trained from human summary comparisons produces summaries humans prefer over supervised fine-tuning or human references on TL;DR and transfers to CNN/DM.
Acute-eval: Improved dialogue evaluation with optimized questions and multi-turn comparisons
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CL 3roles
method 1polarities
use method 1representative citing papers
RAG models set new state-of-the-art results on open-domain QA by retrieving Wikipedia passages and conditioning a generative model on them, while also producing more factual text than parametric baselines.
ToxPrune prunes toxic subwords from BPE tokenizers in LLMs to mitigate toxic dialogue responses and improve diversity on both toxic and non-toxic models.
citing papers explorer
-
Learning to summarize from human feedback
Reinforcement learning on a reward model trained from human summary comparisons produces summaries humans prefer over supervised fine-tuning or human references on TL;DR and transfers to CNN/DM.
-
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
RAG models set new state-of-the-art results on open-domain QA by retrieving Wikipedia passages and conditioning a generative model on them, while also producing more factual text than parametric baselines.
-
Toxic Subword Pruning for Dialogue Response Generation on Large Language Models
ToxPrune prunes toxic subwords from BPE tokenizers in LLMs to mitigate toxic dialogue responses and improve diversity on both toxic and non-toxic models.