People prefer text containing the words that an instruction-tuned model uses far more than its base version, linking human feedback training to LLM word overuse.
https://x.com/JeremyNguyenPhD/status/ 1774021645709295840, last accessed 2024/08/12
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Word Overuse and Alignment in Large Language Models: The Influence of Learning from Human Feedback
People prefer text containing the words that an instruction-tuned model uses far more than its base version, linking human feedback training to LLM word overuse.