Hybrid-DPO, which trains LLMs on preference pairs scored by a DeBERTa NLI entailment signal plus a verifier fluency score, improves NLI entailment over SFT in 11 of 15 model-domain cells and documents a persistent verbosity bias in GPT-4o-mini judging.
In Advances in Neural Information Processing Systems (NeurIPS)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization
Hybrid-DPO, which trains LLMs on preference pairs scored by a DeBERTa NLI entailment signal plus a verifier fluency score, improves NLI entailment over SFT in 11 of 15 model-domain cells and documents a persistent verbosity bias in GPT-4o-mini judging.