Search Results for author:
Found 4 papers, 3 papers with code
D2PO: Discriminator-Guided DPO with Response Evaluation Models
Varied approaches for aligning language models have been proposed, including supervised fine-tuning, RLHF, and direct optimization methods such as DPO.
A Long Way to Go: Investigating Length Correlations in RLHF
Furthermore, we find that even running RLHF with a reward based solely on length can reproduce most of the downstream improvements over the initial policy model, showing that reward models in these settings have a long way to go.
EEL: Efficiently Encoding Lattices for Reranking
Standard decoding approaches for conditional text generation tasks typically search for an output hypothesis with high model probability, but this may not yield the best hypothesis according to human judgments of quality.
Assessing Out-of-Domain Language Model Performance from Few Examples
We address the task of predicting out-of-domain (OOD) performance in a few-shot fashion: given a few target-domain examples and a set of models with similar training performance, can we understand how these models will perform on OOD test data?
