Search Results for author:
Found 3 papers, 2 papers with code
Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive
In this work, first we show theoretically that the standard DPO loss can lead to a \textit{reduction} of the model's likelihood of the preferred examples, as long as the relative probability between the preferred and dispreferred classes increases.
Giraffe: Adventures in Expanding Context Lengths in LLMs
To use these models on sequences longer than the train-time context length, one might employ techniques from the growing family of context length extrapolation methods -- most of which focus on modifying the system of positional encodings used in the attention mechanism to indicate where tokens or activations are located in the input sequence.
Sentiment Analysis: Predicting Yelp Scores
In this work, we predict the sentiment of restaurant reviews based on a subset of the Yelp Open Dataset.
