Search Results for author:
Found 4 papers, 4 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.
Data Contamination Through the Lens of Time
Recent claims about the impressive abilities of large language models (LLMs) are often supported by evaluating publicly available benchmarks.
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.
Unsupervised Learning under Latent Label Shift
Thus motivated, we introduce a practical algorithm that leverages domain-discriminative models as follows: (i) push examples through domain discriminator $p(d|\mathbf{x})$; (ii) discretize the data by clustering examples in $p(d|\mathbf{x})$ space; (iii) perform non-negative matrix factorization on the discrete data; (iv) combine the recovered $p(y|d)$ with the discriminator outputs $p(d|\mathbf{x})$ to compute $p_d(y|x) \; \forall d$.
