Inseq: An interpretability toolkit for sequence generation models
Past work in natural language processing interpretability focused mainly on popular
classification tasks while largely overlooking generation settings, partly due to a lack of …
classification tasks while largely overlooking generation settings, partly due to a lack of …
How do languages influence each other? Studying cross-lingual data sharing during LLM fine-tuning
Multilingual large language models (MLLMs) are jointly trained on data from many different
languages such that representation of individual languages can benefit from other …
languages such that representation of individual languages can benefit from other …
Make every example count: On the stability and utility of self-influence for learning from noisy NLP datasets
Increasingly larger datasets have become a standard ingredient to advancing the state-of-
the-art in NLP. However, data quality might have already become the bottleneck to unlock …
the-art in NLP. However, data quality might have already become the bottleneck to unlock …
Examining modularity in multilingual lms via language-specialized subnetworks
Recent work has proposed explicitly inducing language-wise modularity in multilingual LMs
via sparse fine-tuning (SFT) on per-language subnetworks as a means of better guiding …
via sparse fine-tuning (SFT) on per-language subnetworks as a means of better guiding …
The Echoes of Multilinguality: Tracing Cultural Value Shifts during LM Fine-tuning
Texts written in different languages reflect different culturally-dependent beliefs of their
writers. Thus, we expect multilingual LMs (MLMs), that are jointly trained on a concatenation …
writers. Thus, we expect multilingual LMs (MLMs), that are jointly trained on a concatenation …
The Echoes of Multilinguality: Tracing Cultural Value Shifts during Language Model Fine-tuning
Texts written in different languages reflect different culturally-dependent beliefs of their
writers. Thus, we expect multilingual LMs (MLMs), that are jointly trained on a concatenation …
writers. Thus, we expect multilingual LMs (MLMs), that are jointly trained on a concatenation …