Announcement_5
- Publications: Debias-SparseGPT: Bias-Aware Pruning for Large Language Models (EMNLP 2026 Main Conference), Fair-GPTQ: Bias-Aware Quantization for Large Language Models (TACL, to appear), Are You Sure You’re Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity (UncertaiNLP @ EMNLP 2026, Cohere Labs Community)
- UncertaiNLP @ EMNLP 2026: Very happy to present our Cohere Labs Community project, On the Impact of Instruction Tuning on Confidence and Lexical Diversity, at the Uncertainty-Aware NLP Workshop at EMNLP. [PDF]
- PhD defense: I defended my PhD thesis, “Towards an Unbiased Compression of Large Language Models”, on March 5, 2026 at the Université de Lyon, France.
- PhD thesis: Download the thesis (PDF). Cite as: Irina Proskurina. Towards an Unbiased Compression of Large Language Models. PhD thesis, Université de Lyon, 2026. See Publications for the tex reference.