NLIP Seminar Series

Introductory Presentations from new PhD students and Research Assistants in the NLIP Group: **New PhD Students** **Bianca-Mihaela Ganescu** (supervised by Prof Paula Buttery) **Filip Trhlik** (supervised by Prof Paula Buttery) **Yizhou Chi** (supervised by Prof Andreas Vlachos) **Przemyslaw Kubiak** (supervised by Dr...

Abstract not available

Despite massive investments in training large language models, tokenizers remain a critical but often neglected component with weaknesses that can cause wild hallucinations, bypass safety guardrails, and break downstream applications. This talk will cover: Our recent research in automatically detecting problematic 'glitch...

Abstract not available

Abstract not available

Abstract not available

Abstract not available

**Abstract** Apparently rational behaviors of autoregressive LLMs, such as in-context learning, have been attributed to implicit Bayesian inference: since training data is best explained as a mixture, the optimal next-token-predictor learns to implicitly infer latent concepts and completes prompts consistently with...

We introduce MultiBLiMP, a massively multilingual benchmark of linguistic minimal pairs, covering 101 languages, 6 linguistic phenomena and containing more than 120.000 minimal pairs. Our minimal pairs are created using a fully automated pipeline, leveraging the large-scale linguistic resources of Universal Dependencies...

Large language models (LLMs) are helping millions of users to learn and write about a diversity of issues. In doing so, LLMs may expose users to new ideas and perspectives, or reinforce existing knowledge and user opinions. This creates concerns about political bias in LLMs, and how these biases might influence LLM users...