6 papers
Jailbreaking Large Language Models in Infinitely Many Ways
Oliver Goldstein, Emanuele La Malfa, Felix Drinkall +2
We discuss the ``Infinitely Many Paraphrases'' attacks (IMP), a category of jailbreaks that leverages the increasing capabilities of a model to handle paraphrases and encoded commu…
Stories that (are) Move(d by) Markets: A Causal Exploration of Market Shocks and Semantic Shifts across Different Partisan Groups
Felix Drinkall, Stefan Zohren, Michael McMahon +1
Macroeconomic fluctuations and the narratives that shape them form a mutually reinforcing cycle: public discourse can spur behavioural changes leading to economic shifts, which the…
When Dimensionality Hurts: The Role of LLM Embedding Compression for Noisy Regression Tasks
Felix Drinkall, Janet B. Pierrehumbert, Stefan Zohren
Large language models (LLMs) have shown remarkable success in language modelling due to scaling laws found in model size and the hidden dimension of the model's text representation…
Forecasting Credit Ratings: A Case Study where Traditional Methods Outperform Generative LLMs
Felix Drinkall, Janet B. Pierrehumbert, Stefan Zohren
Large Language Models (LLMs) have been shown to perform well for many downstream tasks. Transfer learning can enable LLMs to acquire skills that were not targeted during pre-traini…
Language Models Learn Metadata: Political Stance Detection Case Study
Stanley Cao, Felix Drinkall
Stance detection is a crucial NLP task with numerous applications in social science, from analyzing online discussions to assessing political campaigns. This paper investigates the…
Time Machine GPT
Felix Drinkall, Eghbal Rahimikia, Janet B. Pierrehumbert +1
Large language models (LLMs) are often trained on extensive, temporally indiscriminate text corpora, reflecting the lack of datasets with temporal metadata. This approach is not al…