4 papers
Turnslide: Scalable Multi-Turn Data Synthesis by Walking a Finite-State Machine
Aaron Fainman, Gabriela Kadlecová, Maciej Gryka +7
Small language models are inexpensive to serve and can run on private infrastructure, but base models are often not good enough at multi-turn tool calling, and fine-tuning them nee…
Hyperband-based Bayesian Optimization for Black-box Prompt Selection
Lennart Schneider, Martin Wistuba, Aaron Klein +3
Optimal prompt selection is crucial for maximizing large language model (LLM) performance on downstream tasks, especially in black-box settings where models are only accessible via…
Structural Pruning of Pre-trained Language Models via Neural Architecture Search
Aaron Klein, Jacek Golebiowski, Xingchen Ma +2
Pre-trained language models (PLM), for example BERT or RoBERTa, mark the state-of-the-art for natural language understanding task when fine-tuned on labeled data. However, their la…
Geographical Erasure in Language Generation
Pola Schwöbel, Jacek Golebiowski, Michele Donini +2
Large language models (LLMs) encode vast amounts of world knowledge. However, since these models are trained on large swaths of internet data, they are at risk of inordinately capt…