6 papers
AdaptArena: Evaluating Test-Time Personalization of Web Agents
Dongchan Shin, Xing Han Lù, Jiaqi Deng +7
Large language model (LLM) agents have demonstrated strong performance on complex web navigation tasks, yet they remain brittle in real-world settings where user intentions are und…
BRIDGE: Predicting Human Task Completion Time From Model Performance
Fengyuan Liu, Jay Gala, Nilaksh +3
Evaluating the real-world capabilities of AI systems requires grounding benchmark performance in human-interpretable measures of task difficulty. Existing approaches that rely on d…
TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior
Gül Sena Altıntaş, Malikeh Ehghaghi, Brian Lester +4
Tokenizers provide the fundamental basis through which text is represented and processed by language models (LMs). Despite the importance of tokenization, its role in LM performanc…
Gradient-Sign Masking for Task Vector Transport Across Pre-Trained Models
Filippo Rinaldi, Aniello Panariello, Giacomo Salici +4
When a new release of a foundation model is published, practitioners typically need to repeat fine-tuning, even if the same task was already tackled in the previous version. A prom…
Efficient Model Development through Fine-tuning Transfer
Pin-Jie Lin, Rishab Balasubramanian, Fengyuan Liu +2
Modern LLMs struggle with efficient updates, as each new pretrained model version requires repeating expensive alignment processes. This challenge also applies to domain- or langua…
AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution
Fengyuan Liu, Nikhil Kandpal, Colin Raffel
The influence of contextual input on the behavior of large language models (LLMs) has prompted the development of context attribution methods that aim to quantify each context span…