24 citations · 25 across the 6 of their papers we have counts for
8 papers
Causal and Interpretable Structures in LLM Compositional Tasks
Gurbir Arora, Toni J. B. Liu, Jiajun Bao +2
Large language models are able to solve tasks whose answers depend on not only individual input tokens, but also on relations among them. How is such relational information represe…
The Geometry of Ignorance: LLMs Know When to Temper Bayesian Priors
Toni J. B. Liu, Jiajun Bao, Yizhou Liu +4
What does a language model predict when it has few clues? The answer lurks in its unembedding geometry: a single direction of the unembedding matrix encodes the unigram distributio…
A Graph Signal Processing Perspective on Numerical Sequence Representations in LLM In-Context Learning
Jiajun Bao, Zihao Qi, Toni J. B. Liu +4
Pretrained large language models (LLMs) have demonstrated in-context learning (ICL) capabilities for numerical inference over sequences serialized as text. Prior work has identifie…
ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces
Xiangyi Li, Kyoung Whan Choe, Yimin Liu +12
Large language model (LLM) agents are increasingly deployed to automate productivity tasks (e.g., email, scheduling, document management), but evaluating them on live services is r…
Text-Trained LLMs Can Zero-Shot Extrapolate PDE Dynamics, Revealing a Three-Stage In-Context Learning Mechanism
Jiajun Bao, Nicolas Boullé, Toni J. B. Liu +2
Large language models (LLMs) have demonstrated emergent in-context learning (ICL) capabilities across a range of tasks, including zero-shot time-series forecasting. We show that te…
Toward Machine Interpreting: Lessons from Human Interpreting Studies
Matthias Sperber, Maureen de Seyssel, Jiajun Bao +1
Current speech translation systems, while having achieved impressive accuracies, are rather static in their behavior and do not adapt to real-world situations in ways human interpr…
When Did It Happen? Duration-informed Temporal Localization of Narrated Actions in Vlogs
Oana Ignat, Santiago Castro, Yuhang Zhou +3
We consider the task of temporal human action localization in lifestyle vlogs. We introduce a novel dataset consisting of manual annotations of temporal localization for 13,000 nar…
Conversations Gone Alright: Quantifying and Predicting Prosocial Outcomes in Online Conversations
Jiajun Bao, Junjie Wu, Yiming Zhang +2
Online conversations can go in many directions: some turn out poorly due to antisocial behavior, while others turn out positively to the benefit of all. Research on improving onlin…