3 papers
cs.AI2024
Influential Language Data Selection via Gradient Trajectory Pursuit
Zhiwei Deng, Tao Li, Yang Li
Curating a desirable dataset for training has been the core of building highly capable large language models (Touvron et al., 2023; Achiam et al., 2023; Team et al.,2024). Gradient…
cs.AI2024
Devil's Advocate: Anticipatory Reflection for LLM Agents
Haoyu Wang, Tao Li, Zhiwei Deng +2
In this work, we introduce a novel approach that equips LLM agents with introspection, enhancing consistency and adaptability in solving complex tasks. Our approach prompts LLM age…
cs.HC2024
Automatic Macro Mining from Interaction Traces at Scale
Forrest Huang, Gang Li, Tao Li +1
Macros are building block tasks of our everyday smartphone activity (e.g., "login", or "booking a flight"). Effectively extracting macros is important for understanding mobile inte…