Kenneth Li

6 papers · 2023–2026 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird 🧭 Keyword Pioneer

Venues

ICML (3) ACL (1) ICLR (1) NeurIPS (1)

Top co-authors

Martin Wattenberg (4) Fernanda Viégas (3) Hanspeter Pfister (2) Samy Jelassi (1) Chenxi Whitehouse (1) Eshika Saxena (1) Bhaktipriya Radharapu (1) Oam Patel (1) Vignav Ramesh (1) David Bau (1)

Research topics

Artificial Intelligence (6) Core AI (6) Machine Learning (4) Core Methods (4) Natural Language Processing (2) Resources & Methods (2) Reinforcement Learning (1) Methods (1)

Keywords

large language model (2) confidence calibration (1) model interpretability (1) pretraining (1) language model (1) world model (1) uncertainty estimation (1) sequence model (1) attention head (1) linear representation (1) internal representation (1) brier score (1) activation steering (1) inference-time intervention (1) intermediate layer (1) linear probe (1) interventional analysis (1) emergent representation (1) linear function (1) post training (1)

Papers

Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation ACL 2026 Communicating Activations Between Language Model Agents ICML 2025 When Bad Data Leads to Good Models ICML 2025 Q-Probe: A Lightweight Approach to Reward Maximization for Language Models ICML 2024 Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task ICLR 2023 Inference-Time Intervention: Eliciting Truthful Answers from a Language Model NeurIPS 2023