Danny Halawi

4 papers · 2024–2025 · 3 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 👑 Triple Crown

Venues

ICLR (2) ICML (1) NeurIPS (1)

Top co-authors

Jacob Steinhardt (3) Fred Zhang (2) Chen Yueh-Han (2) Alexander Wei (1) Jean-Stanislas Denain (1) Eric Wallace (1) Philip Tetlock (1) Ezra Karger (1) Zachary Jacobs (1) Nika Haghtalab (1)

Research topics

Artificial Intelligence (4) Core AI (4) Machine Learning (2) Natural Language Processing (1) Learning Paradigms (1) Learning Types (1) Optimization & Theory (1) Resources & Methods (1)

Keywords

language model (2) few-shot learning (1) harmful content (1) event forecasting (1) data leakage (1) induction head (1) retrieval-augmented generation (1) model internal (1) fine tuning (1) prediction accuracy (1) prediction aggregation (1) harmful response (1) black box (1) competitive forecasting (1) forecasting benchmark (1) forecasting question (1) expert forecasting (1) adversary (1) encoded harmful requests (1) representation learning (1)

Papers

ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities ICLR 2025 Approaching Human-Level Forecasting with Language Models NeurIPS 2024 Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation ICML 2024 Overthinking the Truth: Understanding how Language Models Process False Demonstrations ICLR 2024