conftrace_

Jan Betley

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

Venues

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

Top co-authors

Owain Evans (4) Anna Sztyber-Betley (2) Xuchan Bao (2) Kaivalya Hariharan (1) Johannes Treutlein (1) Mikita Balesni (1) Nathan Labenz (1) Sam Marks (1) Roger Grosse (1) Marius Hobbhahn (1)

Research topics

Artificial Intelligence (4) Core AI (4) Deep Learning (1) Machine Learning (1) Natural Language Processing (1) Applications (1) Architectures (1) Learning Types (1)

Keywords

large language model (3) ai safety (2) question answering (1) inductive reasoning (1) instruction following (1) situational awareness (1) model self-awareness (1) behavioral testing (1) backdoor detection (1) fine tuning (1) chain of thought (1) model self-knowledge (1) out-of-context reasoning (1) behavioral self-awareness (1) misalignment (1) backdoor (1) insecure code (1) motivation (1) zero-shot learning (1) predict (1)

Papers

Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs ICML 2025 Tell me about yourself: LLMs are aware of their learned behaviors ICLR 2025 Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data NeurIPS 2024 Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs NeurIPS 2024