8 papers
Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models
Anton de la Fuente, Arthur Conmy
Alignment training, model organisms, and toy models are usually treated as separate research areas. But projects in all three frequently use supervised fine-tuning (SFT) to pursue…
Subliminal Learning Is Steering Vector Distillation
Camila Blank, Agam Bhatia, Senthooran Rajamanoharan +2
Subliminal learning refers to a student language model acquiring a teacher's traits (e.g. a system-prompted preference for owls) when fine-tuned on the teacher's outputs, despite t…
How Transparent is DiffusionGemma?
Joshua Engels, Callum McDougall, Bilal Chughtai +11
LLM reasoning transparency is a critical affordance for understanding model decisions, mitigating misuse and misalignment, and debugging surprising model behaviors. However, Diffus…
How do LLMs Compute Verbal Confidence
Dharshan Kumaran, Arthur Conmy, Federico Barbero +3
Verbal confidence -- prompting LLMs to state their confidence as a number or category -- is widely used to extract uncertainty estimates from black-box models. However, how LLMs in…
Simple LLM Baselines are Competitive for Model Diffing
Elias Kempf, Simon Schrodi, Bartosz Cywiński +3
Standard LLM evaluations only test capabilities or dispositions that evaluators designed them for, missing unexpected differences such as behavioral shifts between model revisions…
Building Production-Ready Probes For Gemini
János Kramár, Joshua Engels, Zheng Wang +4
Frontier language model capabilities are improving rapidly. We thus need stronger mitigations against bad actors misusing increasingly powerful systems. Prior work has shown that a…
Fluid Reasoning Representations
Dmitrii Kharlapenko, Terry Jingchen Zhang, Arth Singh +4
Frontier large language models increasingly solve complex tasks involving abstract concepts through extended test-time thinking. Yet we lack a mechanistic account of how extended t…
Evaluating Sparse Autoencoders for Monosemantic Representation
Moghis Fereidouni, Muhammad Umair Haider, Peizhong Ju +1
A key barrier to interpreting large language models is polysemanticity, where neurons activate for multiple unrelated concepts. Sparse autoencoders (SAEs) have been proposed to mit…