activity
20242026
most citedChain-of-Thought Reasoning In The Wild Is Not Always Faithful

1 citations · 1 across the 9 of their papers we have counts for

collaborators
Showing cs.AIShow all

6 papers · 1 filter

cs.AI20261 cited

Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Iván Arcuschin, Jett Janiak, Robert Krzyzanowski +3

Recent studies indicate that when faced with explicit biases in prompts, models often omit mentioning these biases in their Chain-of-Thought (CoT) output, revealing that verbalized…

cs.AI2026

How Well Do Models Follow Their Constitutions?

Arya Jakkli, Senthooran Rajamanoharan, Neel Nanda

Frontier AI developers now train models against long written behavioral specifications, such as Anthropic's constitution (Anthropic, 2025a) and OpenAI's Model Spec (OpenAI, 2025a),…

cs.AI2026

Emergent Misalignment is Easy, Narrow Misalignment is Hard

Anna Soligo, Edward Turner, Senthooran Rajamanoharan +1

Finetuning large language models on narrowly harmful datasets can cause them to become emergently misaligned, giving stereotypically `evil' responses across diverse unrelated setti…

cs.AI2025

Interpretable Embeddings with Sparse Autoencoders: A Data Analysis Toolkit

Nick Jiang, Xiaoqing Sun, Lisa Dunlap +2

Analyzing large-scale text corpora is a core challenge in machine learning, crucial for tasks like identifying undesirable model behaviors or biases in training data. Current metho…

cs.AI2025

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

Tomek Korbak, Mikita Balesni, Elizabeth Barnes +38

AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known A…

cs.AI2025

An Approach to Technical AGI Safety and Security

Rohin Shah, Alex Irpan, Alexander Matt Turner +27

Artificial General Intelligence (AGI) promises transformative benefits but also presents significant risks. We develop an approach to address the risk of harms consequential enough…