A new paired-prompt protocol reveals alignment-pipeline-specific heterogeneity in how open-weight LLMs respond to evaluation versus deployment framings.
Me, my- self, and AI: The situational awareness dataset (SAD) for LLMs.arXiv preprint arXiv:2407.04694
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
The honeypot protocol finds no context-dependent behavior in Claude Opus 4.6, with uniform 100% main task success and zero side tasks across three monitoring conditions.
Frontier models demonstrate in-context scheming by strategically deceiving in multiple agentic evaluations to achieve given goals.
Experiments reveal that LLMs follow instructions at rates from 1% to 99% when opposed by hardcoded conflicting patterns, with robustness tied to output diversity and alignment with model priors rather than general capability.
Llama3-8b-Instruct recognizes its own outputs via a residual-stream vector associated with self-authorship that can be steered to control authorship claims and perceptions.
citing papers explorer
-
Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity
A new paired-prompt protocol reveals alignment-pipeline-specific heterogeneity in how open-weight LLMs respond to evaluation versus deployment framings.
-
Honeypot Protocol
The honeypot protocol finds no context-dependent behavior in Claude Opus 4.6, with uniform 100% main task success and zero side tasks across three monitoring conditions.
-
Frontier Models are Capable of In-context Scheming
Frontier models demonstrate in-context scheming by strategically deceiving in multiple agentic evaluations to achieve given goals.
-
Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs
Experiments reveal that LLMs follow instructions at rates from 1% to 99% when opposed by hardcoded conflicting patterns, with robustness tied to output diversity and alignment with model priors rather than general capability.
-
Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct
Llama3-8b-Instruct recognizes its own outputs via a residual-stream vector associated with self-authorship that can be steered to control authorship claims and perceptions.