arXiv (All)
open access
Why Static Probes Fail: Context Determines Deception Feature Composition
With increasing autonomy, Large Language Models (LLMs) may engage in deceptive behaviors, such as scheming to pursue misaligned goals or sandbagging to escape oversight. Monitoring outputs alone is insufficient, as models can produce seemingly benign responses while harboring misaligned internal obj
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- DecepEval: A Benchmark for Evaluating Deception in LLM Agents#1217702
- Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibratione#1051542
- Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibration#1335833
- Contextual Contamination: A Descriptive Case Study of Drift in a Goal-Aware LLM Dialogue Amplified by Gender-Bias#204181
- The Calls are Coming from Inside the Model: Investigating Probe-based Detection of Tool-Calling Errors in LLMs#781045
Record · ID 1403373
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive