2406.19501

arxiv.org · 7,426 words · saved by 1 readers

N/A

Preprint. M ONITORING L ATENT W ORLD S TATES IN L ANGUAGE M ODELS WITH P ROPOSITIONAL P ROBES Jiahai Feng∗, Stuart Russell & Jacob Steinhardt UC Berkeley A BSTRACT Language models (LMs) are susceptible to bias, sycophancy, backdoors, and other arXiv:2406.19501v2 [cs.CL] 6 Dec 2024…

related reading

[2406.19501] Monitoring Latent World States in Language Models with Propositional Probesarxiv.org
Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
Surfacing Pathological Behaviors in Language Models | Transluce AItransluce.org
2308.03958arxiv.org
[2606.04071] Covert Influence Between Language Modelsarxiv.org
2212.03827arxiv.org
[2511.08579] Training Language Models to Explain Their Own Computationsarxiv.org
[2604.16812] Introspection Adapters: Training LLMs to Report Their Learned Behaviorsarxiv.org
Position: It's Time to Optimize for Self-Consistencytime-for-consistency.github.io
[2608.21664] Measuring Activation Control in Large Language Modelsarxiv.org
[2210.13382] Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskarxiv.org
Training Language Models to Explain Their Own Computationsarxiv.org