arXiv AI

Constitutional Value Potentials: reading and steering internal priority margins in language models

arXiv:2606. 15420v1 Announce Type: cross Abstract: A constitution tells a language model what to value, but little tells us whether it does.

arXiv AI

Jun 2

Causal state binding predicts action control in language agents

arXiv:2605. 09692v3 Announce Type: replace Abstract: Autonomous language agents increasingly expose traces, memories, plans and constraints, but existing evaluations rarely test whether these state variables are bound to final actions.

By Xiao Jia

llms agents benchmarks

arXiv AI

Jun 12

Prefill Awareness in Large Language Models

arXiv:2606. 12747v1 Announce Type: new Abstract: Safety-relevant studies of language models, including alignment and jailbreaking evaluations and AI control protocols, often rely on prefilling model outputs.

By Andy Wang, Parv Mahajan, David Demitri Africa, Alexandra Souly, Jordan Taylor, Robert Kirk

llms agents benchmarks safety

arXiv AI

5d ago

Jagged Judges: Epistemic Stability Under Silence, Pressure, and Persistence

arXiv:2608. 12645v1 Announce Type: new Abstract: LLM judges have become central infrastructure for model evaluations, online grading, and reward modeling.

By Justin Zhao, Himaghna Bhattacharjee, Hannah Korevaar, Bhaktipriya Radharapu, Khalid El-Arini

llms reinforcement-learning safety

arXiv AI

Jul 14

Interaction Scaling: Grounding the Third Axis of Test-Time Compute

arXiv:2607. 11598v1 Announce Type: new Abstract: There are two standard ways to spend more compute at test time: let a model reason longer, or sample more attempts and keep one.

By Bojie Li, Noah Shi

llms multimodal

arXiv AI

Jun 17

In-Context Environments Induce Evaluation-Awareness in Language Models

arXiv:2603. 03824v2 Announce Type: replace Abstract: Humans often become more self-aware under threat, yet can lose self-awareness when absorbed in a task; we hypothesize that language models exhibit environment-dependent \textit{evaluation awareness}.

By Maheep Chaudhary

llms benchmarks safety

arXiv Machine Learning

Jul 8

More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges

arXiv:2607. 05904v1 Announce Type: new Abstract: Training a language model against its own reference-free judgments (the premise of self-rewarding, self-play, and LLM-as-a-judge pipelines) assumes a model's verdict on a shown answer tracks correctness.

By Chenyu Zhou

llms reinforcement-learning

arXiv Machine Learning

Jun 30

Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring

arXiv:2606. 30449v1 Announce Type: new Abstract: Probes on model internals could help monitor agentic systems if they identify harmful text or tool actions before those actions are generated.

By Max Fomin, Elad David, Amit LeVi

llms agents fine-tuning

arXiv AI

Jun 24

AdversaBench: Automated LLM Red-Teaming with Multi-Judge Confirmation and Cross-Model Transferability

arXiv:2606. 24589v1 Announce Type: new Abstract: Scaling adversarial evaluation of large language models requires both a method for generating hard inputs and a reliable way to confirm that resulting failures are real.

By Khanak Khandelwal (Indian Institute of Technology Jodhpur)

llms agents safety

arXiv Machine Learning

Aug 10

Sharding Prevents LLM Oversight Failures and Adversarial Exploitation

arXiv:2608. 06422v1 Announce Type: new Abstract: Giving an LLM judge more compute does not necessarily make it check more requirements.

By Victor Akinwande, J. Zico Kolter, Aran Nayebi

llms safety

arXiv Machine Learning

Jul 30

Constitutional Midtraining: Content Presence Drives Alignment Gains

arXiv:2607. 26654v1 Announce Type: cross Abstract: Post-training alignment is often shallow, eroding under fine-tuning.

By Desiree Cho, Cameron Tice, Bernie Hogan, Hunar Batra, Puria Radmard, Jun Zhao, Nigel Shadbolt

fine-tuning benchmarks safety

arXiv AI

Jul 1

The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs

arXiv:2606. 22686v2 Announce Type: replace-cross Abstract: Modern Large Language Models (LLMs) rely on extensive safety alignment, yet the mechanistic basis of refusal remains opaque.

By Shivam Ratnakar, Kartikeya Vats

llms multimodal safety

Hugging Face Trending Papers

Jul 13

Interaction Scaling: Grounding the Third Axis of Test-Time Compute

There are two standard ways to spend more compute at test time: let a model reason longer, or sample more attempts and keep one. Both share a hidden limit: they are internal.

llms multimodal

Related stories