arXiv Computation and Language September 1, 2026 By Chenghao Yang

Beyond Surface Alignment: Grounding the Dynamics of Situational Understanding and Generative Control in LLMs

Read the original on arXiv Computation and Language →

The Flow has not summarised this story yet — read it at arXiv Computation and Language.

arXiv AI

3d ago

LLM Probability Concentration: How Alignment Shrinks the Generative Horizon

arXiv:2506.17871v4 Announce Type: replace-cross Abstract: Despite their impressive capabilities, aligned large language models (LLMs) often generate outputs that lack diversity. What drives this cons...

By Chenghao Yang, Sida Li, Ari Holtzman

llms safety

Hugging Face Trending Papers

Jun 17

The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs

Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment.

llms benchmarks safety

arXiv AI

Aug 11

Unified Hallucination Fuzzing for Multimodal Large Language Models

arXiv:2608. 07525v1 Announce Type: cross Abstract: Hallucination remains a persistent challenge for Multimodal Large Language Models (MLLMs), severely limiting their reliability in high-stakes applications.

By Pengfei Zhou, Jiajun Song, Zhiwei Tang, Yixing Ma, Xiaopeng Peng, Donghui Si, Yuhang Xu, Huiqi Song, Yiyuan Miao, Yichen Qian, Weihua Chen, Wangbo Zhao, Bohan Zhuang, Jiasheng Tang, Yang You

llms reinforcement-learning multimodal benchmarks safety

arXiv AI

Jun 30

Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering

arXiv:2606. 29824v1 Announce Type: cross Abstract: While Large Language Models (LLMs) excel as static solvers, transforming them into autonomous agents remains challenging.

By Chengfeng Zhao, Yuqiao Tan, Shizhu He, Yequan Wang, Jun Zhao, Kang Liu

llms rag agents benchmarks

Hugging Face Trending Papers

Jun 29

Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering

While Large Language Models (LLMs) excel as static solvers, transforming them into autonomous agents remains challenging. This transition requires continuous environmental interaction, yet current agents lack the necessary persistent procedural memory.

llms rag agents benchmarks

arXiv AI

Jul 28

Do LLMs Experience an Internal Polylogue? Investigating Reasoning through the Lens of Personas

arXiv:2605. 09159v2 Announce Type: replace Abstract: Recent work shows that large language models (LLMs) encode behavioral traits ("personas") as linear directions in activation space, often called "persona vectors".

By Nils A. Herrmann, Leander Girrbach, Kirill Bykov, Zeynep Akata

llms

One email a morning, machine-written

Related stories

LLM Probability Concentration: How Alignment Shrinks the Generative Horizon

The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs

Unified Hallucination Fuzzing for Multimodal Large Language Models

Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering

Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering

Do LLMs Experience an Internal Polylogue? Investigating Reasoning through the Lens of Personas