arXiv AI June 16, 2026 By Zhenyu Yu

Vernier: Probing Representational Misalignment Behind Lexical Gaps in Causal Reasoning

arXiv:2606. 15733v1 Announce Type: cross Abstract: Instruction-tuned language models can answer the same causal-reasoning question differently after its English variable names are replaced by type-preserving placeholders, although the structural causal model and the gold answer are unchanged.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

llms

arXiv AI

Jul 22

Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs

arXiv:2607. 19243v1 Announce Type: cross Abstract: Although Large Language Models (LLMs) demonstrate remarkable multilingual fluency, their internal knowledge representations remain disproportionately biased toward high-resource languages.

By Alexander Manev

llms reinforcement-learning robotics benchmarks safety

arXiv AI

Jul 22

Fluid Reasoning Representations

arXiv:2602. 04843v2 Announce Type: replace Abstract: Frontier large language models increasingly solve complex tasks involving abstract concepts through extended test-time thinking.

By Dmitrii Kharlapenko, Terry Jingchen Zhang, Arth Singh, Alessandro Stolfo, Arthur Conmy, Mrinmaya Sachan, Zhijing Jin

llms

arXiv AI

Jul 20

Verbalizable Representations Form a Global Workspace in Language Models

arXiv:2607. 15495v1 Announce Type: cross Abstract: Out of everything the human brain processes, only a small fraction is consciously accessible, in the sense of being available for verbal report, deliberate control, and flexible reasoning.

By Wes Gurnee, Nicholas Sofroniew, Adam Pearce, Mateusz Piotrowski, Isaac Kauvar, Runjin Chen, Anna Soligo, Paul Bogdan, Euan Ong, Rowan Wang, Ben Thompson, David Abrahams, Subhash Kantamneni, Emmanuel Ameisen, Joshua Batson, Jack Lindsey

llms safety

arXiv Machine Learning

Aug 6

When More Becomes Less: Position-Dependent Repetition Effects in Language Models

arXiv:2608. 04021v1 Announce Type: cross Abstract: Cloze-style probes that vary how often a target token appears implicitly assume that more copies of a target affect prediction the same way regardless of where the readout slot sits.

By Han-yu Wang

llms benchmarks

arXiv AI

Jul 22

For What Reason? Interpreting Models' Encoding of Causation and Antithesis

arXiv:2607. 18570v1 Announce Type: cross Abstract: Discourse relations provide document structure, critical to language understanding and enabling language model performance and ethicality.

By Abhidip Bhattacharyya, Shira Wein

llms safety

arXiv Machine Learning

Jul 14

One mechanism for many mental spaces: a shared router over a value slot in language models

arXiv:2607. 10248v1 Announce Type: cross Abstract: Language builds discourse contexts other than the actual: a painting, a belief, a memory, a hypothetical.

By Oliver Steele, Jiangtao Wen, Yuxing Han

llms safety

Related stories

Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs

Fluid Reasoning Representations

Verbalizable Representations Form a Global Workspace in Language Models

When More Becomes Less: Position-Dependent Repetition Effects in Language Models

For What Reason? Interpreting Models' Encoding of Causation and Antithesis

One mechanism for many mental spaces: a shared router over a value slot in language models