The paper introduces a site-asymmetry audit for activation-space interventions, decomposing order-dependent activation statistics into a canonical additive response from single interventions and an antisymmetrized second difference that removes first-order and self-curvature effects. Across six language-model families, the single-intervention baseline accounts for most of the bracket norm, while the corrected residual often clears a generic-interaction null. The method also transfers to non-language models, demonstrating its portability.
By Anqi Peter Li
arXiv:2606. 01060v1 Announce Type: cross Abstract: Preference alignment has substantially improved the observable behavior of large language models, yet it remains unclear what alignment changes internally.
By Partha Pratim Saha, Samarth Raina, Mayur Parvatikar, Amit Dhanda, Vinija Jain, Aman Chadha, Amitava Das
FLIP is a final‑layer inference‑time probe designed to test whether a logit‑facing intervention site in an open‑weight vision‑language model (VLM) supports structured, task‑linked computation rather than generic perturbation. The probe applies elementwise flooring to the final normalized hidden state before logit computation, leaving other model components unchanged. By sweeping intervention strength on a controlled detection/counting task, FLIP identifies three regimes—negligible change, a bounded interior regime with improved detection recall and reduced counting error, and over‑suppression—while a four‑criterion protocol ensures the observed effects are mechanistically interpretable.
By Drandreb Earl O. Juanico, Rowel O. Atienza
arXiv:2605.01609v2 Announce Type: replace-cross
Abstract: We find that transformer concept representations systematically anti-concentrate in the spectral tail of the unembedding covariance, encoding...
By Pratyush Acharya, Nuraj Rimal, Habish Dhakal
arXiv:2608. 09490v1 Announce Type: new Abstract: Task arithmetic treats fine-tuning displacements as composable directions in weight space, yet it remains unclear when parameter addition reflects predictable changes in model function.
By Chencheng Zhu, Xiaoyang Li, Taotao Cai
arXiv:2607. 09842v1 Announce Type: new Abstract: We investigate whether identity-specifying system prompts produce statistically distinguishable geometric fingerprints in the hidden-state trajectories of four open-weight transformer language models spanning four post-training regimes: no training (Gemma-4-E4B base), multimodal RLHF (Gemma-4-E4B-it), RL distillation (DeepSeek-R1-Distill-Qwen-7B), and SFT (Qwen2.
By Jorge A. Castillo, Marco Torres Y\'evenes, Juan Carlos Lanas
arXiv:2606. 01090v1 Announce Type: cross Abstract: Equivariance theory predicts that an architectural symmetry prior reduces sample complexity by a factor of |G|; this is widely cited but rarely measured as a scaling law with controls that separate the prior from its confounds.
By Ahmed M. Adly
The study investigates whether open‑weight language models can introspect on their own internal computations. Using the Open‑Weight Masked Introspection (OWMI) framework, researchers intervened on various internal components of eight models and asked them to report whether changes had occurred. Across 78,000 measurements, none of the models reliably distinguished real interventions from sham ones, with AUROC values essentially at chance.
Why It Matters: The findings suggest that current open‑weight models lack the ability to audit their own internal states, highlighting a limitation for oversight that relies on a model’s self‑reporting.
By Emilio Ferrara
arXiv:2609.13308v1 Announce Type: cross
Abstract: A companion evaluation found that naming the target part in a manipulation prompt increased action accuracy by 0.32-0.63 across eight vision-language...
By Sarthak Sattigeri
arXiv:2608.20647v1 Announce Type: new
Abstract: Splitting a bidirectional LSTM's contextual representation into a forward-only $F_i$ (strictly a function of tokens $1..i$) and a backward-only $B_i$ (...
By Sai Krishna Arthanari, JaeHyeong Chang, Chengzhe Sun, Siwei Lyu
arXiv:2607. 28308v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) language models route each token to multiple experts, suggesting a geometric account of their benefit: co-selected experts should contribute distinct representation directions.
By Huiyuan Tian, Bonan Xu, Shijian Li
arXiv:2607. 17219v1 Announce Type: cross Abstract: Human survey respondents exhibit question-order effects that satisfy the QQ (quantum question) equality, an a priori, parameter-free prediction of the projective quantum question-order model.
By Pilsung Kang