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:2608. 02665v1 Announce Type: cross Abstract: A benchmark score is a measurement instrument, yet most benchmarks read each item at a single canonical surface form.
By Yongxi Zhou, Junwei Yao, Yuanzhe Liu, Zihan Dong, Wenbo Ye, Jiaxi Wen, Lai Yun Choi
The paper demonstrates that a prompt’s influence is not inherent to the prompt itself but depends on the model, as prompts optimized for one model degrade on another and rankings shift under neutral reformatting. By examining a task‑free structural readout—specifically the fixed‑point behavior of a short‑window argmax map—the authors show that nine tokens of conditioning can move the fixed‑point fraction across most of its range, altering structural classes and model rankings, while instruction tuning has no effect. Attempts to explain this phenomenon through prefix length, content type, bidirectionality, or attention‑sink dominance all fail, indicating that the prompt‑model pair is the fundamental unit of explanation.
whyItMatters":"The study reveals that prompt effectiveness is model‑specific and that simple structural readouts can capture this interaction, challenging assumptions about prompt generality and guiding future prompt‑engineering efforts."
By Nicol\'as Vera Z\'u\~niga
arXiv:2608.29070v1 Announce Type: new
Abstract: Chain-of-thought (CoT) reasoning traces are increasingly proposed as a mechanism for AI oversight: a monitor inspecting a model's reasoning can, in pri...
By Zimo Shi, Xander Tifft, Wen Xing
Order-dependent activation statistics are often interpreted as evidence of interaction, but that interpretation can be confounded by where interventions enter the network. We introduce a no-fit site-a...
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
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
This study independently reproduces the dissociation reported by Zhao (2026) regarding chain-of-thought entropy in large language models. It confirms that the shape of the entropy trajectory predicts answer correctness, while the total entropy drop magnitude does not, across four open-weight models and two benchmarks (GSM8K and MATH‑500). The reproduction also maps settings where the magnitude signal holds or fails and documents protocol differences not reported in the original work.
By Theodore O. Cochran
arXiv:2609.01108v1 Announce Type: new
Abstract: TRACE (Math & Lienhart, arXiv:2602.01135) reads causal graphs over event types out of a pretrained autoregressive sequence model by thresholding a per-...
By Alex Chadyuk, Alicia Zhang, Roy Kucukates
The paper introduces AgentDiff, a metric that quantifies how much LLM agents’ answers differ when inputs are altered by meaning‑bearing rewrites (paraphrases, synonym substitutions) versus presentation changes (reordering, formatting, distractors). Across 68 model–benchmark–scaffold combinations involving ten LLMs and over 1,500 questions, meaning‑bearing rewrites consistently produce a roughly 20‑percentage‑point higher inconsistency rate than presentation changes, a gap that persists across severity proxies and remains significant even outside the Qwen family. Trace analysis reveals that meaning‑bearing rewrites preserve the first action but reduce thought similarity from the second step onward, extending the divergence cascade—a phenomenon termed “stealth divergence.”
By Liyun Zhang, Jiayi Guo
arXiv:2608. 02089v1 Announce Type: new Abstract: Large language models often show users a final response and a short reasoning summary while the full reasoning trace stays hidden.
By Andres Algaba, Francesca Carlon, Lynn Delcon, Marthe Ballon, Bert Verbruggen, Vincent Ginis
arXiv:2607. 19257v1 Announce Type: cross Abstract: Practitioners make three prompt-design decisions with almost no controlled evidence behind them: how to format instructions and context (markdown, plain text, prose, or tabular), how many simultaneous instructions a system prompt can carry before compliance degrades, and how much context a model can hold before recall and honesty degrade.
By Netanel Eliav