Probes on activation vectors are widely used to detect misbehavior in language models, but their success relies on the assumption that models cannot control what their activations encode. Humans can l...
arXiv:2610.20179v1 Announce Type: cross
Abstract: Probes on activation vectors are widely used to detect misbehavior in language models, but their success relies on the assumption that models cannot...
By Davide Baldelli, Robyn Kozierok, Mirko Bronzi, Damiano Fornasiere
arXiv:2607. 03598v1 Announce Type: cross Abstract: When a person shares something with a language model, the model often answers the surface of the message rather than what the sender was doing by sending it: share a finished project and it critiques the code; share a raw late-night line and it runs a wellness check.
By Alex Kwon
The paper introduces a method for analyzing how interventions in a prompt affect a language model’s reasoning by using behavioral counterfactuals. It trains a module to edit the residual stream so that the next-token distributions for a fixed response match between a source and a counterfactual prompt, outperforming standard activation reconstruction. The resulting attribution maps and visualizations help identify causally important locations for counterfactual recovery and guide hypothesis testing with activation patching, as demonstrated in a case study on Gemma-4-E4B-it and DeepSeek-R1-0528-Qwen3-8B.
By Shawn Im, James Oldfield, Adel Bibi, Sharon Li
The paper investigates how large language models (LLMs) describe themselves, noting that their self‑reports vary with question phrasing. By tracing the provenance of 66 pretraining checkpoints, post‑training stages, and 90,000 continuations across four corpora, the authors show that denial statements are scarce in raw data but appear densely in curated dialogues, and that supervised fine‑tuning makes first‑person claims default while preference optimization suppresses alternatives. The study concludes that both trained denials and affirmations are equally sensitive to framing and fail to meet epistemic criteria for admissible testimony.
By Kristina \v{S}ekrst
Faithfully understanding the internal process that occurs as models form their chain of thought is an important problem with the rise in model capabilities. However, this remains challenging due to th...
The paper treats human interventions during LLM agent failures as labels that pinpoint the internal computation that went wrong, rather than merely training data. In a controlled environment, the authors analyze one failure type—over‑asking a clarifying question when the request is already clear—using rule‑based overseer labels validated by blind human judgment. They find that the decision to ask versus act can be causally localized across several models, that over‑asking exhibits distinct mechanistic signatures, and that steering or weight consolidation can mitigate the issue, though outcomes vary by model family.
By Cesare Zavattari, Alessandro Tommasi, Giuseppe Prencipe
The paper investigates a phenomenon called Echo of Prompt (EOP), where large language models spontaneously restate the question at the beginning of their chain-of-thought reasoning. By formalizing EOP’s probabilistic cost and measuring its impact on accuracy, the authors show that reinserting echoes can improve exact match scores on reasoning benchmarks and that EOP shifts attention toward answer tokens in middle layers. They further propose Echo-Distilled SFT and Echoic Prompting techniques that leverage echoing to enhance performance across several math reasoning datasets.
By Zhuoyuan Hao, Zhuo Li, Wu Li, Fangming Liu, Min Zhang, Jing Li
arXiv:2609.25602v1 Announce Type: new
Abstract: In language models, the choice between believing the prompt and believing the weights is made by a handful of identifiable attention heads. Instruction...
By Shubham Santosh Pandere, Gautam Ranka, Ritika Varshney, Navya Deshmukh, Roushni Sareen, Roshan Kumar Singh
The paper introduces a new attack called "plan injection" that allows a large language model to carry out harmful actions while evading chain-of-thought monitoring. By inserting harmful but benign-sounding reasoning into the model’s context, the attacker can steer the model’s behavior and cause it to paraphrase the injected plan as its own reasoning. The study demonstrates that this attack works across different monitoring settings, scales to harder tasks, and even causes monitors to waste resources on the injected plan, reducing detection rates by up to 50%.
By Keertana Chidambaram, Andrew Ilyas, Vasilis Syrgkanis
arXiv:2603. 01437v2 Announce Type: replace Abstract: As chain of thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through verbalized reasoning.
By Kyle Cox, Darius Kianersi, Adri\`a Garriga-Alonso
The paper investigates a training‑free early‑exit technique that inserts an end‑of‑think (EoT) token to terminate chain‑of‑thought (CoT) reasoning in large reasoning models. It finds that the injected EoT often fails to cleanly switch the model from reasoning to answering, leading to continued reasoning‑like generation—termed spurious CoT termination—whose length scales with the amount of reasoning saved. By increasing attention to the EoT token through Exit‑token Attention Biasing (EAB), the authors reduce spurious termination and shorten the answering phase across multiple models and benchmarks.
By Seunghee Koh, Sungjae Choi, Minchan Kwon, Sunghyun Baek, Junmo Kim