The paper investigates natural language autoencoders (NLAs) as tools for verbalizing activation differences in large language models. It examines whether NLAs capture compositional structure, generalize to fine‑tuned models, recover fine‑tuning objectives, and can be specialized for model diffing. Experiments across four models show that NLAs largely succeed in these tasks, though they do not yet match state‑of‑the‑art diffing methods on emergent misalignment detection.
By Andrea Blasi N\'u\~nez, Gianluca Barmina, Federico Torrielli, Thiusius Rajeeth Savarimuthu, Peter Schneider-Kamp, Lukas Galke Poech
Large language models are typically trained with next-token prediction (NTP), which rewards predicting specific tokens rather than explicitly accounting for the semantic similarities between different...
arXiv:2610.29843v1 Announce Type: new
Abstract: Large language models are typically trained with next-token prediction (NTP), which rewards predicting specific tokens rather than explicitly accountin...
By Laya Iyer, Chen Shani
arXiv:2606. 15521v1 Announce Type: cross Abstract: Tokenization introduces representational redundancy: under a fixed token vocabulary, every byte string admits many valid token encodings, or segmentations, that decode to the same surface string.
By Kanishk Jain, Matthew Day, Tankut Can
arXiv:2604. 19139v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) continue to evolve through alignment techniques such as Reinforcement Learning from Human Feedback (RLHF) and Constitutional AI, a growing and increasingly conspicuous phenomenon has emerged: the proliferation of verbal tics--repetitive, formulaic linguistic patterns that pervade model outputs.
By Shuai Wu, Xue Li, Yanna Feng, Yufang Li, Zhijun Wang, Ran Wang
arXiv:2610.18727v2 Announce Type: replace
Abstract: Natural Language Autoencoders (NLAs) are proposed as oversight tools for language models: an Activation Verbaliser (AV) writes an English explanati...
By Kevin Yandoka Denamgana\"i
arXiv:2609.34187v2 Announce Type: replace-cross
Abstract: The strong version of the stochastic parrot argument claims that, although large language models (LLMs) may exceed rote regurgitation, they c...
By Julia Witte Zimmerman, Calla G. Beauregard, Tabia Tanzin Prama, Parisa Suchdev, Kathryn Cramer, Elisabeth Kollrack
arXiv:2608. 16627v1 Announce Type: cross Abstract: Natural language explanations (NLEs) are increasingly used as inputs, for example, as few-shot rationales that influence model behavior in in-context learning (ICL).
By Mahdi Dhaini, Adam Dejl, Juraj Vladika, Volkan \"Ozer, Barbara Plank, Gjergji Kasneci
arXiv:2605.30381v2 Announce Type: replace-cross
Abstract: When a language model is fine-tuned to produce systematically incorrect responses, does this training leave a structured, linearly recoverabl...
By Vahideh Zolfaghari
arXiv:2606. 11552v1 Announce Type: cross Abstract: Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their autoregressive decoding process incurs substantial inference costs due to inherently sequential token generation.
By Lexington Whalen, Yuki Ito, Ryo Sakamoto
arXiv:2606. 08682v1 Announce Type: cross Abstract: Activation steering has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs).
By Qi Cao, Jian Lou, Meiting Liu, Wenjie Feng, Dan Li, See-Kiong Ng, Anh Tuan Luu
The paper introduces domain-specific languages (DSLs) as an explicit representation layer to bridge the gap between high-level natural-language abstractions and concrete actions. Experiments on the visually-grounded “Hexagons” task and the “Text2CAD” benchmark show that code generation using a human-curated DSL yields dramatic performance gains, especially at higher abstraction levels, while automatically induced DSLs only partially recover these gains. The study highlights that the right representation can close much of the performance gap caused by abstraction, but that automatically learning such representations remains a challenge.
By Amit Lisha, Reut Tsarfaty