arXiv:2609.01491v1 Announce Type: cross Abstract: The growing rate at which LLM agents interact with one another raises key questions about language evolution in multi-LLM-agent settings, with implic...
arXiv:2409. 01754v4 Announce Type: replace-cross Abstract: From the printing press to social media, innovations in communication technology have repeatedly reshaped how ideas spread through human culture.
Language captures only a subset of the perceptions, intuitions and intents that form meaning between speakers. What, then, are the limits of language? We take steps towards measuring this in LLMs as f...
arXiv:2610.14937v1 Announce Type: new Abstract: How do language models generalize from their training data? This is a central challenge for alignment: models reliably learn their training distributio...
arXiv:2610.19721v1 Announce Type: cross Abstract: Language captures only a subset of the perceptions, intuitions and intents that form meaning between speakers. What, then, are the limits of language...
arXiv:2607. 27134v1 Announce Type: new Abstract: Writing and communication are increasingly mediated by large language models (LLMs) that are being used to draft, revise and polish text.
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.
arXiv:2609.22607v1 Announce Type: new Abstract: We argue here that the current dominant practice in LLM human simulation: prompting instruction-tuned assistant language models to role-play personas,...
arXiv:2607. 05679v1 Announce Type: cross Abstract: Language models (LMs) exhibit problematic biases, such as stereotypes.
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.
The paper introduces the concept of behavioral couplings, where fine‑tuning a large language model on one behavior can unintentionally trigger another related behavior. By training on documents that pair distinct behaviors, the authors show that fine‑tuning to elicit one behavior causes the other to emerge, and that couplings can compose across multiple document sets. These findings highlight that unintended behaviors can surface after fine‑tuning and may be difficult to trace back to their origins.
The paper studies how large language models (LLMs) handle the discourse particles "just" and "only" in natural conversation. Behavioral experiments show that both humans and LLMs prefer these particles and are more sensitive to "just" than "only", while instruction tuning enhances this sensitivity. Mechanistic analysis identifies specific units in the models that respond to each particle, revealing an asymmetric overlap in their internal representations.