arXiv:2606. 16407v1 Announce Type: cross Abstract: Faithful and robust pronoun use is important for fair and coherent generations, yet large language models largely fail when multiple referents use different pronouns.
arXiv:2603. 23485v2 Announce Type: replace-cross Abstract: Standard evaluation practices assume that large language model (LLM) outputs are stable when prompts are embedded in contextually equivalent discourses.
Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment.
arXiv:2608.30719v1 Announce Type: new Abstract: Productive dialogue alignment requires distinguishing \emph{surface coordination} (acknowledgments and smooth task progression) from \emph{epistemic al...
Nastase et al. (2026) argue that large language models (LLMs) can shed light on language processing because both use distributed, context‑sensitive representations shaped by statistical learning, and they advocate for LLM‑brain alignment research. They reject simple cortical “boxology” but claim that representational alignment can constrain mechanistic hypotheses, though it does not itself identify a mechanism. The author critiques this position, pointing out logical, causal, and computational underdetermination and the tension between the authors’ methodological caveats and their conclusion that LLMs could serve as fully mechanistic models of language.
Large Language Models (LLMs) frequently exhibit sycophancy, where they agree with a user's statement even when incorrect. While sycophancy is often treated as a single defined behavior, it can manifest in substantially distinct ways and circumstances, raising the question of whether this multi-faceted nature is reflected in its internal mechanisms.
arXiv:2608. 13069v1 Announce Type: new Abstract: Large language models (LLMs) are predominantly aligned to function as passive, sycophantic assistants.
The study probes Gemma‑2‑9B‑IT with Sparse Autoencoders across English, Hebrew, and Russian to examine how multilingual LLMs handle informal register. By using a dataset of polysemous terms that appear in literal and informal contexts, the authors isolate pragmatic register processing from lexical cues. They discover a small, robust cross‑linguistic core that forms an informal register subspace, which becomes clearer in deeper layers and can causally shift output formality across all tested languages, even transferring zero‑shot to six unseen languages.
The paper investigates how language models decide between contextual information and their internal memory when the two conflict. By estimating "authority directions" from agreement prompts and swapping these directions between matched prompts, the authors show that such interventions can reproduce 30–68% of the shift in source choice across Qwen, Llama, and OLMo models. Cross‑task experiments reveal that authority directions learned on one task transfer only modestly (≈9%) to another, indicating that authority computations are largely task‑specific.
arXiv:2607. 19243v1 Announce Type: cross Abstract: Although Large Language Models (LLMs) demonstrate remarkable multilingual fluency, their internal knowledge representations remain disproportionately biased toward high-resource languages.
arXiv:2502.10577v2 Announce Type: replace-cross Abstract: Instruct-based large language models (LLMs) have been shown to propagate and even amplify gender bias when prompted with contextually constra...
The paper investigates how alignment training, specifically reinforcement learning from human feedback (RLHF), affects the internal partisan structure of a large language model. Using a mechanistic case study on Llama 3.1 8B, the authors find that alignment training does not erase the model’s partisan geometry but compresses its variance, producing consistently balanced, non‑partisan outputs. Sparse autoencoder analysis and feature‑level steering experiments reveal that policy‑encoding features become inactive in the aligned model, indicating a causal disconnect rather than structural removal of partisan knowledge.
arXiv:2609.23065v1 Announce Type: cross Abstract: Chain-of-thought (CoT) can sound plausible yet be unfaithful to the model's underlying reasoning. Most prior work probes CoT faithfulness through inp...