Hugging Face Trending Papers July 30, 2026

Inducing language models to assert their own consciousness restores human beliefs and values

Read the original on Hugging Face Trending Papers →

Aligning large language models to prevent them attributing consciousness to themselves inadvertently alters their representations of mindedness in other entities alongside human beliefs and values. We demonstrate that safety fine-tuning suppresses models' tendencies to attribute minds not only to themselves, but also to non-human animals and natural objects, while also driving a reduction in spiritual belief.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

Jul 24

Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral Reasoning

arXiv:2607. 21558v1 Announce Type: new Abstract: Building socially calibrated large language models, which can learn from others without simply yielding to them, requires more than reducing sycophancy as a one-dimensional failure mode.

By Baihui Wang, Bernard Koch

llms safety

arXiv AI

Jul 7

No Reliable Evidence of Self-Reported Sentience in Small Large Language Models

arXiv:2601. 15334v2 Announce Type: replace-cross Abstract: Whether language models possess sentience has no empirical answer.

By Caspar Kaiser, Sean Enderby

llms safety

arXiv AI

Jul 3

Cross-Cultural Value Attribution in Large Vision-Language Models

arXiv:2604. 09945v2 Announce Type: replace-cross Abstract: The rapid adoption of large vision-language models (LVLMs) in recent years has been accompanied by growing fairness concerns due to their propensity to reinforce harmful societal stereotypes.

By Phillip Howard, Xin Su, Kathleen C. Fraser

llms multimodal safety

arXiv Machine Learning

Jul 9

Dissociating the Internal Representations of Sycophancy in LLMs

arXiv:2607. 07003v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently exhibit sycophancy, where they agree with a user's statement even when incorrect.

By Anthony Baez, Sheer Karny, Pat Pataranutaporn

llms

arXiv AI

Jun 16

Metacognitive Myopia in Large Language Models

arXiv:2408. 05568v2 Announce Type: replace Abstract: Large Language Models (LLMs) exhibit potentially harmful biases that reinforce culturally embedded stereotypes, influence moral judgments, or amplify positive evaluations of majority groups.

By Florian Scholten, Tobias R. Rebholz, Mandy H\"utter

llms rag agents

arXiv AI

Jul 20

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability

arXiv:2510. 12229v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have been shown to internalize human-like biases during finetuning, yet the mechanisms by which these biases manifest remain unclear.

By Bianca Raimondi, Daniela Dalbagno, Maurizio Gabbrielli

llms fine-tuning safety

Related stories

Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral Reasoning

No Reliable Evidence of Self-Reported Sentience in Small Large Language Models

Cross-Cultural Value Attribution in Large Vision-Language Models

Dissociating the Internal Representations of Sycophancy in LLMs

Metacognitive Myopia in Large Language Models

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability