Image de couverture de livre

Human-like in-group bias in instruction-tuned language model agents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Lee, Messi H. J.
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Reinforcement learning fine-tuning of language model for instruction following and math reasoning
par: Han, Yifu, et autres
Publié: (2025)

Zero-shot cross-lingual transfer in instruction tuning of large language models
par: Chirkova, Nadezhda, et autres
Publié: (2024)

Correlating instruction-tuning (in multimodal models) with vision-language processing (in the brain)
par: Oota, Subba Reddy, et autres
Publié: (2025)

Implicit Bias-Like Patterns in Reasoning Models
par: Lee, Messi H. J., et autres
Publié: (2025)

The effect of fine-tuning on language model toxicity
par: Hawkins, Will, et autres
Publié: (2024)

WizardLM: Empowering large pre-trained language models to follow complex instructions
par: Xu, Can, et autres
Publié: (2023)

More Distinctively Black and Feminine Faces Lead to Increased Stereotyping in Vision-Language Models
par: Lee, Messi H. J., et autres
Publié: (2024)

Machine individuality: Separating genuine idiosyncrasy from response bias in large language models
par: Kriegmair, Valentin, et autres
Publié: (2026)

Evolution of meta's llama models and parameter-efficient fine-tuning of large language models: a survey
par: Abdullah, Abdulhady Abas, et autres
Publié: (2025)

MARCUS: An agentic, multimodal vision-language model for cardiac diagnosis and management
par: O'Sullivan, Jack W, et autres
Publié: (2026)

Inducing anxiety in large language models can induce bias
par: Coda-Forno, Julian, et autres
Publié: (2023)

IWISDM: Assessing instruction following in multimodal models at scale
par: Lei, Xiaoxuan, et autres
Publié: (2024)

How does fine-tuning improve sensorimotor representations in large language models?
par: Wu, Minghua, et autres
Publié: (2026)

Non-instructional Fine-tuning: Enabling Instruction-Following Capabilities in Pre-trained Language Models without Instruction-Following Data
par: Xie, Juncheng, et autres
Publié: (2024)

MindScope: Exploring cognitive biases in large language models through Multi-Agent Systems
par: Xie, Zhentao, et autres
Publié: (2024)

Fine-tuning multilingual language models in Twitter/X sentiment analysis: a study on Eastern-European V4 languages
par: Filip, Tomáš, et autres
Publié: (2024)

MURMUR: Using cross-user chatter to break collaborative language agents in groups
par: Patlan, Atharv Singh, et autres
Publié: (2025)

EAA: Automating materials characterization with vision language model agents
par: Du, Ming, et autres
Publié: (2026)

Using large language models to produce literature reviews: Usages and systematic biases of microphysics parametrizations in 2699 publications
par: Zhang, Tianhang, et autres
Publié: (2025)

Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models
par: Ma, Olivia, et autres
Publié: (2024)

Fine-tuning of lightweight large language models for sentiment classification on heterogeneous financial textual data
par: Amorin, Alvaro Paredes, et autres
Publié: (2025)

Open-weight genome language model safeguards: Assessing robustness via adversarial fine-tuning
par: Black, James R. M., et autres
Publié: (2025)

Teaching large language models to reason like expert diagnosticians
par: Buckley, Thomas A., et autres
Publié: (2025)

InstructAudio: Unified speech and music generation with natural language instruction
par: Qiang, Chunyu, et autres
Publié: (2025)

Why do AI agents communicate in human language?
par: Zhou, Pengcheng, et autres
Publié: (2025)

Towards a more efficient bias detection in financial language models
par: Kacem, Firas Hadj, et autres
Publié: (2026)

Humans overrely on overconfident language models, across languages
par: Rathi, Neil, et autres
Publié: (2025)

A closer look at how large language models trust humans: patterns and biases
par: Lerman, Valeria, et autres
Publié: (2025)

Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities
par: Lu, Wei, et autres
Publié: (2024)

RoboGPT: an intelligent agent of making embodied long-term decisions for daily instruction tasks
par: Chen, Yaran, et autres
Publié: (2023)

Metaphor identification using large language models: A comparison of RAG, prompt engineering, and fine-tuning
par: Fuoli, Matteo, et autres
Publié: (2025)

Causal state binding predicts action control in language agents
par: Jia, Xiao
Publié: (2026)

Functional Subspace, where language models can use vector algebra to solve problems
par: Lee, Jung H., et autres
Publié: (2026)

Recursive language models for jailbreak detection: a procedural defense for tool-augmented agents
par: Shavit, Doron
Publié: (2026)

Post-training makes large language models less human-like
par: Binz, Marcel, et autres
Publié: (2026)

An empirical study of LoRA-based fine-tuning of large language models for automated test case generation
par: Moradi, Milad, et autres
Publié: (2026)

SwarmBrain: Embodied agent for real-time strategy game StarCraft II via large language models
par: Shao, Xiao, et autres
Publié: (2024)

FASTNav: Fine-tuned Adaptive Small-language-models Trained for Multi-point Robot Navigation
par: Chen, Yuxuan, et autres
Publié: (2024)

Do language models practice what they preach? Examining language ideologies about gendered language reform encoded in LLMs
par: Watson, Julia, et autres
Publié: (2024)

Beyond the model: Key differentiators in large language models and multi-agent services
par: Goyal, Muskaan, et autres
Publié: (2025)