arXiv Machine Learning August 6, 2026 By Hadi Mohammadi, Tina Shahedi, Robert A. Bagheri, Mehdi Dastani, Masoume M. Raeissi

Learning Sexism Detection Using Multi-Agent Perspectivist Preference Optimization

Read the original on arXiv Machine Learning →

arXiv:2608. 04056v1 Announce Type: cross Abstract: When people label text for sexism, they often disagree, and not because some of them are wrong: they genuinely perceive sexism differently.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 18

Steerable Cultural Preference Optimization of Reward Models

arXiv:2606. 18606v1 Announce Type: cross Abstract: It is essential for large language model (LLM) technology to serve many different cultural sub-communities in a manner that is acceptable to each community.

By Minsik Oh, Advit Deepak, Sophie Wu, Douwe Kiela, Ekaterina Shutova

llms reinforcement-learning fine-tuning safety

arXiv Computation and Language

Sep 1

Labels have Human Values: Value Calibration of Subjective Tasks

arXiv:2601.06631v2 Announce Type: replace Abstract: Building NLP systems for subjective tasks requires one to ensure their alignment to contrasting human values. We propose the MultiCalibrated Subjec...

By Mohammed Fayiz Parappan, Ricardo Henao

rag nlp safety

arXiv Computation and Language

Sep 1

Low-Resource Preference Adaptation of LLMs via Activation-Based Label Propagation

arXiv:2608.30902v1 Announce Type: new Abstract: Adapting large language models to user-specific preferences is often constrained by the cost of human annotation, making preference optimisation imprac...

By Alessio Galatolo, Meriem Beloucif

llms safety

arXiv AI

Jun 8

Analysing Differences in Persuasive Language in LLM-Generated Text: Uncovering Stereotypical Gender Patterns

arXiv:2601. 05751v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used for everyday communication tasks, including drafting interpersonal messages intended to influence and persuade.

By Amalie Brogaard Pauli, Maria Barrett, Max M\"uller-Eberstein, Isabelle Augenstein, Ira Assent

llms

arXiv AI

Sep 1

Evaluating and Mitigating Anti-LGBTQ Biases in German and Multilingual Language Models

The paper introduces a German-English benchmark dataset to evaluate anti‑LGBTQ biases in language models, combining community‑sourced stereotypes from German‑speaking queer individuals with a German translation of WinoQueer. Eight language models of varying sizes and architectures were assessed, revealing that they reproduce anti‑queer stereotypes with differences across identities and models. Fine‑tuning on community and progressive media content reduced bias on average, though the effect was not consistent across all models and identities.

By Melina Morch, Daniel Braun

llms fine-tuning benchmarks safety

arXiv AI

Jul 17

Step-Level Preference Learning for Generative Agents in Social Simulations

arXiv:2607. 14485v1 Announce Type: new Abstract: Large language model (LLM)-based generative agents simulate human behavior through long-horizon decision-making processes that comprise intermediate steps such as planning, memory retrieval, reflection, and action selection.

By Wenchang Gao, Pingyue Sheng, Lanlan Qiu, Yunfei Ma, Jian Zhao, Baicheng Chen, Kangda Wang, Yuyang Tian, Shunqiang Mao, Tianxing He

llms agents fine-tuning

One email a morning, machine-written

Related stories

Steerable Cultural Preference Optimization of Reward Models

Labels have Human Values: Value Calibration of Subjective Tasks

Low-Resource Preference Adaptation of LLMs via Activation-Based Label Propagation

Analysing Differences in Persuasive Language in LLM-Generated Text: Uncovering Stereotypical Gender Patterns

Evaluating and Mitigating Anti-LGBTQ Biases in German and Multilingual Language Models

Step-Level Preference Learning for Generative Agents in Social Simulations