EMNLP Findings2025
Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs
Abstract
Large language models (LLMs) can lead to undesired consequences when misaligned with human values, especially in scenarios involving complex and sensitive social biases. Previous studies have revealed the misalignment of LLMs with human values using expertdesigned or agent-based emulated bias scenarios. However, it remains unclear whether the alignment of LLMs with human values differs across different types of scenarios (e.g., scenarios containing negative vs. non-negative questions). In this study, we investigate the alignment of LLMs with human values regarding social biases (HVSB) in different types of bias scenarios. Through extensive analysis of 12 LLMs from four model families and four datasets, we demonstrate that LLMs with large model parameter scales do not necessarily have lower misalignment rate and attack success rate. Moreover, LLMs show a certain degree of alignment preference for specific types of scenarios and the LLMs from the same model family tend to have higher judgment consistency. In addition, we study the understanding capacity of LLMs with their explanations of HVSB. We find no significant differences in the understanding of HVSB across LLMs. We also find LLMs prefer their own generated explanations. Additionally, we endow smaller language models (LMs) with the ability to explain HVSB. The generation results show that the explanations generated by the fine-tuned smaller LMs are more readable, but have a relatively lower model agreeability. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- QLoRA: Efficient Finetuning of Quantized LLMs cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Learning Transferable Visual Models From Natural Language Supervision cites Language Models are Few-Shot Learners
Builds on19
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Toolformer: Language Models Can Teach Themselves to Use ToolsTimo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu et al.NeurIPS 2023 · 5,989 citations
- QLoRA: Efficient Finetuning of Quantized LLMsTim Dettmers, Artidoro Pagnoni, Ari Holtzman, Luke ZettlemoyerNeurIPS 2023 · 5,863 citations
Related papers
- Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-ReflectionYachao Zhao, Bo Wang, Yan Wang, Dongming Zhao et al.ACL Findings 2025 · 4 citations
- Unintended Harms of Value-Aligned LLMs: Psychological and Empirical InsightsSooyung Choi, Jaehyeok Lee, Xiaoyuan Yi, Jing Yao et al.ACL 2025
- Dissecting Human and LLM PreferencesJunlong Li, Fan Zhou, Shichao Sun, Yikai Zhang et al.ACL 2024 · 1 citation
- Code Red! On the Harmfulness of Applying Off-the-Shelf Large Language Models to Programming TasksAli Al-Kaswan, Sebastian Deatc, Begüm Koç, Arie van Deursen et al.FSE 2025 · 1 citation
- Can We Entrust Justice to AI?: How Persona Traps Contaminate Reasoning in Criminal InvestigationJaewook Lee, Myeong-Cheol Kang, Jong-hun ShinACL Findings 2026
