# What's Not Said Still Hurts: A Description-Based Evaluation Framework for Measuring Social Bias in LLMs

arXiv: https://arxiv.org/abs/2502.19749 · HTML: https://mlsanity.com/paper/2502.19749/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 27 Feb 2025.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation](https://mlsanity.com/paper/2101.11718/) (2021)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- ["I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Dataset](https://mlsanity.com/paper/2205.09209/) (2022)
- [Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems](https://mlsanity.com/paper/2401.05778/) (2024)
- [Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes](https://mlsanity.com/paper/2402.01981/) (2024)
- [Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination](https://mlsanity.com/paper/2406.08818/) (2024)
- [Angry Men, Sad Women: Large Language Models Reflect Gendered Stereotypes in Emotion Attribution](https://mlsanity.com/paper/2403.03121/) (2024)
- [Gender Bias in Large Language Models across Multiple Languages](https://mlsanity.com/paper/2403.00277/) (2024)
- [Unsupervised Discovery of Implicit Gender Bias](https://mlsanity.com/paper/2004.08361/) (2020)
- [Social Bias Probing: Fairness Benchmarking for Language Models](https://mlsanity.com/paper/2311.09090/) (2023)
- [Understanding the Effect of Model Compression on Social Bias in Large Language Models](https://mlsanity.com/paper/2312.05662/) (2023)
- [Measuring Gender Bias in West Slavic Language Models](https://mlsanity.com/paper/2304.05783/) (2023)

## Built on by (most cited first, 8 of 8)

- [Evaluating Implicit Biases in LLM Reasoning through Logic Grid Puzzles](https://mlsanity.com/paper/2511.06160/) (2025)
- [Fair outputs, Biased Internals: Causal Potency and Asymmetry of Latent Bias in LLMs for High-Stakes Decisions](https://mlsanity.com/paper/2605.15217/) (2026)
- [The Straight and Narrow: Do LLMs Possess an Internal Moral Path?](https://mlsanity.com/paper/2601.10307/) (2026)
- [Knowing Bias, Doing Better: Mitigating Social Bias in LLMs via Know-Bias Neuron Enhancement](https://mlsanity.com/paper/2601.21864/) (2026)
- [StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs](https://mlsanity.com/paper/2605.10442/) (2026)
- [Debias It Yourself: Teaching LLMs Cognitive Bias Mitigation Interventions](https://mlsanity.com/paper/2609.40124/) (2026)
- [Acmite: Mitigating Gender Bias in LLMs through Concept-Guided Mutual Information](https://mlsanity.com/paper/2610.01696/) (2026)
- [Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering](https://mlsanity.com/paper/2610.05894/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) often exhibit social biases inherited from their training data. While existing benchmarks evaluate bias by term-based mode through direct term associations between demographic terms and bias terms, LLMs have become increasingly adept at avoiding biased responses, leading to seemingly low levels of bias. However, biases persist in subtler, contextually hidden forms that traditional benchmarks fail to capture. We introduce the Description-based Bias Benchmark (DBB), a novel dataset designed to assess bias at the semantic level that bias concepts are hidden within naturalistic, subtly framed contexts in real-world scenarios rather than superficial terms. We analyze six state-of-the-art LLMs, revealing that while models reduce bias in response at the term level, they continue to reinforce biases in nuanced settings. Data, code, and results are available at https://github.com/JP-25/Description-based-Bias-Benchmark.