# KLAAD: Refining Attention Mechanisms to Reduce Societal Bias in Generative Language Models

arXiv: https://arxiv.org/abs/2507.19962 · HTML: https://mlsanity.com/paper/2507.19962/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 26 Jul 2025.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [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)
- [BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation](https://mlsanity.com/paper/2101.11718/) (2021)
- [Measuring and Reducing Gendered Correlations in Pre-trained Models](https://mlsanity.com/paper/2010.06032/) (2020)
- [Gender Bias in Neural Natural Language Processing](https://mlsanity.com/paper/1807.11714/) (2018)
- [Crowdsourcing a Word-Emotion Association Lexicon](https://mlsanity.com/paper/1308.6297/) (2013)
- [Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets](https://mlsanity.com/paper/2106.10328/) (2021)
- [FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders](https://mlsanity.com/paper/2103.06413/) (2021)
- [Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models](https://mlsanity.com/paper/2405.10431/) (2024)
- [NRC VAD Lexicon v2: Norms for Valence, Arousal, and Dominance for over 55k English Terms](https://mlsanity.com/paper/2503.23547/) (2025)
- [Debiasing Algorithm through Model Adaptation](https://mlsanity.com/paper/2310.18913/) (2023)
- [ChatGPT Based Data Augmentation for Improved Parameter-Efficient Debiasing of LLMs](https://mlsanity.com/paper/2402.11764/) (2024)
- [Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads](https://mlsanity.com/paper/2311.10395/) (2023)
- [Identifying and Mitigating Social Bias Knowledge in Language Models](https://mlsanity.com/paper/2408.11843/) (2024)
- [FineDeb: A Debiasing Framework for Language Models](https://mlsanity.com/paper/2302.02453/) (2023)
- [From Prejudice to Parity: A New Approach to Debiasing Large Language Model Word Embeddings](https://mlsanity.com/paper/2402.11512/) (2024)

## Built on by (most cited first, 3 of 3)

- [Intra-Fairness Dynamics: The Bias Spillover Effect in Targeted LLM Alignment](https://mlsanity.com/paper/2602.16438/) (2026)
- [UGID: Unified Graph Isomorphism for Debiasing Large Language Models](https://mlsanity.com/paper/2603.19144/) (2026)
- [MASCRDM: Multi-Agent System for Compliance Risk Detection and Mitigation in Training Process of Large Language Models](https://mlsanity.com/paper/2609.39107/) (2026)

## Abstract (arXiv)

Large language models (LLMs) often exhibit societal biases in their outputs, prompting ethical concerns regarding fairness and harm. In this work, we propose KLAAD (KL-Attention Alignment Debiasing), an attention-based debiasing framework that implicitly aligns attention distributions between stereotypical and anti-stereotypical sentence pairs without directly modifying model weights. KLAAD introduces a composite training objective combining Cross-Entropy, KL divergence, and Triplet losses, guiding the model to consistently attend across biased and unbiased contexts while preserving fluency and coherence. Experimental evaluation of KLAAD demonstrates improved bias mitigation on both the BBQ and BOLD benchmarks, with minimal impact on language modeling quality. The results indicate that attention-level alignment offers a principled solution for mitigating bias in generative language models.