Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment (2025.naacl-long)
Copied to clipboard
Sangwon Yu, Jongyoon Song, Bongkyu Hwang, Hoyoung Kang, Sooah Cho, Junhwa Choi, Seongho Joe, Taehee Lee, Youngjune Gwon, Sungroh Yoon
| Challenge: | Experimental results show that large language models exhibit a negative bias in binary decision tasks . hallucination is a factor that degrades reliability of LLMs . |
| Approach: | They propose a negative attention score to systematically and quantitatively formulate negative bias by using a parameter-efficient fine-tuning technique. |
| Outcome: | The proposed method reduces the gap between precision and recall caused by negative bias while preserving generalization abilities. |
Similar Papers
KLAAD: Refining Attention Mechanisms to Reduce Societal Bias in Generative Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models exhibit societal biases in their outputs, prompting ethical and societal challenges. |
| Approach: | They propose an attention-based debiasing framework that implicitly aligns attention distributions between stereotypical and anti-stereotypical sentence pairs without directly modifying model weights. |
| Outcome: | The proposed framework improves on BBQ and BOLD benchmarks while maintaining fluency and coherence. |
Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models can lead to undesired consequences when misaligned with human values . previous studies have shown misalignment of LLMs with human value using expert-designed or agent-based emulated bias scenarios . |
| Approach: | They investigate whether large language models (LLMs) are misaligned with human values . they find no significant differences in understanding of HVSB between LLMs . |
| Outcome: | The results show that large language models do not have lower misalignment rates and attack success rates . the study also shows that smaller language models have the ability to explain HVSB . |
This is not a Disimprovement: Improving Negation Reasoning in Large Language Models via Prompt Engineering (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Negation reasoning remains a challenge for large language models (LLMs) a negative token attention score (NTAS) is introduced to quantify attention to negation words. |
| Approach: | They propose two genres of prompts that improve negation accuracy by up to 3.17% . they also propose a negative token attention score to quantify attention to negation words . |
| Outcome: | The proposed prompts improve negation accuracy and absolute accuracy by 3.17% over baselines. |
Likelihood-based Mitigation of Evaluation Bias in Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are widely used to evaluate natural language generation tasks as automated metrics. |
| Approach: | They propose to use LLMs to evaluate sentences with higher likelihoods and lower likelihoods to mitigate the likelihood bias. |
| Outcome: | The proposed method overrates sentences with higher likelihoods while underrating sentences with lower likelihoods. |
Mixed Signals: Decoding VLMs’ Reasoning and Underlying Bias in Vision-Language Conflict (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Vision-language models have demonstrated impressive performance by effectively integrating visual and textual information to solve complex tasks. |
| Approach: | They build upon existing benchmarks to create five datasets containing mismatched image-text pairs and examine how they reason over visual and textual data . |
| Outcome: | The proposed model reasoned over visual and textual data in real-world applications but not in the visual and visual descriptions. |
Constructing Your Model’s Value Distinction: Towards LLM Alignment with Anchor Words Tuning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a study of large language models (LLMs) shows that they can generate outputs that are honest, positive, harmless, etc. |
| Approach: | They propose a method that amplifies logits difference between positive and negative tokens . they propose to use the logits gap to generate positive and positive tokens after alignment . |
| Outcome: | The proposed method achieves effective alignment, but requires fewer computational resources compared to training-time alignment methods. |
Towards Low-Resource Alignment to Diverse Perspectives with Sparse Feedback (2025.findings-emnlp)
Copied to clipboard
| Challenge: | popular training paradigms for language models often assume there is one optimal answer for every query. |
| Approach: | They propose to enhance pluralistic alignment of language models using pluralistic decoding and model steering methods. |
| Outcome: | The proposed methods improve pluralistic alignment of language models in a low-resource setting . the proposed methods decrease false positives in several high-stakes tasks . |
Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race (2025.acl-long)
Copied to clipboard
| Challenge: | et al., 2012) show value-aligned language models exhibit stereotypes in word association tasks . ignoring racial nuances can perpetuate subtle biases in LMs . |
| Approach: | They propose a bias mitigation strategy that incentivizes representation of racial concepts in early model layers. |
| Outcome: | The proposed approach incentivizes representation of racial concepts in early model layers . it reduces implicit bias by reducing the number of ambiguous inputs, the authors show . |
Characterizing Positional Bias in Large Language Models: A Multi-Model Evaluation of Prompt Order Effects (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models can be influenced by various forms of biases, says a new study . positional bias affects how LLMs interpret and weigh information, the authors say . |
| Approach: | a new study examines the impact of positional bias on large language models . positional biased models prioritize items based on their position rather than content or quality . |
| Outcome: | a new study shows that LLMs prioritize items based on their position rather than content or quality . the positional bias affects how LLM interpret and weigh information, the authors say . |
Reasons to Reject? Aligning Language Models with Judgments (2024.findings-acl)
Copied to clipboard
| Challenge: | a new framework for aligning large language models with judgments is proposed to help with alignment . a framework that allows for fine-grained inappropriate content detection and correction based on judgments . large language model alignment is critical for making artificial intelligence a reliable ally for humanity . |
| Approach: | They propose a framework that allows for fine-grained inappropriate content detection and correction based on judgments. |
| Outcome: | The proposed framework beats the 175B DaVinci003 and improves on AlpacaEval using judgments. |