HEIMAT, a HEurIstic-style autoMATic debiasing framework for LMs, effectively mitigates bias in different cultures while maintaining the model's natural language understanding (NLU) performance.
Abstract
Language models (LMs) often acquire various biases during pre-training and may express them in interactions, potentially causing social harm. Existing methods often rely on counterfactual augmentation or representation projection. These strategies remain limited in practice due to their high computational costs and difficulty in scaling to larger models. Additionally, many of these strategies require manual data annotation, narrowing their scope to specific cultures and bias categories. To overcome these limitations, we propose HEIMAT, a HEurIstic-style autoMATic debiasing framework for LMs. HEIMAT consists of two main steps: bias disclosure and debiasing fine-tuning. In the first step, it uses simple templates to construct heuristic prompts, which are applied to reveal model biases and generate corresponding context prompts. In the second step, it fine-tunes the model by minimizing the Jensen-Shannon divergence of predictions on these context prompts to reduce bias. Extensive experiments show that HEIMAT effectively mitigates bias in different cultures while maintaining the model's natural language understanding (NLU) performance.
It is proposed that persona-based evaluation can serve as a scalable diagnostic of what generative systems value and prioritize when depicting humanity, and that persona generations are far from neutral.
N. Corrêa, Rafaela Weber Mallmann, David Kaczér et al.· Artificial Intelligence Revi...· 0 citations
Large language models often repeatedly select the same answer even when many alternatives are plausible. Prior work treats this concentration as bias, but it does not distinguish stable model preferences from responses that depend on a particular prompt wording. We introduce a bias depth score that measures both how strongly a model prefers its top answer under direct prompting and whether that answer survives scenario reframing. Across 4,442 opinion prompts and four large language models, only about a quarter of the concentrated preferences survive reframing. We call these persistent cases Deep biases, and the remaining prompt-dependent cases Shallow biases. Our results show that Deep biases are more often inherited from pretraining and preserved through SFT. Under both continued fine-tuning and prompt-based debiasing for diversity, Deep biases are consistently harder to remove than Shallow biases. Bias depth therefore separates stable learned biases from prompt-wording artifacts that single-prompt metrics conflate. Code, models, and data are available at deepbias.github.io.
An Vo, Vy Tuong Dang, Khai-Nguyen Nguyen et al.· 0 citations
While Large language models (LLMs) incorporate user personalization signals to improve usability and helpfulness, they increasingly shift from providing balanced, informative responses toward optimizing for user satisfaction when conditioned on personal context such as conversation history, inferred preferences, and user profiles. Specifically, we identify three emerging risks: (1) irrelevant personalization, where models reference personal information in unnecessary contexts; (2) preference narrowing, where models reinforce informational echo chambers; and (3) sycophantic bias, where models agree excessively with user opinions. As a result, models may reference personal information in contexts where it is unnecessary, inadvertently collapse response diversity, or agree excessively with user opinions. Despite the growing use of personalization in AI assistants, there has been limited systematic evaluation of its potential side effects. To bridge this gap, we propose PRISK, a dynamic evaluation framework with automated data generation and tailored metrics that uncovers systematic limitations in current LLM personalization and how personalized information shapes its responses. Our empirical analysis across 13 LLMs demonstrates the presence of user profiles and retrieved memories consistently exacerbates biases, resulting in an average drop of 45.9% in irrelevant personalization, 41.7% in preference narrowing and 61.7% in sycophantic bias.
Yumeng Wang, Yu-Chen Wu, Cheng Qian et al.· 0 citations
This work finds that likelihood-trained TPMs can result in failed generations due to overly large corrections to the LM’s logits, and trains TPMs with LM-aligned objectives that better align with the LM token-probability space.
Hanzhang Liu, William Zhao, Zilei Shao et al.· 0 citations
This work investigates whether large language models (LLMs) can automatically adapt template-based bias datasets to specific domains using zero-shot prompting and shows that domain-adapted templates capture real-world bias patterns more faithfully than standard templates.
Tamara Quiroga, Felipe Bravo-Marquez, Valentin Barrière· ACM Transactions on Intellig...· 0 citations
Benevolence bias is identified and measure, a small but consistent tendency for aligned LLMs to lean toward the kinder, safer, more socially approved answer on value-laden survey questions, and is easy to diagnose and straightforward to fix.
Yuanzi Li, Jun-Hao Wang, Minghui Liu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
