Benchmarking and Pushing the Multi-Bias Elimination Boundary of LLMs via Causal Effect Estimation-guided Debiasing

• URL: http://arxiv.org/abs/2505.16522v2
• Date: Tue, 27 May 2025 02:22:22 GMT
• Title: Benchmarking and Pushing the Multi-Bias Elimination Boundary of LLMs via Causal Effect Estimation-guided Debiasing
• Authors: Zhouhao Sun, Zhiyuan Kan, Xiao Ding, Li Du, Yang Zhao, Bing Qin, Ting Liu,
• Abstract summary: Current large language models (LLMs) may still utilize bias during inference, leading to the poor generalizability of LLMs.<n>We propose a multi-bias benchmark where each piece of data contains five types of biases.<n>We show that CMBE can effectively eliminate multiple types of bias simultaneously to enhance the generalizability of LLMs.
• Score: 41.90664134611629
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite significant progress, recent studies have indicated that current large language models (LLMs) may still utilize bias during inference, leading to the poor generalizability of LLMs. Some benchmarks are proposed to investigate the generalizability of LLMs, with each piece of data typically containing one type of controlled bias. However, a single piece of data may contain multiple types of biases in practical applications. To bridge this gap, we propose a multi-bias benchmark where each piece of data contains five types of biases. The evaluations conducted on this benchmark reveal that the performance of existing LLMs and debiasing methods is unsatisfying, highlighting the challenge of eliminating multiple types of biases simultaneously. To overcome this challenge, we propose a causal effect estimation-guided multi-bias elimination method (CMBE). This method first estimates the causal effect of multiple types of biases simultaneously. Subsequently, we eliminate the causal effect of biases from the total causal effect exerted by both the semantic information and biases during inference. Experimental results show that CMBE can effectively eliminate multiple types of bias simultaneously to enhance the generalizability of LLMs.

Related papers

• Benchmarking Debiasing Methods for LLM-based Parameter Estimates [7.790904593265873]
  Large language models (LLMs) offer an inexpensive yet powerful way to annotate text, but are often inconsistent when compared with experts.<n>To mitigate this bias, researchers have developed debiasing methods such as Design-based Supervised Learning (Supervised Learning) and Prediction-Powered Inference (PPI)<n>We compare DSL and PPI across a range of tasks, finding that although both achieve low bias with large datasets, DSL often outperforms PPI on bias reduction and empirical efficiency.
  arXiv  Detail & Related papers  (2025-06-11T11:37:02Z)
• Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training [57.03005244917803]
  Large language models (LLMs) often fail on out-of-distribution (OOD) samples due to spurious correlations acquired during pre-training.<n>Here, we aim to mitigate such spurious correlations through causality-aware post-training (CAPT)<n> Experiments on the formal causal inference benchmark CLadder and the logical reasoning dataset PrOntoQA show that 3B-scale language models fine-tuned with CAPT can outperform both traditional SFT and larger LLMs on in-distribution (ID) and OOD tasks.
  arXiv  Detail & Related papers  (2025-06-11T06:30:28Z)
• No LLM is Free From Bias: A Comprehensive Study of Bias Evaluation in Large Language models [0.9620910657090186]
  Large Language Models (LLMs) have increased the performance of different natural language understanding as well as generation tasks.<n>Although LLMs have breached the state-of-the-art performance in various tasks, they often reflect different forms of bias present in the training data.<n>We provide a unified evaluation of benchmarks using a set of representative LLMs that cover different forms of biases starting from physical characteristics to socio-economic categories.
  arXiv  Detail & Related papers  (2025-03-15T03:58:14Z)
• Preference Leakage: A Contamination Problem in LLM-as-a-judge [69.96778498636071]
  Large Language Models (LLMs) as judges and LLM-based data synthesis have emerged as two fundamental LLM-driven data annotation methods.<n>In this work, we expose preference leakage, a contamination problem in LLM-as-a-judge caused by the relatedness between the synthetic data generators and LLM-based evaluators.
  arXiv  Detail & Related papers  (2025-02-03T17:13:03Z)
• How far can bias go? -- Tracing bias from pretraining data to alignment [54.51310112013655]
  This study examines the correlation between gender-occupation bias in pre-training data and their manifestation in LLMs.<n>Our findings reveal that biases present in pre-training data are amplified in model outputs.
  arXiv  Detail & Related papers  (2024-11-28T16:20:25Z)
• Causal-Guided Active Learning for Debiasing Large Language Models [40.853803921563596]
  Current generative large language models (LLMs) may still capture dataset biases and utilize them for generation. Previous prior-knowledge-based debiasing methods and fine-tuning-based debiasing methods may not be suitable for current LLMs. We propose a casual-guided active learning framework, which utilizes LLMs itself to automatically and autonomously identify informative biased samples and induce the bias patterns.
  arXiv  Detail & Related papers  (2024-08-23T09:46:15Z)
• CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models [58.57987316300529]
  Large Language Models (LLMs) are increasingly deployed to handle various natural language processing (NLP) tasks.<n>To evaluate the biases exhibited by LLMs, researchers have recently proposed a variety of datasets.<n>We propose CEB, a Compositional Evaluation Benchmark that covers different types of bias across different social groups and tasks.
  arXiv  Detail & Related papers  (2024-07-02T16:31:37Z)
• UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation [12.04811490937078]
  We investigate how feedforward neural networks (FFNs) and attention heads result in the bias of large language models (LLMs)<n>To mitigate these biases, we introduce UniBias, an inference-only method that effectively identifies and eliminates biased FFN vectors and attention heads.
  arXiv  Detail & Related papers  (2024-05-31T03:59:15Z)
• Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMs [6.090496490133132]
  We propose Reinforcement Learning from Multi-role Debates as Feedback (RLDF), a novel approach for bias mitigation replacing human feedback in traditional RLHF. We utilize LLMs in multi-role debates to create a dataset that includes both high-bias and low-bias instances for training the reward model in reinforcement learning.
  arXiv  Detail & Related papers  (2024-04-15T22:18:50Z)
• Mitigating Biases of Large Language Models in Stance Detection with Counterfactual Augmented Calibration [43.02857908228108]
  Large language models (LLMs) have demonstrated significant advancements across various natural language processing tasks including stance detection.<n>Their performance in stance detection is limited by biases and spurious correlations inherent due to their data-driven nature.<n>We propose a Counterfactual Augmented Network (FACTUAL), which a novel calibration network is devised to calibrate potential bias in the stance prediction of LLMs.
  arXiv  Detail & Related papers  (2024-02-22T05:17:49Z)
• SMoA: Sparse Mixture of Adapters to Mitigate Multiple Dataset Biases [27.56143777363971]
  We propose a new debiasing method Sparse Mixture-of-Adapters (SMoA), which can mitigate multiple dataset biases effectively and efficiently. Experiments on Natural Language Inference and Paraphrase Identification tasks demonstrate that SMoA outperforms full-finetuning, adapter tuning baselines, and prior strong debiasing methods.
  arXiv  Detail & Related papers  (2023-02-28T08:47:20Z)
• Counterfactual Maximum Likelihood Estimation for Training Deep Networks [83.44219640437657]
  Deep learning models are prone to learning spurious correlations that should not be learned as predictive clues. We propose a causality-based training framework to reduce the spurious correlations caused by observable confounders. We conduct experiments on two real-world tasks: Natural Language Inference (NLI) and Image Captioning.
  arXiv  Detail & Related papers  (2021-06-07T17:47:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.