Large language models (LLMs) have demonstrated impressive capabilities in
various tasks using the in-context learning (ICL) paradigm. However, their
effectiveness is often compromised by inherent bias, leading to prompt
brittleness, i.e., sensitivity to design settings such as example selection,
order, and prompt formatting. Previous studies have addressed LLM bias through
external adjustment of model outputs, but the internal mechanisms that lead to
such bias remain unexplored. Our work delves into these mechanisms,
particularly investigating how feedforward neural networks (FFNs) and attention
heads result in the bias of LLMs. By Interpreting the contribution of
individual FFN vectors and attention heads, we identify the biased LLM
components that skew LLMs' prediction toward specific labels. To mitigate these
biases, we introduce UniBias, an inference-only method that effectively
identifies and eliminates biased FFN vectors and attention heads. Extensive
experiments across 12 NLP datasets demonstrate that UniBias significantly
enhances ICL performance and alleviates prompt brittleness of LLMs.

通过研究语言模型中前馈神经网络和注意力头的作用，我们识别出导致偏见的组件，并提出了一种名为 UniBias 的仅用于推理的方法，该方法能够有效地识别和消除偏见的前馈神经网络向量和注意力头，大量实验验证了 UniBias 显著提高了模型的性能和减轻了模型的敏感性。

UniBias：通过内部注意力和 FFN 调整揭示和减轻 LLM 的偏见

UniBias: Unveiling and Mitigating LLM Bias through Internal Attention  and FFN Manipulation

Prompting and in-context learning (ICL) have become efficient learning
paradigms for large language models (LLMs). However, LLMs suffer from prompt
brittleness and various bias factors in the prompt, including but not limited
to the formatting, the choice verbalizers, and the ICL examples. To address
this problem that results in unexpected performance degradation, calibration
methods have been developed to mitigate the effects of these biases while
recovering LLM performance. In this work, we first conduct a systematic
analysis of the existing calibration methods, where we both provide a unified
view and reveal the failure cases. Inspired by these analyses, we propose Batch
Calibration (BC), a simple yet intuitive method that controls the contextual
bias from the batched input, unifies various prior approaches, and effectively
addresses the aforementioned issues. BC is zero-shot, inference-only, and
incurs negligible additional costs. In the few-shot setup, we further extend BC
to allow it to learn the contextual bias from labeled data. We validate the
effectiveness of BC with PaLM 2-(S, M, L) and CLIP models and demonstrate
state-of-the-art performance over previous calibration baselines across more
than 10 natural language understanding and image classification tasks.

通过对现有校准方法的系统分析，我们提出了一种简单而直观的批量校准（BC）方法，它控制了批量输入的上下文偏差，统一了各种先前的方法，并有效解决了上述问题，这种方法是零 - shot、只有推理过程中存在，且额外成本极低。在少样本设置下，我们进一步扩展了 BC，使其能够从标记数据中学习上下文偏差，并且通过对 PaLM 2-(S, M, L) 和 CLIP 模型的验证，证明了 BC 的有效性，并在 10 多个自然语言理解和图像分类任务中展示了优于以往校准基线的最新表现。