BEFT: Bias-Efficient Fine-Tuning of Language Models in Low-Data Regimes
Fine-tuning the bias terms of large language models (LLMs) has the potential to achieve unprecedented parameter efficiency while maintaining competitive performance, particularly in low-data regimes. However, the link between fine-tuning different bias terms (i.e., $\boldsymbol{b}_q$, $\boldsymbol{b}_k$, and $\boldsymbol{b}_v$ in the query, key, or value projections) and downstream performance remains largely unclear to date. In this paper, we investigate the link between fine-tuning $\boldsymbol{b}_q$, $\boldsymbol{b}_k$, and $\boldsymbol{b}_v$ with the performance of the downstream task. Our key finding is that directly fine-tuning $\boldsymbol{b}_v$ generally leads to higher downstream performance in low-data regimes, in comparison to $\boldsymbol{b}_q$ and $\boldsymbol{b}_k$. We extensively evaluate this unique property across a wide range of LLMs spanning encoder-only and decoder-only architectures up to 6.7B parameters (including bias-free LLMs). Our results provide strong evidence for the effectiveness of directly fine-tuning $\boldsymbol{b}_v$ across various downstream tasks. The implementation code is available at https://github.com/whubaichuan/BEFT.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
BERAG: Bayesian Ensemble Retrieval-Augmented Generation for Knowledge-based Visual Question Answering
A common approach to question answering with retrieval-augmented generation (RAG) is to concatenate documents into a single context and pass it to a language model to generate an answer. While simple, this strategy can o…
Visual Question AnsweringRobustDebias: Debiasing Language Models using Distributionally Robust Optimization
Pretrained language models have been shown to exhibit biases and social stereotypes. Prior work on debiasing these models has largely focused on modifying embedding spaces during pretraining, which is not scalable for la…
Gender-tuning: Empowering Fine-tuning for Debiasing Pre-trained Language Models
Recent studies have revealed that the widely-used Pre-trained Language Models (PLMs) propagate societal biases from the large unmoderated pre-training corpora. Existing solutions require debiasing training processes and …
Language ModelingLanguage ModellingMasked Language ModelingBitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models
We show that with small-to-medium training data, fine-tuning only the bias terms (or a subset of the bias terms) of pre-trained BERT models is competitive with (and sometimes better than) fine-tuning the entire model. Fo…
Language ModelingLanguage Modellingparameter-efficient fine-tuningOn Transferability of Bias Mitigation Effects in Language Model Fine-Tuning
Fine-tuned language models have been shown to exhibit biases against protected groups in a host of modeling tasks such as text classification and coreference resolution. Previous works focus on detecting these biases, re…
coreference-resolutionCoreference ResolutionFairnessHate Speech Detection+6