惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

MyScale Blog
MyScale Blog
F
Fortinet All Blogs
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
D
Docker
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
爱范儿
爱范儿
V
Visual Studio Blog
Last Week in AI
Last Week in AI
WordPress大学
WordPress大学
aimingoo的专栏
aimingoo的专栏
小众软件
小众软件
L
LangChain Blog
Vercel News
Vercel News
阮一峰的网络日志
阮一峰的网络日志
IT之家
IT之家
P
Proofpoint News Feed
博客园_首页
D
DataBreaches.Net
T
The Blog of Author Tim Ferriss
The GitHub Blog
The GitHub Blog
酷 壳 – CoolShell
酷 壳 – CoolShell
C
Check Point Blog
Engineering at Meta
Engineering at Meta
Microsoft Azure Blog
Microsoft Azure Blog

cs.LG updates on arXiv.org

Memory-Guided Trust-Region Bayesian Optimization (MG-TuRBO) for High Dimensions EngageTriBoost: Predictive Modeling of User Engagement in Digital Mental Health Intervention Using Explainable Machine Learning Reservoir observer enhanced with residual calibration and attention mechanism Efficient RL Training for LLMs with Experience Replay Wireless Communication Enhanced Value Decomposition for Multi-Agent Reinforcement Learning Adversarial Sensor Errors for Safe and Robust Wind Turbine Fleet Control IKKA: Inversion Classification via Critical Anomalies for Robust Visual Servoing Adaptive Simulation Experiment for LLM Policy Optimization EvoLen: Evolution-Guided Tokenization for DNA Language Model Smartwatch-Based Sitting Time Estimation in Real-World Office Settings Structural Evaluation Metrics for SVG Generation via Leave-One-Out Analysis Loom: A Scalable Analytical Neural Computer Architecture Spectral Geometry of LoRA Adapters Encodes Training Objective and Predicts Harmful Compliance Finite-Sample Analysis of Nonlinear Independent Component Analysis:Sample Complexity and Identifiability Bounds How does Chain of Thought decompose complex tasks? Uncertainty-Aware Transformers: Conformal Prediction for Language Models Adaptive Candidate Point Thompson Sampling for High-Dimensional Bayesian Optimization Using Synthetic Data for Machine Learning-based Childhood Vaccination Prediction in Narok, Kenya Delve into the Applicability of Advanced Optimizers for Multi-Task Learning Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning Multi-Agent Decision-Focused Learning via Value-Aware Sequential Communication Predictive Entropy Links Calibration and Paraphrase Sensitivity in Medical Vision-Language Models Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning Modality-Aware Zero-Shot Pruning and Sparse Attention for Efficient Multimodal Edge Inference The nextAI Solution to the NeurIPS 2023 LLM Efficiency Challenge Feature-Label Modal Alignment for Robust Partial Multi-Label Learning Integrated electro-optic attention nonlinearities for transformers Toward World Models for Epidemiology Tracing the Chain: Deep Learning for Stepping-Stone Intrusion Detection Batch Distillation Data for Developing Machine Learning Anomaly Detection Methods
Attention Speaks Volumes: Localizing and Mitigating Bias ...
Rishabh Adiga, Besmira Nushi, Varun Chandrasekaran · 2024-10-30 · via cs.LG updates on arXiv.org

We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context for preference. Most approaches for bias mitigation focus on either post-hoc analysis or data augmentation. However, these are transient solutions, without addressing the root cause: the model itself. Numerous prior works show the influence of the attention module towards steering generations. We believe that analyzing attention is also crucial for understanding bias, as it provides insight into how the LLM distributes its focus across different entities and how this contributes to biased decisions. To this end, we first introduce a metric to quantify the LLM's preference for one entity over another. We then propose $\texttt{ATLAS}$ (Attention-based Targeted Layer Analysis and Scaling), a technique to localize bias to specific layers of the LLM by analyzing attention scores and then reduce bias by scaling attention in these biased layers. To evaluate our method, we conduct experiments across 3 datasets (BBQ, Crows-Pairs, and WinoGender) using $\texttt{GPT-2 XL}$ (1.5B), $\texttt{GPT-J}$ (6B), $\texttt{LLaMA-2}$ (7B) and $\texttt{LLaMA-3}$ (8B). Our experiments demonstrate that bias is concentrated in the later layers, typically around the last third. We also show how $\texttt{ATLAS}$ effectively mitigates bias through targeted interventions without compromising downstream performance and an average increase of only 0.82% in perplexity when the intervention is applied. We see an average improvement of 0.28 points in the bias score across all the datasets.