paper-with-me

Papers

How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?

2024-04-04 · Siye Wu, Jian Xie, Jiangjie Chen, Tinghui Zhu, Kai Zhang, Yanghua Xiao

By leveraging the retrieval of information from external knowledge databases, Large Language Models (LLMs) exhibit enhanced capabilities for accomplishing many knowledge-intensive tasks. However, due to the inherent flaws of current retrieval systems, there might exist irrelevant information within those retrieving top-ranked passages. In this work, we present a comprehensive investigation into the robustness of LLMs to different types of irrelevant information under various conditions. We initially introduce a framework to construct high-quality irrelevant information that ranges from semantically unrelated, partially related, and related to questions. Furthermore, our analysis demonstrates that the constructed irrelevant information not only scores highly on similarity metrics, being highly retrieved by existing systems, but also bears semantic connections to the context. Our investigation reveals that current LLMs still face challenges in discriminating highly semantically related information and can be easily distracted by these irrelevant yet misleading content. Besides, we also find that current solutions for handling irrelevant information have limitations in improving the robustness of LLMs to such distractions. All the resources are available on GitHub at https://github.com/Di-viner/LLM-Robustness-to-Irrelevant-Information.

📄 PDF Abstract BibTeX arXiv:2404.03302

Code (1)

di-viner/llm-robustness-to-irrelevant-information 공식 구현 pytorch

Tasks

Retrieval

Similar Papers 제목 키워드 기반

Ensemble Quantile Classifier

2019-10-28 · Yuanhao Lai, Ian McLeod

Both the median-based classifier and the quantile-based classifier are useful for discriminating high-dimensional data with heavy-tailed or skewed inputs. But these methods are restricted as they assign equal weight to e…

Text Categorization

Inlier-Centric Post-Training Quantization for Object Detection Models

2026-02-03 · Minsu Kim, Dongyeun Lee, Jaemyung Yu, Jiwan Hur 외 arxiv

Object detection is pivotal in computer vision, yet its immense computational demands make deployment slow and power-hungry, motivating quantization. However, task-irrelevant morphologies such as background clutter and s…

Object Detection

Text is All You Need for Vision-Language Model Jailbreaking

2026-01-31 · Yihang Chen, Zhao Xu, Youyuan Jiang, Tianle Zheng 외 arxiv

Large Vision-Language Models (LVLMs) are increasingly equipped with robust safety safeguards to prevent responses to harmful or disallowed prompts. However, these defenses often focus on analyzing explicit textual inputs…

Large Language Models are not Fair Evaluators

2023-05-29 · Peiyi Wang, Lei LI, Liang Chen, Zefan Cai 외

In this paper, we uncover a systematic bias in the evaluation paradigm of adopting large language models~(LLMs), e.g., GPT-4, as a referee to score and compare the quality of responses generated by candidate models. We f…

Language ModellingLarge Language ModelPosition

Type III Responses to Transient Inputs in Hybrid Nonlinear Neuron Models

2020-07-23

Experimental characterization of neuronal dynamics involves recording both of spontaneous activity patterns and of responses to transient and sustained inputs. While much theoretical attention has been devoted to the spo…

Vocal Bursts Type Prediction