How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?
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.
Code (1)
Tasks
RetrievalSimilar Papers 제목 키워드 기반
Ensemble Quantile Classifier
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 CategorizationInlier-Centric Post-Training Quantization for Object Detection Models
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 DetectionText is All You Need for Vision-Language Model Jailbreaking
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
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 ModelPositionType III Responses to Transient Inputs in Hybrid Nonlinear Neuron Models
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