XPrompt:Explaining Large Language Model's Generation via Joint Prompt Attribution
Large Language Models (LLMs) have demonstrated impressive performances in complex text generation tasks. However, the contribution of the input prompt to the generated content still remains obscure to humans, underscoring the necessity of elucidating and explaining the causality between input and output pairs. Existing works for providing prompt-specific explanation often confine model output to be classification or next-word prediction. Few initial attempts aiming to explain the entire language generation often treat input prompt texts independently, ignoring their combinatorial effects on the follow-up generation. In this study, we introduce a counterfactual explanation framework based on joint prompt attribution, XPrompt, which aims to explain how a few prompt texts collaboratively influences the LLM's complete generation. Particularly, we formulate the task of prompt attribution for generation interpretation as a combinatorial optimization problem, and introduce a probabilistic algorithm to search for the casual input combination in the discrete space. We define and utilize multiple metrics to evaluate the produced explanations, demonstrating both faithfulness and efficiency of our framework.
Code (0)
등록된 구현이 없습니다.
Tasks
Combinatorial OptimizationcounterfactualCounterfactual ExplanationText GenerationSimilar Papers 제목 키워드 기반
XPrompt: Exploring the Extreme of Prompt Tuning
Prompt tuning learns soft prompts to condition frozen Pre-trained Language Models (PLMs) for performing downstream tasks in a parameter-efficient manner. While prompt tuning has gradually reached the performance level of…
SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Data
Text-to-SQL aims to automate the process of generating SQL queries on a database from natural language text. In this work, we propose "SQLPrompt", tailored to improve the few-shot prompting capabilities of Text-to-SQL fo…
In-Context LearningText to SQLText-To-SQLELIXIR: Efficient and LIghtweight model for eXplaIning Recommendations
Collaborative filtering drives many successful recommender systems but struggles with fine-grained user-item interactions and explainability. As users increasingly seek transparent recommendations, generating textual exp…
Collaborative FilteringText GenerationFrom Passive Perception to Active Memory: A Weakly Supervised Image Manipulation Localization Framework Driven by Coarse-Grained Annotations
Image manipulation localization (IML) faces a fundamental trade-off between minimizing annotation cost and achieving fine-grained localization accuracy. Existing fully-supervised IML methods depend heavily on dense pixel…
Image Manipulation LocalizationKnowledge DistillationExplaining the Reasoning of Large Language Models Using Attribution Graphs
Large language models (LLMs) exhibit remarkable capabilities, yet their reasoning remains opaque, raising safety and trust concerns. Attribution methods, which assign credit to input features, have proven effective for e…
Decision Making