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.

该研究引入了基于联合提示归属的反事实解释框架 XPrompt，旨在解释少数提示文本是如何共同影响大型语言模型（LLM）的完整生成，并通过定义和利用多个评估指标来展示我们框架的忠实度和效率。

XPrompt：通过联合提示归因解释大型语言模型的生成

XPrompt:Explaining Large Language Model's Generation via Joint Prompt  Attribution

In-context learning (ICL) is an astonishing emergent ability of large
language models (LLMs). By presenting a prompt that includes multiple
input-output pairs as examples and introducing a new query input, models can
generate the corresponding output. However, the performance of models heavily
relies on the quality of the input prompt when implementing in-context
learning. Biased or imbalanced input prompts can significantly degrade the
performance of language models. To address this issue, we introduce a
reweighted algorithm called RICL (Reweighted In-context Learning). This
algorithm fine-tunes language models using an unbiased validation set to
determine the optimal weight for each input-output example to approximate
unbiased in-context learning. Furthermore, we also introduce a low-cost
reweighted algorithm, a linear optimal weight approximation algorithm called
LARICL (Linear Approximation of Reweighted In-context Learning). This algorithm
requires minimal training cost while providing effective results. We prove the
convergence of our algorithm and validate its performance through experiments
conducted on a numerical dataset. The experimental findings reveal a
substantial improvement in comparison to benchmarks including the performance
of casual prompt-based in-context learning and the performance of a classic
fine-tuning method.

引入了一种重新加权的算法 RICL（Reweighted In-context Learning），并提出了一种低成本重新加权算法 LARICL（Linear Approximation of Reweighted In-context Learning），这些算法通过有效地优化输入提示来改善大语言模型（LLMs）的性能。