RVISA：面向隐式情感分析的推理与验证
RVISA: Reasoning and Verification for Implicit Sentiment Analysis
AI总结：
针对隐式情感缺乏显著提示词的问题，提出 RVISA 两阶段框架，结合 DO LLM 生成三跳推理理据、微调 ED LLM 并加入验证机制，在两个基准上达到 SOTA。
摘要：
随着社会对细粒度情感分析（SA）的需求不断增长，隐式情感分析（ISA）因表达中缺乏显著提示词而构成重大挑战。它需要可靠的推理来理解情感是如何被唤起的，从而确定隐式情感。在大语言模型（LLM）时代，鉴于 Encoder-Decoder（ED，编码器—解码器）LLM 在多种任务中展现出令人印象深刻的文本理解与推理能力，它们已被广泛用作 SA 应用的骨干模型。另一方面，Decoder-only（DO，仅解码器）LLM 表现出更强的自然语言生成和上下文学习能力。然而，它们的回答可能包含误导性或不准确的信息。为了通过可靠推理识别隐式情感，本研究提出 RVISA，这是一个两阶段推理框架，利用 DO LLM 的生成能力和 ED LLM 的推理能力来训练一个增强型推理器。具体而言，我们采用三跳推理提示，显式提供情感元素作为线索。生成的理据被用于微调 ED LLM，使其成为熟练的推理器。此外，我们开发了一种简单而有效的验证机制，以确保推理学习的可靠性。我们在两个基准数据集上评估了所提出的方法，并在 ISA 性能上取得了当前最优结果。
英文摘要：
With an increasing social demand for fine-grained sentiment analysis (SA), implicit sentiment analysis (ISA) poses a significant challenge with the absence of salient cue words in expressions. It necessitates reliable reasoning to understand how the sentiment is aroused and thus determine implicit sentiments. In the era of Large Language Models (LLMs), Encoder-Decoder (ED) LLMs have gained popularity to serve as backbone models for SA applications, considering impressive text comprehension and reasoning ability among diverse tasks. On the other hand, Decoder-only (DO) LLMs exhibit superior natural language generation and in-context learning capabilities. However, their responses may contain misleading or inaccurate information. To identify implicit sentiment with reliable reasoning, this study proposes RVISA, a two-stage reasoning framework that harnesses the generation ability of DO LLMs and the reasoning ability of ED LLMs to train an enhanced reasoner. Specifically, we adopt three-hop reasoning prompting to explicitly furnish sentiment elements as cues. The generated rationales are utilized to fine-tune an ED LLM into a skilled reasoner. Additionally, we develop a straightforward yet effective verification mechanism to ensure the reliability of the reasoning learning. We evaluated the proposed method on two benchmark datasets and achieved state-of-the-art results in ISA performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
