Implicit sentiment analysis (ISA) presents significant challenges due to the absence of salient cue words. Previous methods have struggled with insufficient data and limited reasoning capabilities to infer underlying opinions. Integrating multi-task learning (MTL) with large language models (LLMs) offers the potential to enable models of varying sizes to reliably perceive and recognize genuine opinions in ISA. However, existing MTL approaches are constrained by two sources of uncertainty:data-level uncertainty, arising from hallucination problems in LLM-generated contextual information, andtask-level uncertainty, stemming from the varying capacities of models to process contextual information. To handle these uncertainties, we proposeMT-ISA, a novel MTL framework that enhances ISA by leveraging the generation and reasoning capabilities of LLMs through automatic weight learning (AWL). Specifically,MT-ISAconstructs auxiliary tasks using generative LLMs to supplement sentiment elements and incorporates automatic MTL to fully exploit auxiliary data. We introduce data-level and task-level AWL, which dynamically identify relationships and prioritize more reliable data and critical tasks, enabling models of varying sizes to adaptively learn fine-grained weights based on their reasoning capabilities. Three strategies are investigated for data-level AWL, which are integrated with homoscedastic uncertainty for task-level AWL. Extensive experiments reveal that models of varying sizes achieve an optimal balance between primary prediction and auxiliary tasks inMT-ISA. This underscores the effectiveness and adaptability of our approach.

Under the context of the increasing social demand for fine-grained sentiment analysis (SA), implicit sentiment analysis (ISA) poses a significant challenge owing to the absence of salient cue words in expressions. Thus, reliable reasoning is required to understand how sentiment is evoked, enabling the identification of implicit sentiments. In the era of large language models (LLMs), encoder-decoder (ED) LLMs have emerged as popular backbone models for SA applications, given their impressive text comprehension and reasoning capabilities across diverse tasks. In comparison, decoder-only (DO) LLMs exhibit superior natural language generation and in-context learning capabilities. However, their responses may contain misleading or inaccurate information. To accurately identify implicit sentiments with reliable reasoning, this study introduces a two-stage reasoning framework named Reasoning and Verification for Implicit Sentiment Analysis (RVISA), which leverages the generation ability of DO LLMs and reasoning ability of ED LLMs to train an enhanced reasoner. The framework involves three-hop reasoning prompting to explicitly furnish sentiment elements as cues. The generated rationales are then used to fine-tune an ED LLM into a skilled reasoner. Additionally, we develop a straightforward yet effective answer-based verification mechanism to ensure the reliability of reasoning learning. Evaluation of the proposed method on two benchmark datasets demonstrates that it achieves state-of-the-art performance in ISA.