Structured sentiment analysis using few-shot prompting of an ensemble of LLMs

This paper describes our participation in RuOpinionNE-2024 shared task (Loukachevitch et al., 2025).The objective of this task is to extract opinion tuples of the form <holder, target, polarity expression, polarity> from news texts in Russian.We approached this task with few-shot prompting of super large language models (LLMs).The quality of LLMs' predictions was improved in two ways.In the first stage we used prompts with examples which text embeddings were similar to that of the target text.In the second stage we augmented prompts with answers of LLMs from the previous stage, achieving the second-best F1 score in the competition in the post-evaluation stage.Our results show that the addition of answer suggestions to the prompt is particularly useful if they provide novel and variable information.