Conversational stance detection, which aims to identify stances within conversation threads, has become a research hotspot recently. As the number of dialogue turns increases and the conversation content becomes more complex, existing methods that simply incorporate conversational context are insufficient to effectively capture the nuanced information necessary for accurate stance detection. To address this issue, we introduce a Multi-agent Reasoning Graph Knowledge Distillation (MRGKD) framework, leveraging conversational reasoning among multiple Large Language Models (LLMs) into smaller language models. Specifically, we first construct a multi-agent reasoning graph to infer implicit logical relationships within the conversational history from the diverse perspectives of multiple LLMs. To fully leverage the in-context learning capabilities of LLMs, we design a reasoning knowledge editing mechanism that internalizes new information by aligning the output distribution of smaller language models with both the conversational history and the knowledge derived from the multi-agent reasoning graph. Additionally, we incorporate a contrastive loss to distinguish between correct and incorrect reasoning, alongside a stance detection loss, to fine-tune the smaller language models. This approach not only ensures the accurate acquisition of logical knowledge but also preserves the integrity of the conversational history. Experiments conducted on two public datasets demonstrate that our MRGKD significantly outperforms all baselines.

In this paper, we leverage in-context learning (ICL) paradigm to handle few-shot aspect-based sentiment analysis (ABSA). Previous works first rank candidate examples by some metrics and then independently retrieve examples similar to test samples. However, their effectiveness may be discounted because of two limitations: in-context example redundancy and example preference misalignment between retriever and LLM. To alleviate them, we propose a novel framework that sequentially retrieves in-context examples. It not only considers which example is useful for the test sample but also prevents its information from being duplicated by already retrieved examples. Subsequently, we exploit the rewards of LLMs on retrieved in-context examples to optimize parameters for bridging preference gaps. Experiments on four ABSA datasets show that our framework is significantly superior to previous works.

Existing approaches for sarcasm detection are mainly based on supervised learning, in which the promising performance largely depends on a considerable amount of labeled data or extra information. In the real world scenario, however, the abundant labeled data or extra information requires high labor cost, not to mention that sufficient annotated data is unavailable in many low-resource conditions. To alleviate this dilemma, we investigate sarcasm detection from an unsupervised perspective, in which we explore a masking and generation paradigm in the context to extract the context incongruities for learning sarcastic expression. Further, to improve the feature representations of the sentences, we use unsupervised contrastive learning to improve the sentence representation based on the standard dropout. Experimental results on six perceived sarcasm detection benchmark datasets show that our approach outperforms baselines. Simultaneously, our unsupervised method obtains comparative performance with supervised methods for the intended sarcasm dataset.