The rapid advancement of large language models (LLMs) has revitalised research in Emotion Recognition in Conversation (ERC). However, existing LLM-based ERC approaches operate solely on textual input, whereas MLLM-based emotion recognition methods in non-conversational scenarios typically perform only basic multimodal fusion and fail to consider speaker-sensitive contextual dependencies, which limits their performance on ERC tasks. To integrate multimodal cues effectively and address their limitations in handling contextual dependencies, we propose a novel LLM-based framework, Causal-ERC, which captures context representations within each modality and incorporates them into the LLM. Moreover, experimental results show that LLMs perform poorly on long conversations. To improve LLMs' ability to model long conversations, we adjust corresponding causal prompts according to the causal type of each utterance. Experiments on two benchmark MERC datasets demonstrate that our Causal-ERC framework consistently outperforms existing state-of-the-art approaches and improves LLM's performance in long-context scenarios.

Argument generation is a fundamental NLP task that aims to automatically produce persuasive arguments.Effective human argumentation is inherently complex and multifaceted, integrating argumentative strategies, appropriate styles, and adaptation to target audiences, etc.However, existing studies focus on limited control signals such as topic, stance, or key aspects, failing to capture this complexity.As LLMs advance, the lack of benchmarks evaluating multifaceted argumentative control becomes a critical bottleneck.To address this, we introduce ArgGenBench, a novel benchmark containing complex instructions that integrate multi-dimensional control, including topic, stance, length, style, strategy, audience, and key points.Extensive evaluation across 15 LLMs reveals significant limitations: even the best-performing model achieves only 42.7% win rate against human-verified references.These results highlight the challenge of controlled argument generation and establish ArgGenBench as a rigorous testbed for developing more capable systems.

Bojun Jin, Jianzhu Bao, Yufang Hou, Yang Sun, Yice Zhang, Huajie Wang, Bin Liang, Ruifeng Xu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Recently developed large language models (LLMs) have presented promising new avenues to address data scarcity in low-resource scenarios.In few-shot aspect-based sentiment analysis (ABSA), previous efforts have explored data augmentation techniques, which prompt LLMs to generate new samples by modifying existing ones.However, these methods fail to produce adequately diverse data, impairing their effectiveness.Additionally, some studies apply incontext learning for ABSA by using specific instructions and a few selected examples as prompts.Though promising, LLMs often yield labels that deviate from task requirements.To overcome these limitations, we propose DS 2 -ABSA, a dual-stream data synthesis framework targeted for few-shot ABSA.It leverages LLMs to synthesize data from two complementary perspectives: key-point-driven and instancedriven, which effectively generate diverse and high-quality ABSA samples in low-resource settings.Furthermore, a label refinement module is integrated to improve the synthetic labels.Extensive experiments demonstrate that DS 2 -ABSA significantly outperforms previous fewshot ABSA solutions and other LLM-oriented data generation methods.

Jingqian Zhao, Bingbing Wang, Geng Tu, Yice Zhang, Qianlong Wang, Bin Liang, Jing Li, Ruifeng Xu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

The advancement of Argument Mining (AM) is hindered by a critical bottleneck: the scarcity of structure-annotated datasets, which are expensive to create manually.Inspired by recent successes in synthetic data generation across various NLP tasks, this paper explores methodologies for LLMs to generate synthetic data for AM.We investigate two complementary synthesis perspectives: a quality-oriented synthesis approach, which employs structure-aware paraphrasing to preserve annotation quality, and a diversity-oriented synthesis approach, which generates novel argumentative texts with diverse topics and argument structures.Experiments on three datasets show that augmenting original training data with our synthetic data, particularly when combining both quality-and diversity-oriented instances, significantly enhances the performance of existing AM models, both in full-data and low-resource settings.Moreover, the positive correlation between synthetic data volume and model performance highlights the scalability of our methods.

Recent efforts leverage knowledge distillation techniques to develop lightweight and practical sentiment analysis models.These methods are grounded in human-written instructions and large-scale user texts.Despite the promising results, two key challenges remain: (1) manually written instructions are limited in diversity and quantity, making them insufficient to ensure comprehensive coverage of distilled knowledge; (2) large-scale user texts incur high computational cost, hindering the practicality of these methods.To this end, we introduce COMPEFFDIST, a comprehensive and efficient distillation framework for sentiment analysis.Our framework consists of two key modules: attribute-based automatic instruction construction and difficulty-based data filtering, which correspondingly tackle the aforementioned challenges.Applying our method across multiple model series (Llama-3, Qwen-3, and Gemma-3), we enable 3B student models to match the performance of 20x larger teacher models on most tasks.In addition, our approach greatly outperforms baseline methods in data efficiency, attaining the same performance level with only 10% of the data.All codes are available at https://github.com/ HITSZ-HLT/COMPEFFDIST.

This paper explores targeted distillation methods for sentiment analysis 1 , aiming to build compact and practical models that preserve strong and generalizable sentiment analysis capabilities.To this end, we conceptually decouple the distillation target into knowledge and alignment and accordingly propose a two-stage distillation framework.Moreover, we introduce SENTIBENCH, a comprehensive and systematic sentiment analysis benchmark that covers a diverse set of tasks across 12 datasets.We evaluate a wide range of models on this benchmark.Experimental results show that our approach substantially enhances the performance of compact models across diverse sentiment analysis tasks, and the resulting models demonstrate strong generalization to unseen tasks, showcasing robust competitiveness against existing small-scale models.2 1. collect a large and diverse set of user texts. construct large-scale distillation corpus.4. optimize student model using two-stage approach.Distillation

Multimodal Emotion Recognition in Conversations (MERC) aims to detect emotions expressed in each utterance within conversational videos. Graph-based methods are widely employed in MERC due to their superiority in modeling intricate speaker-sensitive and context-sensitive dependencies in conversations. Despite promising advancements made, existing graph-based methods primarily suffer from two inherent issues due to their reliance on manually predefined graph structures: structural redundancy, which burdens models with irrelevant noise aggregation, and insufficient connections, which results in a lack of cross-modal contextual cues. To address the above issues, we propose a novel graph structure learning framework for MERC, which comprises two key components: Context-aware Graph Sparsification (CGS) and Implicit Graph Relation Mining (IGR). CGS employs an edge selection network to refine the manually predefined graph, filtering out noisy information caused by structural redundancy. IGR explores potential connections that are beneficial for emotional reasoning. Experimental results on two datasets show that our proposed framework significantly improves the performance of graph-based methods in MERC.

Generative methods tackle Multi-Label Classification (MLC) by autoregressively generating label sequences. These methods excel at modeling label correlations and have achieved outstanding performance. However, a key challenge is determining the order of labels, as empirical findings indicate the significant impact of different orders on model learning and inference. Previous works adopt static label-ordering methods, assigning a unified label order for all samples based on label frequencies or co-occurrences. Nonetheless, such static methods neglect the unique semantics of each sample. More critically, these methods can cause the model to rigidly memorize training order, resulting in missing labels during inference. In light of these limitations, this paper proposes a dynamic label-order learning approach that adaptively learns a label order for each sample. Specifically, our approach adopts a difficulty-prioritized principle and iteratively constructs the label sequence based on the sample s semantics. To reduce the additional cost incurred by label-order learning, we use the same SEQ2SEQ model for label-order learning and MLC learning and introduce a unified loss function for joint optimization. Extensive experiments on public datasets reveal that our approach greatly outperforms previous methods. We will release our code at https: //github.com/KagamiBaka/DLOL.

Aspect Sentiment Quad Prediction (ASQP) aims to predict all quads (aspect term, aspect category, opinion term, sentiment polarity) for a given review, which is the most representative and challenging task in aspect-based sentiment analysis.A key challenge in the ASQP task is the scarcity of labeled data, which limits the performance of existing methods.To tackle this issue, we propose a self-training framework with a pseudo-label scorer, wherein a scorer assesses the match between reviews and their pseudo-labels, aiming to filter out mismatches and thereby enhance the effectiveness of selftraining.We highlight two critical aspects to ensure the scorer's effectiveness and reliability: the quality of the training dataset and its model architecture.To this end, we create a humanannotated comparison dataset and train a generative model on it using ranking-based objectives.Extensive experiments on public ASQP datasets reveal that using our scorer can greatly and consistently improve the effectiveness of self-training.Moreover, we explore the possibility of replacing humans with large language models for comparison dataset annotation, and experiments demonstrate its feasibility.1

Aspect-Based Sentiment Analysis (ABSA) aims to recognize fine-grained sentiments and opinions of users, which is a pivotal problem in sentiment analysis. ABSA research generally involves four fundamental sentiment elements: aspect term, opinion term, aspect category, and sentiment polarity. The core challenge of ABSA lies in effectively modeling the relations between aspect and opinion terms, as these relations are crucial for accurately determining aspect categories and sentiment polarities. Consequently, researchers develop various modules to model these relations, attaining outstanding performances. Recently, generative approaches have attracted increasing attention in ABSA due to their capacity to handle various ABSA tasks in a unified manner. However, existing generative approaches do not exploit these relations, potentially limiting their performance. In this paper, we introduce two novel relation modules: Relation Supervision Module (RSM) and Relation Prompt Module (RPM) for generative ABSA approaches. These modules enhance the relation modeling capability of generative models at both encoding and decoding stages. Extensive experiments on three benchmarks demonstrate that the proposed modules significantly improve the performance of existing generative approaches.

Recent efforts have endeavored to employ the sequence-to-sequence (Seq2Seq) model in Information Extraction (IE) due to its potential to tackle multiple IE tasks in a unified manner.Under this formalization, multiple structured objects are concatenated as the target sequence in a predefined order.However, structured objects, by their nature, constitute an unordered set.Consequently, this formalization introduces a potential order bias, which can impair model learning.Targeting this issue, this paper proposes a set learning approach that considers multiple permutations of structured objects to optimize set probability approximately.Notably, our approach does not require any modifications to model structures, making it easily integrated into existing generative IE frameworks.Experiments show that our method consistently improves existing frameworks on vast tasks and datasets.

Aspect Sentiment Triplet Extraction (ASTE) is an important task in sentiment analysis, aiming to extract aspect-level opinions and sentiments from user-generated reviews.The fine-grained nature of ASTE incurs a high annotation cost, while the scarcity of annotated data limits the performance of existing methods.This paper exploits data augmentation to address this issue.Traditional augmentation methods typically modify the input sentences of existing samples via heuristic rules or language models, which have shown success in text classification tasks.However, applying these methods to fine-grained tasks like ASTE poses challenges in generating diverse augmented samples while maintaining alignment between modified sentences and origin labels.Therefore, this paper proposes a target-to-source augmentation approach for ASTE.Our approach focuses on learning a generator that can directly generate new sentences based on labels and syntactic templates.With this generator, we can generate a substantial number of diverse augmented samples by mixing labels and syntactic templates from different samples.Besides, to ensure the quality of the generated sentence, we introduce fluency and alignment discriminators to provide feedback on the generated sentence and then use this feedback to optimize the generator via a reinforcement learning framework.Experiments demonstrate that our approach significantly enhances the performance of existing ASTE models. 1

Aspect Sentiment Triplet Extraction (ASTE) aims to extract the aspect terms along with the corresponding opinion terms and the expressed sentiments in the review, which is an important task in sentiment analysis.Previous research efforts generally address the ASTE task in an endto-end fashion through the table-filling formalization, in which the triplets are represented by a two-dimensional (2D) table of word-pair relations.Under this formalization, a term-level relation is decomposed into multiple independent word-level relations, which leads to relation inconsistency and boundary insensitivity in the face of multi-word aspect terms and opinion terms.To overcome these issues, we propose Boundary-Driven Table-Filling (BDTF), which represents each triplet as a relation region in the 2D table and transforms the ASTE task into detection and classification of relation regions.We also notice that the quality of the table representation greatly affects the performance of BDTF.Therefore, we develop an effective relation representation learning approach to learn the table representation, which can fully exploit both word-to-word interactions and relation-torelation interactions.Experiments on several public benchmarks show that the proposed approach achieves state-of-the-art performances 1 .

Argument pair extraction (APE) aims to extract interactive argument pairs from two passages of a discussion.Previous work studied this task in the context of peer review and rebuttal, and decomposed it into a sequence labeling task and a sentence relation classification task.However, despite the promising performance, such an approach obtains the argument pairs implicitly by the two decomposed tasks, lacking explicitly modeling of the argument-level interactions between argument pairs.In this paper, we tackle the APE task by a mutual guidance framework, which could utilize the information of an argument in one passage to guide the identification of arguments that can form pairs with it in another passage.In this manner, two passages can mutually guide each other in the process of APE.Furthermore, we propose an inter-sentence relation graph to effectively model the interrelations between two sentences and thus facilitates the extraction of argument pairs.Our proposed method can better represent the holistic argument-level semantics and thus explicitly capture the complex correlations between argument pairs.Experimental results show that our approach significantly outperforms the current state-of-the-art model.