Sarcasm detection is a crucial yet challenging Natural Language Processing task. Existing Large Language Model methods are often limited by single-perspective analysis, static reasoning pathways, and a susceptibility to hallucination when processing complex ironic rhetoric, which impacts their accuracy and reliability. To address these challenges, we propose SEVADE, a novel Self-Evolving multi-agent Analysis framework with Decoupled Evaluation for hallucination-resistant sarcasm detection. The core of our framework is a Dynamic Agentive Reasoning Engine (DARE), which utilizes a team of specialized agents grounded in linguistic theory to perform a multifaceted deconstruction of the text and generate a structured reasoning chain. Subsequently, a separate lightweight rationale adjudicator (RA) performs the final classification based solely on this reasoning chain. This decoupled architecture is designed to mitigate the risk of hallucination by separating complex reasoning from the final judgment. Extensive experiments on four benchmark datasets demonstrate that our framework achieves state-of-the-art performance, with average improvements of 7.01% in Accuracy and 6.55% in Macro-F1 score.

Sarcasm detection remains a significant challenge due to its reliance on nuanced contextual understanding, world knowledge, and multifaceted linguistic cues that vary substantially across different sarcastic expressions.Existing approaches, from fine-tuned transformers to large language models, apply a uniform reasoning strategy to all inputs, struggling to address the diverse analytical demands of sarcasm.These demands range from modeling contextual expectation violations to requiring external knowledge grounding or recognizing specific rhetorical patterns.To address this limitation, we introduce RAM-SD, a Retrieval-Augmented Multi-Agent framework for Sarcasm Detection.The framework operates through four stages: (1) contextual retrieval grounds the query in both sarcastic and non-sarcastic exemplars; (2) a meta-planner classifies the sarcasm type and selects an optimal reasoning plan from a predefined set; (3) an ensemble of specialized agents performs complementary, multi-view analysis ; and (4) an integrator synthesizes these analyses into a final, interpretable judgment with a natural language explanation.Evaluated on four standard benchmarks, RAM-SD achieves a state-of-theart Macro-F1 of 77.74%, outperforming the strong GPT-4o+CoC baseline by 7.01 points.Our framework not only sets a new performance benchmark but also provides transparent and interpretable reasoning traces, illuminating the cognitive processes behind sarcasm comprehension.

The proliferation of AI-generated disinformation has amplified the demand for evidence-based fake news detection. Although existing techniques leverage relevant evidence to verify the authenticity of news, they often rely on spurious correlations between superficial patterns and labels instead of genuine evidence-claim reasoning. This tendency degrades the model generalization when applied to real-world scenarios with distribution shifts. To address this challenge, we propose Causal-GATNet1, a unified causal inference architecture that integrates causal intervention with adaptive evidence gating. Our approach: 1) Employs a dual-path causal debiasing framework that compares the standard prediction using all available evidence with a counterfactual prediction generated by blocking bias-inducing evidence, thereby yielding an unbiased output through prediction differencing. 2) Incorporates the Gated Affine Transformation (GAT) mechanism to enhance evidence reliability by combining the source credibility of evidence with their semantics. Experiments on multiple datasets demonstrate that integrating Causal-GATNet with established baseline models such as BERT and MAC significantly improves prediction accuracy and bias mitigation compared to the original implementations.

This paper mainly uses the stochastic forest model and multiple linear models to forecast stock return rates. Based on the ten risk factors of the Barra framework, the above two models are used to predict the predicted return rate of each stock. The main conclusions of this paper are as follows. First, in the single-factor sequencing analysis of stock return prediction, the long-short combination of return prediction based on a random forest model can obtain a return rate of 1.66% per month, which is significant at a 1% significance level. The long-short combination has a Sharp rate of 1.78, which is 1.24 higher than that of the linear model. Second, in the case of controlling six classical factors, such as market factors and market value factors, the long-short combination based on the random forest model can still obtain 1.63% excess return per month and is significant at the 5% significance level. Finally, the results based on Fama-MacBeth regression show that the prediction result of random forest predicted rate of return on the real rate of return is long-term stable.

Unsupervised text style transfer aims to alter the underlying style of the text to a desired value while keeping its style-independent semantics, without the support of parallel training corpora.Existing methods struggle to achieve both high style conversion rate and low content loss, exhibiting the over-transfer and undertransfer problems.We attribute these problems to the conflicting driving forces of the style conversion goal and content preservation goal.In this paper, we propose a collaborative learning framework for unsupervised text style transfer using a pair of bidirectional decoders, one decoding from left to right while the other decoding from right to left.In our collaborative learning mechanism, each decoder is regularized by knowledge from its peer which has a different knowledge acquisition process.The difference is guaranteed by their opposite decoding directions and a distinguishability constraint.As a result, mutual knowledge distillation drives both decoders to a better optimum and alleviates the over-transfer and undertransfer problems.Experimental results on two benchmark datasets show that our framework achieves strong empirical results on both style compatibility and content preservation.

Speaker verification aims to recognize target speakers with very few enrollment utterances. Conventional approaches learn a representation model to extract the speaker embeddings for verification. Recently, there are several new approaches in meta-learning which try to learn a shared metric space. Among these approaches, prototypical networks aim at learning a non-linear mapping from the input space to an embedding space with a predefined distance metric. In this paper, we investigate the use of prototypical networks in a small footprint text-independent speaker verification task. Our work is evaluated on SRE10 evaluation set. Experiments show that prototypical networks outperform the conventional method when the amount of data per training speaker is limited.

Model-Agnostic Meta-Learning (MAML) and its variants are popular few-shot classification methods. They train an initializer across a variety of sampled learning tasks (also known as episodes) such that the initialized model can adapt quickly to new ones. However, current MAML-based algorithms have limitations in forming generalizable decision boundaries. In this paper, we propose an approach called MetaMix, which generates virtual feature-target pairs within each episode to regularize the backbone models. MetaMix can be integrated with any of the MAML-based algorithms and learn the decision boundaries generalizing better to new tasks. Experiments on the mini-ImageNet, CUB, and FC100 datasets show that MetaMix improves the performance of MAML-based algorithms and achieves state-of-the-art result when integrated with Meta-Transfer Learning.

Consistency regularization methods have shown great success in semi-supervised learning tasks. Most existing methods focus on either the local neighborhood or in-between neighborhood of training samples to enforce the consistency constraint. In this paper, we propose a novel generalized framework called Adversarial Mixup (AdvMixup), which unifies the local and in-between neighborhood approaches by defining a virtual data distribution along the paths between the training samples and adversarial samples. Experimental results on both synthetic data and benchmark datasets exhibit that our AdvMixup can achieve better performance and robustness than state-of-the-art methods for semi-supervised learning.

202402 bcch

The abstractive method and extractive method are two main approaches for automatic document summarization. In this paper, to fully integrate the relatedness and advantages of both approaches, we propose a general unified framework for abstractive summarization which incorporates extractive summarization as an auxiliary task. In particular, our framework is composed of a shared hierarchical document encoder, a hierarchical attention mechanism-based decoder, and an extractor. We adopt multi-task learning method to train these two tasks jointly, which enables the shared encoder to better capture the semantics of the document. Moreover, as our main task is abstractive summarization, we constrain the attention learned in the abstractive task with the labels of the extractive task to strengthen the consistency between the two tasks. Experiments on the CNN/DailyMail dataset demonstrate that both the auxiliary task and the attention constraint contribute to improve the performance significantly, and our model is comparable to the state-of-the-art abstractive models. In addition, we cut half number of labels of the extractive task, pretrain the extractor, and jointly train the two tasks using the estimated sentence salience of the extractive task to constrain the attention of the abstractive task. The results do not decrease much compared with using full-labeled data of the auxiliary task.