相关论文: CoGate-LSTM: Prototype-Guided Feature-Space Gating…

With the increasing popularity of video sharing websites such as YouTube and Facebook, multimodal sentiment analysis has received increasing attention from the scientific community. Contrary to previous works in multimodal sentiment…

Due to their architecture and vast pre-training data, large language models (LLMs) demonstrate strong text classification performance. However, LLM output - here, the category assigned to a text - depends heavily on the wording of the…

Existing Chinese toxic content detection methods mainly target sentence-level classification but often fail to provide readable and contiguous toxic evidence spans. We propose \textbf{ToxiTrace}, an explainability-oriented method for…

Textual-visual matching aims at measuring similarities between sentence descriptions and images. Most existing methods tackle this problem without effectively utilizing identity-level annotations. In this paper, we propose an identity-aware…

We propose a novel prompt tuning method called CoAPT(Context Attribute words in Prompt Tuning) for few/zero-shot image classification. The core motivation is that attributes are descriptive words with rich information about a given concept.…

Chain-of-Thought (CoT) prompting has emerged as a foundational technique for eliciting reasoning from Large Language Models (LLMs), yet the robustness of this approach to corruptions in intermediate reasoning steps remains poorly…

We present our works on SemEval-2021 Task 5 about Toxic Spans Detection. This task aims to build a model for identifying toxic words in whole posts. We use the BiLSTM-CRF model combining with ToxicBERT Classification to train the detection…

Large Language Models (LLMs) have demonstrated powerful capabilities that render them valuable in different applications, including conversational AI products. It is paramount to ensure the security and reliability of these products by…

Accurate state-of-health (SOH) estimation for lithium-ion batteries remains a challenging problem due to complex electrochemical degradation mechanisms and long-range temporal dependencies. In this work, we propose a quantum-enhanced…

In order to quantize the gate parameters of the LSTM (Long Short-Term Memory) neural network model with almost no recognition performance degraded, a new quantization method named Quantization Loss Re-Learn Method is proposed in this paper.…

As Large Language Models (LLMs) grow increasingly powerful, ensuring their safety and alignment with human values remains a critical challenge. Ideally, LLMs should provide informative responses while avoiding the disclosure of harmful or…

Standard Recurrent Neural Networks, including LSTMs, struggle to model long-range dependencies, particularly in sequences containing noisy or misleading information. We propose a new architectural principle, Output-Conditioned Gating, which…

Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrails typically rely on single-pass classification or, more recently, distilled reasoning.…

Content moderation and toxicity classification represent critical tasks with significant social implications. However, studies have shown that major classification models exhibit tendencies to magnify or reduce biases and potentially…

Large Language Models (LLMs) remain vulnerable to prompt injection attacks, representing the most significant security threat in production deployments. We present Prompt Fencing, a novel architectural approach that applies cryptographic…

The Cognitive Categorical Transformer (CCT) is a 306M-parameter architecture that augments a pretrained GPT-2 Small backbone with cognitively grounded components derived from category theory and several inspirations from cognitive science.…

Federated Learning (FL) enables collaborative model training across decentralized clients without sharing private data. However, FL suffers from biased global models due to non-IID and long-tail data distributions. We propose…

This paper presents LITE, an LLM-based evaluation method designed for efficient and flexible assessment of taxonomy quality. To address challenges in large-scale taxonomy evaluation, such as efficiency, fairness, and consistency, LITE…

Text analysis of tabular data relies on two core operations: \emph{summarization} for corpus-level theme extraction and \emph{tagging} for row-level labeling. A critical limitation of employing large language models (LLMs) for these tasks…

Few-shot learning (FSL) aims to recognize novel concepts from only a few labeled support samples. Recent studies enhance support features by incorporating additional semantic information or designing complex semantic fusion modules.…