Author name cluster

Chong Teng

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

1 author row

AAAI Conference 2026 Conference Paper

PaSE: Prototype-aligned Calibration and Shapley-based Equilibrium for Multimodal Sentiment Analysis

Kang He
Boyu Chen
Yuzhe Ding
Fei Li
Chong Teng
Donghong Ji

Multimodal Sentiment Analysis (MSA) seeks to understand human emotions by integrating textual, acoustic, and visual signals. Although multimodal fusion is designed to leverage cross-modal complementarity, real-world scenarios often exhibit modality competition: dominant modalities tend to overshadow weaker ones, leading to suboptimal performance. In this paper, we propose PaSE, a novel Prototype-aligned Calibration and Shapley-optimized Equilibrium framework, which enhances collaboration while explicitly mitigating modality competition. PaSE first applies Prototype-guided Calibration Learning (PCL) to refine unimodal representations and align them through an Entropic Optimal Transport mechanism that ensures semantic consistency. To further stabilize optimization, we introduce a Dual-Phase Optimization strategy. A prototype-gated fusion module is first used to extract shared representations, followed by Shapley-based Gradient Modulation (SGM), which adaptively adjusts gradients according to the contribution of each modality. Extensive experiments on IEMOCAP, MOSI, and MOSEI confirm that PaSE achieves the superior performance and effectively alleviates modality competition.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions

Xiaorui Wu
Fei Li
Xiaofeng Mao
Xin Zhang
Li Zheng
Yuxiang Peng
Chong Teng
Donghong Ji

Large language models (LLMs) frequently refuse to respond to pseudo-malicious instructions: semantically harmless input queries triggering unnecessary LLM refusals due to conservative safety alignment, significantly impairing user experience. Collecting such instructions is crucial for evaluating and mitigating over-refusals, but existing instruction curation methods, like manual creation or instruction rewriting, either lack scalability or fail to produce sufficiently diverse and effective refusal-inducing prompts. To address these limitations, we introduce EVOREFUSE, a prompt optimization approach that generates diverse pseudo-malicious instructions consistently eliciting confident refusals across LLMs. EVOREFUSE employs an evolutionary algorithm exploring the instruction space in more diverse directions than existing methods via mutation strategies and recombination, and iteratively evolves seed instructions to maximize evidence lower bound on LLM refusal probability. Using EVOREFUSE, we create two novel datasets: EVOREFUSE-TEST, a benchmark of 582 pseudo-malicious instructions that outperforms the next-best benchmark with 85. 34% higher average refusal triggering rate across 9 LLMs without a safety-prior system prompt, 34. 86% greater lexical diversity, and 40. 03% improved LLM response confidence scores; and EVOREFUSE-ALIGN, which provides 3, 000 pseudo-malicious instructions with responses for supervised and preference-based alignment training. With supervised fine-tuning on EVOREFUSE-ALIGN, LLAMA3. 1-8B-INSTRUCT achieves up to 29. 85% fewer over-refusals than models trained on the second-best alignment dataset, without compromising safety. Our analysis with EVOREFUSE-TEST reveals models trigger over-refusals by overly focusing on sensitive keywords while ignoring broader context. Our code and datasets are available at https: //github. com/FishT0ucher/EVOREFUSE.

PDF Details

AAAI Conference 2025 Conference Paper

Multi-Granular Multimodal Clue Fusion for Meme Understanding

Li Zheng
Hao Fei
Ting Dai
Zuquan Peng
Fei Li
Huisheng Ma
Chong Teng
Donghong Ji

With the continuous emergence of various social media platforms frequently used in daily life, the multimodal meme understanding (MMU) task has been garnering increasing attention. MMU aims to explore and comprehend the meanings of memes from various perspectives by performing tasks such as metaphor recognition, sentiment analysis, intention detection, and offensiveness detection. Despite making progress, limitations persist due to the loss of fine-grained metaphorical visual clue and the neglect of multimodal text-image weak correlation. To overcome these limitations, we propose a multi-granular multimodal clue fusion model (MGMCF) to advance MMU. Firstly, we design an object-level semantic mining module to extract object-level image feature clues, achieving fine-grained feature clue extraction and enhancing the model's ability to capture metaphorical details and semantics. Secondly, we propose a brand-new global-local cross-modal interaction model to address the weak correlation between text and images. This model facilitates effective interaction between global multimodal contextual clues and local unimodal feature clues, strengthening their representations through a bidirectional cross-modal attention mechanism. Finally, we devise a dual-semantic guided training strategy to enhance the model's understanding and alignment of multimodal representations in the semantic space. Experiments conducted on the widely-used MET-MEME bilingual dataset demonstrate significant improvements over state-of-the-art baselines. Specifically, there is an 8.14% increase in precision for offensiveness detection task, and respective accuracy enhancements of 3.53%, 3.89%, and 3.52% for metaphor recognition, sentiment analysis, and intention detection tasks. These results, underpinned by in-depth analyses, underscore the effectiveness and potential of our approach for advancing MMU.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Compositional Generalization for Multi-Label Text Classification: A Data-Augmentation Approach

Yuyang Chai
Zhuang Li
Jiahui Liu
Lei Chen
Fei Li
Donghong Ji
Chong Teng

Despite significant advancements in multi-label text classification, the ability of existing models to generalize to novel and seldom-encountered complex concepts, which are compositions of elementary ones, remains underexplored. This research addresses this gap. By creating unique data splits across three benchmarks, we assess the compositional generalization ability of existing multi-label text classification models. Our results show that these models often fail to generalize to compositional concepts encountered infrequently during training, leading to inferior performance on tests with these new combinations. To address this, we introduce a data augmentation method that leverages two innovative text generation models designed to enhance the classification models' capacity for compositional generalization. Our experiments show that this data augmentation approach significantly improves the compositional generalization capabilities of classification models on our benchmarks, with both generation models surpassing other text generation baselines. Our codes available at https://github.com/yychai74/LD-VAE.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Reverse Multi-Choice Dialogue Commonsense Inference with Graph-of-Thought

Li Zheng
Hao Fei
Fei Li
Bobo Li
Lizi Liao
Donghong Ji
Chong Teng

With the proliferation of dialogic data across the Internet, the Dialogue Commonsense Multi-choice Question Answering (DC-MCQ) task has emerged as a response to the challenge of comprehending user queries and intentions. Although prevailing methodologies exhibit effectiveness in addressing single-choice questions, they encounter difficulties in handling multi-choice queries due to the heightened intricacy and informational density. In this paper, inspired by the human cognitive process of progressively excluding options, we propose a three-step Reverse Exclusion Graph-of-Thought (ReX-GoT) framework, including Option Exclusion, Error Analysis, and Combine Information. Specifically, our ReX-GoT mimics human reasoning by gradually excluding irrelevant options and learning the reasons for option errors to choose the optimal path of the GoT and ultimately infer the correct answer. By progressively integrating intricate clues, our method effectively reduces the difficulty of multi-choice reasoning and provides a novel solution for DC-MCQ. Extensive experiments on the CICERO and CICERO_v2 datasets validate the significant improvement of our approach on DC-MCQ task. On zero-shot setting, our model outperform the best baseline by 17.67% in terms of F1 score for the multi-choice task. Most strikingly, our GPT3.5-based ReX-GoT framework achieves a remarkable 39.44% increase in F1 score.

PDF Details DOI

EAAI Journal 2023 Journal Article

MOIT: A Novel task for mining opinions towards implicit targets

Jun Zhou
Fei Li
Chong Teng
Yijiang Liu
Chunli Xiang
Donghong Ji

The extraction of opinions and their corresponding targets has gained significant interest recently, as it offers valuable insights into Opinion Mining (OM) at a granular level. Opinion and target terms to be extracted by existing OM tasks need to be explicitly present in reviews. Targets that are not present but implied in contextual semantics, are neglected by existing OM tasks, even though an investigation reported that about 60% of reviews contain implicit targets. To enable implicit target extraction, a novel task named Mining Opinions towards Implicit Targets (MOIT) under the fine-grained OM, is proposed to extract both opinions and their corresponding implicit targets, enabling a more comprehensive analysis of reviews. To set up the basis for follow-up research on MOIT, two large-scale datasets were constructed as resources in two languages, where the Chinese dataset was built from scratch via a standard human annotation process, and the English dataset was built semi-automatically through machine translation and manual checking. Furthermore, three baseline models adapting three representative paradigms of information extraction, namely sequence labeling, question answering, and text generation, were proposed to solve MOIT. Extensive experiments demonstrated the effectiveness of the models. The proposed MOIT task extends the field of OM research, and the datasets and models establish a foundation for future studies in this area.

Details DOI

AAAI Conference 2022 Conference Paper

Mastering the Explicit Opinion-Role Interaction: Syntax-Aided Neural Transition System for Unified Opinion Role Labeling

Shengqiong Wu
Hao Fei
Fei Li
Meishan Zhang
Yijiang Liu
Chong Teng
Donghong Ji

Unified opinion role labeling (ORL) aims to detect all possible opinion structures of ‘opinion-holder-target’ in one shot, given a text. The existing transition-based unified method, unfortunately, is subject to longer opinion terms and fails to solve the term overlap issue. Current top performance has been achieved by employing the span-based graph model, which however still suffers from both high model complexity and insufficient interaction among opinions and roles. In this work, we investigate a novel solution by revisiting the transition architecture, and augmenting it with a pointer network (PointNet). The framework parses out all opinion structures in linear-time complexity, meanwhile breaks through the limitation of any length of terms with PointNet. To achieve the explicit opinion-role interactions, we further propose a unified dependency-opinion graph (UDOG), co-modeling the syntactic dependency structure and the partial opinion-role structure. We then devise a relation-centered graph aggregator (RCGA) to encode the multi-relational UDOG, where the resulting high-order representations are used to promote the predictions in the vanilla transition system. Our model achieves new state-of-the-art results on the MPQA benchmark. Analyses further demonstrate the superiority of our methods on both efficacy and efficiency.

PDF Details

AAAI Conference 2022 Conference Paper

Unified Named Entity Recognition as Word-Word Relation Classification

Jingye Li
Hao Fei
Jiang Liu
Shengqiong Wu
Meishan Zhang
Chong Teng
Donghong Ji
Fei Li

So far, named entity recognition (NER) has been involved with three major types, including flat, overlapped (aka. nested), and discontinuous NER, which have mostly been studied individually. Recently, a growing interest has been built for unified NER, tackling the above three jobs concurrently with one single model. Current best-performing methods mainly include span-based and sequence-to-sequence models, where unfortunately the former merely focus on boundary identification and the latter may suffer from exposure bias. In this work, we present a novel alternative by modeling the unified NER as word-word relation classification, namely W2 NER. The architecture resolves the kernel bottleneck of unified NER by effectively modeling the neighboring relations between entity words with Next-Neighboring-Word (NNW) and Tail-Head-Word-* (THW-*) relations. Based on the W2 NER scheme we develop a neural framework, in which the unified NER is modeled as a 2D grid of word pairs. We then propose multi-granularity 2D convolutions for better refining the grid representations. Finally, a co-predictor is used to sufficiently reason the word-word relations. We perform extensive experiments on 14 widely-used benchmark datasets for flat, overlapped, and discontinuous NER (8 English and 6 Chinese datasets), where our model beats all the current top-performing baselines, pushing the state-of-the-art performances of unified NER.

PDF Details