Papers by Songlin Hu

Representation Learning with Conditional Information Flow Maximization (2024.acl-long)

Challenge:	Existing approaches focus on improving attack success rates while overlooking the need for comprehensive test case coverage.
Approach:	They propose a top-down approach to automated red teaming that scales up the diversity of test cases using an extensible, fine-grained risk taxonomy.
Outcome:	The proposed approach scales up the diversity of test cases using a top-down approach based on an extensible, fine-grained risk taxonomy and leverages reinforcement learning techniques to facilitate multi-turn adversarial probing in a human-like manner.

Copied to clipboard

Dou Hu, Lingwei Wei, Wei Zhou, Songlin Hu

Uncertainty-aware Propagation Structure Reconstruction for Fake News Detection (2022.coling-1)

Challenge:	Existing knowledge-theoretic representation learning frameworks are based on the information bottleneck principle, which preserves redundant features irrelevant to the given task.
Approach:	They propose a conditional information flow maximization framework to learn sufficient representations for the input data and target task by maximizing both input-representation and representation-label mutual information.
Outcome:	The proposed framework can extract noise-invariant sufficient representations for the input data and target task.

Copied to clipboard

Lingwei Wei, Dou Hu, Wei Zhou, Songlin Hu

Early Detection of Fake News by Utilizing the Credibility of News, Publishers, and Users based on Weakly Supervised Learning (2020.coling-main)

Challenge:	Existing methods to detect fake news neglect a broader propagation uncertainty issue . Existing studies leverage the user interactions in a social media conversation thread to detect false news.
Approach:	They propose a dual graph-based model for improving fake news detection . they propose to explore latent interactions in the actual propagation .
Outcome:	The proposed model improves on two real-world datasets showing that it is superior to existing models.

Copied to clipboard

Chunyuan Yuan, Qianwen Ma, Wei Zhou, Jizhong Han, Songlin Hu

LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing (2025.emnlp-main)

Challenge:	Existing models for fake news detection are often insufficient or lacking in features . a novel structure-aware multi-head attention network can detect fake news in 4 hours .
Approach:	They propose a structure-aware multi-head attention network to detect fake news in mass news . they use credibility of publishers and users as prior weakly supervised information .
Outcome:	The proposed model can detect fake news in 4 hours with an accuracy of over 91% . the proposed model is faster than the state-of-the-art models .

Copied to clipboard

Peng Wang, Biyu Zhou, Xuehai Tang, Jizhong Han, Songlin Hu

QAP: A Quantum-Inspired Adaptive-Priority-Learning Model for Multimodal Emotion Recognition (2023.findings-acl)

Challenge:	Existing models for enhancing knowledge updating are prone to performance degradation due to incomplete knowledge preservation mechanisms.
Approach:	They propose a model for locate-then-edit that decomposes long-term constrained programming into tractable stepwise subproblems for efficient solving.
Outcome:	The proposed framework achieves asymptotic optimal editing performance while meeting the constraints of long-term knowledge preservation.

Copied to clipboard

Ziming Li, Yan Zhou, Yaxin Liu, Fuqing Zhu, Chuanpeng Yang, Songlin Hu

Uncertainty-Aware Cross-Modal Alignment for Hate Speech Detection (2024.lrec-main)

Challenge:	Experimental results show that multimodal emotion recognition is a state-of-the-art technique . textual, visual and acoustic modalities are involved in multimodal video emotion recognition .
Approach:	They propose a quantum-inspired adaptive-priority-learning model to address the challenges . they use quantum state to model modal features and Q-attention to integrate three modalities .
Outcome:	Experimental results show that QAP improves on previous models.

Copied to clipboard

Chuanpeng Yang, Fuqing Zhu, Yaxin Liu, Jizhong Han, Songlin Hu

More Thinking, Less Talking: Internalizing Deliberative Safety into LLM Parameters (2026.acl-long)

Challenge:	Existing methods for detecting hate speech ignore misalignment and uncertainty between modalities . social media platforms have become conduits for the rapid dissemination of hate speech .
Approach:	They propose an uncertainty-aware cross-modal alignment framework for hate speech detection that minimizes the misalignment of image and text in memes.
Outcome:	The proposed framework produces a competitive performance compared with existing methods.

Copied to clipboard

Guan Wang, Xuehai Tang, Biyu Zhou, Jizhong Han, Songlin Hu

Robustness in NLP

Challenge:	Existing safety alignment methods leave Large Language Models vulnerable to sophisticated jailbreak attacks.
Approach:	They propose a safety reasoning internalization framework that internalizes safety reasoning into an implicit computational pathway using Low-Rank Adaptation (LoRA).
Outcome:	The proposed framework achieves a 43% lower Attack Success Rate (ASR) against distinct jailbreak attacks compared to strong baselines.

Query-as-context Pre-training for Dense Passage Retrieval (2023.emnlp-main)

Copied to clipboard

Xing W, Guangyuan Ma, Wanhui Qian, Zijia Lin, Songlin Hu

Information Retrieval

Challenge:	Existing methods to improve passage retrieval performance by using context-supervised pre-training are weakly correlated.
Approach:	They propose to use query-as-context pre-training to train passage-query pairs . they evaluate the pre-trained models on large-scale passage retrieval benchmarks .
Outcome:	The proposed technique improves performance on large-scale passage retrieval benchmarks and out-of-domain zero-shot benchmarks.

CartesianMoE: Boosting Knowledge Sharing among Experts via Cartesian Product Routing in Mixture-of-Experts (2025.naacl-long)

Copied to clipboard

Zhenpeng Su, Xing W, Zijia Lin, Yizhe Xiong, Minxuan Lv, Guangyuan Ma, Hui Chen, Songlin Hu, Guiguang Ding

Multi-hop Selector Network for Multi-turn Response Selection in Retrieval-based Chatbots (D19-1)

Challenge:	Large language models (LLMs) have been attracting much attention due to their impressive performance in all kinds of downstream tasks.
Approach:	They propose a mix-of-experts model that allows the model size to grow without raising training costs.
Outcome:	The proposed model outperforms existing models in perplexity and robustness tests.

Copied to clipboard

Chunyuan Yuan, Wei Zhou, Mingming Li, Shangwen Lv, Fuqing Zhu, Jizhong Han, Songlin Hu

Natural Language Interfaces

Challenge:	Existing studies focus on matching candidate responses with every context utterance, but it also brings noise signals and unnecessary information.
Approach:	They propose a multi-hop selector network to match context with candidate responses . they propose to use a selector to filter the relevant utterances as context .
Outcome:	The proposed model outperforms state-of-the-art methods on three public multi-turn dialogue datasets.

Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversations (2023.acl-long)

Copied to clipboard

Dou Hu, Yinan Bao, Lingwei Wei, Wei Zhou, Songlin Hu

Multi-stream Information Fusion Framework for Emotional Support Conversation (2024.lrec-main)

Challenge:	Existing methods to recognize emotions have limitations in discovering the intrinsic structure of data relevant to emotion labels, and struggle to extract generalized and robust representations.
Approach:	They propose a supervised adversarial contrastive learning framework for learning class-spread structured representations in a controlled manner.
Outcome:	The proposed framework can extract generalized and robust representations on three datasets and achieves state-of-the-art performance.

Copied to clipboard

Yinan Bao, Dou Hu, Lingwei Wei, Shuchong Wei, Wei Zhou, Songlin Hu

Dialogue Systems & Conversational Agents

Challenge:	Existing methods for ESC do not capture the dynamic transition of emotion intensity due to the difficulty to model its dynamic transition.
Approach:	They propose to fuse three streams for the effective modelling of emotion intensity using a multi-stream fusion unit.
Outcome:	The proposed model reduces the emotional distress of users with high-intensity of negative emotions by incorporating three different kinds of streams for the dynamic transition of emotion intensity.

Mem2ActBench: A Benchmark for Evaluating Long-Term Memory Utilization in Task-Oriented Autonomous Agents (2026.acl-long)

Copied to clipboard

Yiting Shen, Kun Li, Wei Zhou, Songlin Hu

Challenge:	Existing benchmarks focus on direct queries for a factual answer, but fail to evaluate the more crucial capability of actively applying memory to execute tasks.
Approach:	They propose a benchmark to evaluate whether agents can proactively leverage long-term memory to execute tool-based actions by selecting appropriate tools and grounding their parameters.
Outcome:	The proposed benchmarks show that 91.3% of tasks are memory-dependent . the benchmarks simulate persistent assistant usage, where users mention the same topic across long, interrupted interactions and expect previously established preferences and task states to be implicitly applied.

Structure-adaptive Adversarial Contrastive Learning for Multi-Domain Fake News Detection (2025.findings-acl)

Copied to clipboard

Lingwei Wei, Dou Hu, Wei Zhou, Philip S. Yu, Songlin Hu

A Unified Propagation Forest-based Framework for Fake News Detection (2022.coling-1)

Challenge:	Existing models for fake news detection capture domain-shared semantic features but fail to generalize well due to poor adaptability.
Approach:	They propose a framework to enable structure knowledge transfer between multiple domains . they compare content-only and propagation-rich data to preserve structural patterns .
Outcome:	The proposed framework can learn semantic and structural features across domains.

Copied to clipboard

Lingwei Wei, Dou Hu, Yantong Lai, Wei Zhou, Songlin Hu

Improve Student’s Reasoning Generalizability through Cascading Decomposed CoTs Distillation (2024.emnlp-main)

Challenge:	Recent studies on fake news detection have focused on textual news material, but there is a lack of authoritative regulators.
Approach:	They propose a framework to explore latent correlations between propagation trees and a root-induced training strategy to encourage representations of propagation tree to be closer to their prototypical root nodes.
Outcome:	The proposed framework explores latent correlations between propagation trees to improve fake news detection.

Copied to clipboard

Chengwei Dai, Kun Li, Wei Zhou, Songlin Hu

Capture the Key in Reasoning to Enhance CoT Distillation Generalization (2025.acl-long)

Challenge:	Existing studies have tried to distill these capabilities into smaller language models (SLMs) however, these capabilities are often associated with more parameters, which is not practical to emergent in smaller models.
Approach:	They propose to decompose the traditional single-step learning process into two cascaded learning steps by restructuring the training objectives and concatenating the question with the rationale as input.
Outcome:	Extensive experiments show that the proposed method improves reasoning generalizability and diversity of the model.

Copied to clipboard

Chengwei Dai, Kun Li, Wei Zhou, Songlin Hu

Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks (2022.acl-short)

Challenge:	Existing distillation methods for Large Language Models (LLMs) focus on fine-tuning student SLMs on correct data, resulting in students struggling to learn the key instead of analyzing mistakes according to correct solutions.
Approach:	They propose a method that exposes key reasoning steps rather than simple fine-tuning students' CoTs data by using a set of prompts with similar reasoning paths but divergent conclusions.
Outcome:	The proposed method improves student SLMs' ability to learn key reasoning steps rather than fine-tuning them on teacher data.

Copied to clipboard

Xing Wu, Chaochen Gao, Meng Lin, Liangjun Zang, Songlin Hu

Information Extraction & Text Mining

Challenge:	Experimental results show text smoothing outperforms data augmentation methods by a substantial margin.
Approach:	They propose to use a masked language model to convert a token to a smoothed representation by converting a sentence from its one-hot representation to 'controllable smoothes' they propose to combine text smoothing with other data augmentation methods to achieve better performance.
Outcome:	The proposed method outperforms mainstream data augmentation methods by a substantial margin on different datasets in a low-resource regime.

TEF: Causality-Aware Taxonomy Expansion via Front-Door Criterion (2025.coling-main)

Copied to clipboard

Yuan Meng, Songlin Zhai, Yuxin Zhang, Zhongjian Hu, Guilin Qi

Multi-Task Representation Alignment on Language Understanding: A Mutual Information Perspective (2026.acl-long)

Challenge:	Existing research still faces spurious query-anchor matching due to unobserved factors.
Approach:	They propose a model that uses the front-door criteria to decompose the expansion process into a parser module and a connector to isolate confounding effects.
Outcome:	Extensive experiments on three benchmarks validate the effectiveness of the proposed model.

Copied to clipboard

Dou Hu, Lingwei Wei, Hongjiang Xiao, Songlin Hu, Yuan Zhang

Towards Propagation Uncertainty: Edge-enhanced Bayesian Graph Convolutional Networks for Rumor Detection (2021.acl-long)

Challenge:	Existing approaches to multitask learning fail to address task interference issues . Existing methods focus on task balancing or probabilistic modeling but fail to learn sufficient representations for all target tasks.
Approach:	They propose a multi-task representation alignment framework to achieve task-specific alignment and self-alignment on shared representations from a mutual information perspective.
Outcome:	The proposed framework outperforms 13 representative MTL methods under label-noisy and data-constrained conditions.

Copied to clipboard

Lingwei Wei, Dou Hu, Wei Zhou, Zhaojuan Yue, Songlin Hu

Structured Data in NLP

Challenge:	Existing studies on rumor detection focus on text content and propagation structure . however, the uncertainty caused by unreliable relations in propagation structures is common .
Approach:	They propose a Bayesian-based model that captures propagation uncertainty for rumor detection.
Outcome:	The proposed model achieves better performance than baseline methods on rumor detection and early rumour detection tasks.

CT-GAT: Cross-Task Generative Adversarial Attack based on Transferability (2023.emnlp-main)

Copied to clipboard

Minxuan Lv, Chengwei Dai, Kun Li, Wei Zhou, Songlin Hu

Robustness in NLP

Challenge:	Neural network models are vulnerable to adversarial examples, and current methods based on adversarially transferable models rely on substitute models, which can be impractical and costly in real-world scenarios due to the unavailability of training data and the victim model’s structural details.
Approach:	They propose a novel approach that directly constructs adversarial examples by extracting transferable features across various tasks.
Outcome:	The proposed approach achieves superior attack performance with small cost on ten datasets and demonstrates that it is a novel approach.

TrojanSQL: SQL Injection against Natural Language Interface to Database (2023.emnlp-main)

Copied to clipboard

Jinchuan Zhang, Yan Zhou, Binyuan Hui, Yaxin Liu, Ziming Li, Songlin Hu

Programming Languages in NLP

Challenge:	Existing studies on text-to-SQL systems have not investigated its security aspects . however, how to implement such attacks remains an open question.
Approach:	They propose a backdoor-based SQL injection framework for text-to-SQL systems that uses boolean-based injection and union-based injecting techniques to exploit SQL injection vulnerabilities.
Outcome:	The proposed framework can produce harmful SQL statements invalidating user queries or compromise sensitive information about the database.

DORA: Dynamic Optimization Prompt for Continuous Reflection of LLM-based Agent (2025.coling-main)

Copied to clipboard

Kun Li, Tingzhang Zhao, Wei Zhou, Songlin Hu

Gamma-Guard: Lightweight Residual Adapters for Robust Guardrails in Large Language Models (2025.emnlp-main)

Challenge:	Existing studies have shown that reflection can enhance performance, but our investigation reveals an undesirable pattern in reflection framework: effective self-reflection occurs primarily at the beginning of iterations, with subsequent attempts failing to produce further improvements.
Approach:	They propose a framework that generates task-adaptive reflection advice using an external open-source small language model.
Outcome:	The proposed framework generates task-adaptive and diverse reflection advice in MiniWoB++ and Alfworld environments.

Copied to clipboard

Lijia Lv, Yuanshu Zhao, Guan Wang, Xuehai Tang, Wen Jie, Jizhong Han, Songlin Hu

ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding (2022.coling-1)

Challenge:	Large language models (LLMs) are widely deployed as zero-shot evaluators for answer grading, content moderation, and document ranking.
Approach:	They propose a system that trains LLMs with adapters to denoise embeddings and refocus attention.
Outcome:	The proposed model lifts adversarial accuracy from 5% to 95% a 90 percentage-point gain while reducing clean-data accuracy by just 8 percentage points.

Copied to clipboard

Xing Wu, Chaochen Gao, Liangjun Zang, Jizhong Han, Zhongyuan Wang, Songlin Hu

Structure-aware Propagation Generation with Large Language Models for Fake News Detection (2025.findings-emnlp)

Challenge:	a new method for learning unsupervised sentence embeddings is proposed . unsup-SimCSE is biased because of the length information encoded into the sentence embeds .
Approach:	They propose a new unsupervised sentence embedding method that uses dropout to obtain positive pairs from a pre-trained Transformer encoder.
Outcome:	The proposed method outperforms the state-of-the-art unsup-SimCSE on a STS task.

Copied to clipboard

Mengyang Chen, Lingwei Wei, Wei Zhou, Songlin Hu

Ethical NLP

Challenge:	propagation-based methods for fake news detection often lack structural data . authors propose a structure-aware synthetic propagation enhanced detection framework .
Approach:	They propose a structure-aware synthetic propagation enhanced detection framework to capture real-world propagation.
Outcome:	The proposed framework captures structural dynamics from real propagation, while ignoring structural patterns.

RaP: Redundancy-aware Video-language Pre-training for Text-Video Retrieval (2022.findings-emnlp)

Copied to clipboard

Xing Wu, Chaochen Gao, Zijia Lin, Zhongyuan Wang, Jizhong Han, Songlin Hu

Resolving the Security-Auditability Dilemma with Auditable Latent Chain-of-Thought Alignment (2026.acl-long)

Challenge:	sparse sampling of videos suffers from inter-modal redundancy and visual redundancies . et al., 2021) proposes to sparsestly sample frames from videos to alleviate temporal redundance .
Approach:	They propose to use sparse sampling to alleviate temporal redundancy in videos . they propose to penalize high-redundant video patches and text tokens .
Outcome:	The proposed method improves on four benchmark datasets.

Copied to clipboard

Guan Wang, Biyu Zhou, Xuehai Tang, Jizhong Han, Songlin Hu

DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs (2025.emnlp-main)

Challenge:	Extensive experiments show that ALCA reduces the success rate of adaptive jailbreak attacks by over 40% compared to strong baselines, while preserving performance.
Approach:	They propose a framework that decouples internal reasoning from external output and allows the model to reconstruct its latent reasoning into human-readable text for supervision under specific guidance.
Outcome:	The proposed framework reduces the success rate of adaptive jailbreak attacks by over 40% compared to baselines while preserving performance.

Copied to clipboard

Minxuan Lv, Zhenpeng Su, Leiyu Pan, Yizhe Xiong, Zijia Lin, Hui Chen, Wei Zhou, Jungong Han, Guiguang Ding, Wenwu Ou, Di Zhang, Kun Gai, Songlin Hu

Uncertainty-Guided Modal Rebalance for Hateful Memes Detection (2024.acl-long)

Challenge:	Existing sparsification methods like pruning can lose model knowledge through parameter removal.
Approach:	They propose a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks.
Outcome:	The proposed approach achieves superior performance across language modeling and downstream tasks under equivalent computational constraints.

Copied to clipboard

Chuanpeng Yang, Yaxin Liu, Fuqing Zhu, Jizhong Han, Songlin Hu

FAIRGAMER: Evaluating Social Biases in LLM-Based Video Game NPCs (2026.acl-long)

Challenge:	Existing methods for integrating hate information from different modalities ignore the modality uncertainty caused by the contribution degree of each modality to hate sentiment.
Approach:	They propose an Uncertainty-guided Modal Rebalance framework for hateful memes detection . they propose to combine cross-modal fusion features with unimodal features .
Outcome:	The proposed framework produces state-of-the-art performance on four widely-used datasets.

Copied to clipboard

Bingkang Shi, Jen-tse Huang, Luo Long, Tianyu Zong, Hongzhu Yi, Yuanxiang Wang, Songlin Hu, Xiaodan Zhang, Zhongjiang Yao

Multi-Granularity Semantic Aware Graph Model for Reducing Position Bias in Emotion Cause Pair Extraction (2022.findings-acl)

Challenge:	Large Language Models (LLMs) have enhanced or replaced traditional non-player characters in video games.
Approach:	They propose a benchmark to evaluate social biases across three interaction patterns: transaction, cooperation, and competition.
Outcome:	The proposed benchmark assesses four bias types across transaction, cooperation, and competition using a novel metric, FairMCV.

Copied to clipboard

Yinan Bao, Qianwen Ma, Lingwei Wei, Wei Zhou, Songlin Hu

Structured Data in NLP

Challenge:	Existing methods to extract emotions and causes as pairs neglect effective semantic connections between distant clauses, leading to poor generalization ability towards position-insensitive data.
Approach:	They propose a novel multi-granularity semantic-aware Graph model to integrate fine-grained and coarse-grain semantic features together without regard to distance limitation.
Outcome:	The proposed model outperforms existing models significantly in position-insensitive data.

Integrating External Event Knowledge for Script Learning (2020.coling-main)

Copied to clipboard

Shangwen Lv, Fuqing Zhu, Songlin Hu

Information Retrieval

Challenge:	Recent studies focus on event co-occurrence to solve this problem.
Approach:	They propose to integrate external event knowledge to help predict the next event . they use a script-based approach that integrates external event information into the model .
Outcome:	The proposed method achieves state-of-the-art performance compared to other methods.

Supervised Prototypical Contrastive Learning for Emotion Recognition in Conversation (2022.emnlp-main)

Copied to clipboard

Xiaohui Song, Longtao Huang, Hui Xue, Songlin Hu

MiLe Loss: a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models (2024.findings-naacl)

Challenge:	Existing methods to capture emotions in conversation (ERC) lack the correlation between emotions and semantics, resulting in many challenges.
Approach:	They propose a Supervised Prototypical Contrastive Learning (SPCL) loss for the ERC task . they use a Prototype Network to leverage the supervised contrastive learning approach .
Outcome:	The proposed approach outperforms CoG-BART's proposed approach on three widely used benchmarks and shows that it is effective on multiple scenarios.

Copied to clipboard

Zhenpeng Su, Zijia Lin, Baixue Baixue, Hui Chen, Songlin Hu, Wei Zhou, Guiguang Ding, Xing W

Dynamic Simulation Framework for Disinformation Dissemination and Correction With Social Bots (2025.findings-emnlp)

Challenge:	Existing generative language models neglect an inherent challenge in text corpus during training, i.e., the imbalance between frequent tokens and infrequent ones.
Approach:	They propose a function to mitigate the imbalance between frequent and infrequent tokens . authors propose 'MiLe Loss' function to assess learning difficulty of tokens during training .
Outcome:	Experiments show that models with proposed model can improve on downstream benchmarks.

Copied to clipboard

Boyu Qiao, Kun Li, Wei Zhou, Songlin Hu

Reasoning

Challenge:	Current studies rely on simplistic user and network modeling and neglect dynamic behavior of bots.
Approach:	They propose a multi-agent-based framework for disinformation dissemination . it incorporates both malicious and legitimate bots and allows quantitative evaluation of correction strategies.
Outcome:	The proposed framework incorporates both malicious and legitimate bots and their controlled dynamic participation allows for quantitative analysis of correction strategies.

Regularized Contrastive Decoding with Hard Negative Samples for LLM Hallucination Mitigation (2025.findings-emnlp)

Copied to clipboard

Haonan Sheng, Dou Hu, Lingwei Wei, Wei Zhou, Songlin Hu

Reasoning

Challenge:	Large language models are prone to generate hallucinations, which can undermine their reliability in high-stakes applications.
Approach:	They propose a method to capture hallucination signals for mitigating hallucis in large language models by regularizing the model's internal signals to a weaker model .
Outcome:	The proposed method achieves better hallucination mitigation performance on four benchmarks.

FABLE: Fine-grained Fact Anchoring for Unstructured Model Editing (2026.findings-acl)

Copied to clipboard

Peng Wang, Biyu Zhou, Xuehai Tang, Jizhong Han, Songlin Hu

Challenge:	Existing methods for model editing memorize text holistically without reliable fine-grained fact access.
Approach:	They propose a hierarchical framework that decouples fine-grained fact injection from holistic text generation.
Outcome:	The proposed framework significantly improves fine-grained question answering while maintaining state-of-the-art holistic editing performance.

Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems (2024.naacl-long)

Copied to clipboard

Zhenpeng Su, Xing W, Wei Zhou, Guangyuan Ma, Songlin Hu

Chain of Attack: Hide Your Intention through Multi-Turn Interrogation (2025.findings-acl)

Challenge:	Existing studies on dialogue response selection focus on post-training and fine-tuning for cross-encoders.
Approach:	They propose a post-training technique tailored for dense encoders in dialogue response selection . they propose 'Dialogue Contextual Masking Auto-Encoder' which compresses dialogue semantics into dense vectors .
Outcome:	The proposed technique achieves state-of-the-art on two commonly evaluated benchmarks.

Copied to clipboard

Xikang Yang, Biyu Zhou, Xuehai Tang, Jizhong Han, Songlin Hu

Dialogue Systems & Conversational Agents

Challenge:	Existing jailbreak attacks focus on single-turn dialogue scenarios, leaving vulnerabilities in multi-turn contexts inadequately explored.
Approach:	They propose an optimal interrogation principle to conceal the jailbreak intent and introduce a multi-turn attack chain generation strategy called CoA.
Outcome:	The proposed method shows that black-box LLMs exhibit insufficient resistance under multi-turn interrogation, with more advantages (ASR, 83% vs 64%)

Smoothed Contrastive Learning for Unsupervised Sentence Embedding (2022.coling-1)

Copied to clipboard

Xing Wu, Chaochen Gao, Yipeng Su, Jizhong Han, Zhongyuan Wang, Songlin Hu

Few-Shot Learning for Cold-Start Recommendation (2024.lrec-main)

Challenge:	Unsupervised contrastive sentence embedding models use InfoNCE loss function . increasing batch size leads to performance degradation when it exceeds threshold .
Approach:	They propose a simple smoothing strategy upon the InfoNCE loss function to reduce the number of false-negative pairs in a batch without increasing the batch size.
Outcome:	The proposed smoothing strategy improves unsupervised SimCSE on semantic similarity tasks.

Copied to clipboard

Mingming Li, Songlin Hu, Fuqing Zhu, Qiannan Zhu

Label-Specific Dual Graph Neural Network for Multi-Label Text Classification (2021.acl-long)

Challenge:	Existing methods for cold-start learning and recommendation are brittle to scenarios with few interactions.
Approach:	They propose a Few-shot learning method for Cold-Start recommendation that consists of three hierarchical structures that are local and global .
Outcome:	The proposed method improves on two public real-world datasets and is stable compared with the state-of-the-art.

Copied to clipboard

Qianwen Ma, Chunyuan Yuan, Wei Zhou, Songlin Hu

Information Extraction & Text Mining

Challenge:	Existing studies for multi-label text classification do not explore label-specific semantic components from documents.
Approach:	They propose a label-specific dual graph neural network that incorporates category information to learn label-related components from documents.
Outcome:	The proposed model outperforms state-of-the-art models on three benchmark datasets and achieves better performance with respect to tail labels.

OpenRLHF: A Ray-based Easy-to-use, Scalable and High-performance RLHF Framework (2025.emnlp-demos)

Copied to clipboard

Jian Hu, Xibin Wu, Wei Shen, Jason Klein Liu, Weixun Wang, Songlin Jiang, Haoran Wang, Hao Chen, Bin Chen, Wenkai Fang, null Xianyu, Yu Cao, Haotian Xu, Yiming Liu

AMOA: Global Acoustic Feature Enhanced Modal-Order-Aware Network for Multimodal Sentiment Analysis (2022.coling-1)

Challenge:	Existing RLHF frameworks face inference bottlenecks and complexity barriers restricting their accessibility for newcomers.
Approach:	They propose an open-source RLHF framework that can be used to train large language models.
Outcome:	The proposed framework achieves superior training efficiency with speedups ranging from 1.22 to 1.68 across different model sizes compared to state-of-the-art frameworks, while requiring significantly fewer lines of code for implementation.

Copied to clipboard

Ziming Li, Yan Zhou, Weibo Zhang, Yaxin Liu, Chuanpeng Yang, Zheng Lian, Songlin Hu

Impartial Multi-task Representation Learning via Variance-invariant Probabilistic Decoding (2025.acl-long)

Challenge:	Existing methods treat three modal features equally, without distinguishing the importance of different modalities. Existing models split the video into frames, leading to missing the global acoustic information.
Approach:	They propose a global Acoustic feature enhanced Modal-Order-Aware network to address these problems.
Outcome:	The proposed model outperforms state-of-the-art models on two public datasets.

Copied to clipboard

Dou Hu, Lingwei Wei, Wei Zhou, Songlin Hu

InfoCSE: Information-aggregated Contrastive Learning of Sentence Embeddings (2022.findings-emnlp)

Challenge:	Existing methods focus on balancing loss or gradients but fail to address this issue due to the representation discrepancy in latent space.
Approach:	They propose a framework that harmonizes representation spaces across tasks to ensure impartial learning by harmonizing representation spaces.
Outcome:	The proposed framework outperforms 12 representative methods under the same multi-task settings, especially in heterogeneous task combinations and data-constrained scenarios.

Copied to clipboard

Xing Wu, Chaochen Gao, Zijia Lin, Jizhong Han, Zhongyuan Wang, Songlin Hu