Papers by Jing He
Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models (2025.acl-long)
Copied to clipboard
Yingshui Tan, Boren Zheng, Baihui Zheng, Kerui Cao, Huiyun Jing, Jincheng Wei, Jiaheng Liu, Yancheng He, Wenbo Su, Xiaoyong Zhu, Bo Zheng, Kaifu Zhang
| Challenge: | Large language models have created significant safety concerns . factuality ability is crucial in determining whether they can be deployed and applied safely and compliantly within specific regions. |
| Approach: | They propose a benchmark to evaluate the factuality of large language models in China . they evaluate the models' ability to provide accurate and reliable information . |
| Outcome: | The proposed benchmark evaluates the factuality abilities of existing LLMs and compares them to LLM abilities. |
MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming (2025.acl-long)
Copied to clipboard
| Challenge: | Existing jailbreak techniques rely on single-round interactions, pro-Corresponding author. |
| Approach: | They propose a multi-turn safety alignment framework to address the challenge of securing large language models in multi-round interactions. |
| Outcome: | The proposed framework exhibits state-of-the-art attack capabilities while improving safety performance on safety benchmarks. |
CORD: Bridging the Audio–Text Reasoning Gap via Weighted On-policy Cross-modal Distillation (2026.findings-acl)
Copied to clipboard
Hu Jing, Danxiang Zhu, Xianlong Luo, Dan Zhang, Shuwei He, Yishu Lei, Shikun Feng, Hai-Tao Zheng, Jingzhou HE, Yu Sun, Hua Wu, Haifeng Wang
| Challenge: | Large Audio Language Models (LALMs) exhibit a degradation in knowledge and reasoning capabilities . empirical results show that CORD significantly bridges the audio–text performance gap . |
| Approach: | They propose a framework that performs online cross-modal self-distillation to bridge the acoustic-semantic gap between LALMs and text-based models. |
| Outcome: | The proposed framework bridges the acoustic-semantic gap between LALMs and text-based models . it employs on-policy reverse KL divergence with importance-aware weighting . |
Infusing Hierarchical Guidance into Prompt Tuning: A Parameter-Efficient Framework for Multi-level Implicit Discourse Relation Recognition (2023.acl-long)
Copied to clipboard
| Challenge: | Multi-level implicit discourse relation recognition (MIDRR) aims at identifying hierarchical discourse relations among arguments. |
| Approach: | They propose a prompt-based multi-level implicit discourse relation recognition framework that leverages parameter-efficient prompt tuning to drive inputted arguments to match the pre-trained space. |
| Outcome: | The proposed framework achieves comparable results on PDTB 2.0 and 3.0 using about 0.1% trainable parameters compared with baselines. |
SwiftPrune: Hessian-Free Weight Pruning for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a novel post-training pruning method relies on the Hessian matrix to perform pruning . current pruning methods are computationally intensive and lack performance due to second-order derivative calculations. |
| Approach: | They propose a Hessian-free weight pruning method that reduces computational burden . they use an Exponentially Weighted Moving Average technique to bypass weight sorting . |
| Outcome: | The proposed method achieves hardware-efficient model compression by eliminating computational intensive calculations. |
Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs (P19-1)
Copied to clipboard
| Challenge: | Existing models to tackle multi-hop reading comprehension (RC) are focusing on a single document or paragraph, but they lack the ability to do reasoning across multiple documents. |
| Approach: | They propose a heterogeneous document-entity graph with different types of nodes and edges to solve multi-hop RC problem. |
| Outcome: | The proposed model can do reasoning over the proposed graph with nodes representation initialized with co-attention and self-attention based context encoders. |
Beyond Literal Descriptions: Understanding and Locating Open-World Objects Aligned with Human Intentions (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for visual grounding rely on the assumption that the given expression must be literal . this impedes the practical deployment of agents in real-world scenarios. |
| Approach: | They propose a visual grounding task that uses intention expressions to locate foreground entities . they build a large-scale IVG dataset with free-form intention expression to promote VG . |
| Outcome: | The proposed method is based on a large-scale intention-driven visual-language (V-L) dataset with free-form intention expressions. |
Reflection on Knowledge Graph for Large Language Models Reasoning (2025.findings-acl)
Copied to clipboard
Yigeng Zhou, Wu Li, Yifan Lu, Jing Li, Fangming Liu, Meishan Zhang, Yequan Wang, Daojing He, Honghai Liu, Min Zhang
| Challenge: | Existing methods for supplementing Large Language Models (LLMs) with knowledge graphs often introduce noise in the retrieval and reasoning pipeline, hindering their ability to integrate external knowledge for complex multi-hop question answering. |
| Approach: | They propose a framework to enhance LLMs' reasoning capabilities through reflective engagement with knowledge graphs by Query Decoupling, LLM-Driven Knowledge Graph Exploration, and Inference with Knowledge Reconstruction. |
| Outcome: | The proposed framework integrates external knowledge into LLMs and trains them to leverage this knowledge for answering questions. |
VALU: A Benchmark for Video Anomaly Temporal Localization and Understanding at Multiple Semantic Levels (2026.acl-long)
Copied to clipboard
Yixiao He, Menghao Zhang, Haifeng Sun, Jing Wang, Kangheng Lin, Jinghan Wang, Chenye Xu, Pengfei Ren, Qi Qi, Jingyu Wang
| Challenge: | Recent advances in Video Large Language Models (Video-LLMs) enhance the ability of VAU models to describe and interpret anomalies. |
| Approach: | They propose a benchmark that explicitly defines anomalies across five semantic levels and provides detailed temporal boundaries and detailed textual descriptions for each. |
| Outcome: | The proposed benchmark defines anomalies across five semantic levels and provides detailed descriptions for each. |
SGG: Learning to Select, Guide, and Generate for Keyphrase Generation (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing keyphrase generation approaches synchronously generate present and absent keyphrases without explicitly distinguishing these two categories. |
| Approach: | They propose to deal with present and absent keyphrases separately with different mechanisms by using a hierarchical neural network with a pointing-based selector and a selection-guided generator. |
| Outcome: | The proposed model outperforms baselines on four keyphrase generation tasks and shows extensibility in natural language generation tasks. |
AgentV-RL: Scaling Reward Modeling with Agentic Verifier (2026.findings-acl)
Copied to clipboard
Jiazheng Zhang, Ziche Fu, Zhiheng Xi, Wenqing Jing, Mingxu Chai, Wei He, Guoqiang Zhang, Chenghao Fan, Chenxin An, Wenxiang Chen, Zhicheng Liu, Haojie Pan, Dingwei Zhu, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing approaches to improve LLM reasoning are limited in complex domains and lack external grounding makes verifiers unreliable on computation-intensive tasks. |
| Approach: | They propose a framework that transforms reward modeling into a multi-turn, tool-augmented deliberative process. |
| Outcome: | The proposed framework surpasses state-of-the-art ORMs by 25.2% under parallel and sequential TTS. |
Federated LoRA Fine-Tuning with Pipelined Error-Mitigated Aggregation and Matrix-Wise Freezing (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning large language models often suffer from biased model aggregation and are hindered by significant communication and computation burden. |
| Approach: | They propose a Federated low-rank adaptation system for large language models that leverages pipelined error-mitigated model aggregation and adaptive matrix-wise parameter freezing to mitigate aggregations. |
| Outcome: | The proposed system improves time-to-target by 2.17-8.48 on real-world datasets. |
Leveraging Web-Crawled Data for High-Quality Fine-Tuning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Currently, large language models are fine-tuned using expensive human-annotated data or GPT-4 generated data. |
| Approach: | They propose to use web-crawled data to train a language model on a smaller set of data . their results show that the model can convert web data with irregular formats into high-quality ones . |
| Outcome: | The proposed model outperforms open-source models larger than 32B and outperformed open-sourced models such as GPT-3.5. |
Modularized Interaction Network for Named Entity Recognition (2021.acl-long)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) models focus on word-level information, while segment-based models focus only on word level information. |
| Approach: | They propose a Modularized Interaction Network (MIN) model which utilizes both word-level information and segment-level dependencies. |
| Outcome: | The proposed model outperforms the current state-of-the-art models on three NER benchmark datasets. |
Fine- and Coarse-Granularity Hybrid Self-Attention for Efficient BERT (2022.acl-long)
Copied to clipboard
| Challenge: | Transformer-based pre-trained models achieve state-of-the-art results, but they can be prohibitively costly. |
| Approach: | They propose a fine- and coarse-granularity hybrid self-attention that shortens the computational sequence length in self- attention by progressively shortening the computational time. |
| Outcome: | The proposed model reduces computation cost by shortening the computational sequence length in self-attention. |
Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models (2025.findings-acl)
Copied to clipboard
Yingqian Cui, Pengfei He, Jingying Zeng, Hui Liu, Xianfeng Tang, Zhenwei Dai, Yan Han, Chen Luo, Jing Huang, Zhen Li, Suhang Wang, Yue Xing, Jiliang Tang, Qi He
| Challenge: | Chain-of-Thought (CoT) reasoning has improved the performance of large language models (LLMs) however, the detailed reasoning process in CoT often incurs long generation times and high computational costs due to the inclusion of unnecessary steps. |
| Approach: | They propose a method to identify critical reasoning steps using perplexity as a measure of their importance. |
| Outcome: | The proposed method achieves a better balance between reasoning accuracy and efficiency of CoT. |
Similarizing the Influence of Words with Contrastive Learning to Defend Word-level Adversarial Text Attack (2023.findings-acl)
Copied to clipboard
| Challenge: | Neural language models are vulnerable to word-level adversarial text attacks . previous word-based search methods assume important words influence prediction . |
| Approach: | They propose a method for similarizing the influence of words with contrast learning that encourages model to learn sentence representations in which words of varying importance have a more uniform influence on prediction. |
| Outcome: | The proposed method is compatible with various training methods and improves model robustness against various adversarial attacks. |
FacLens: Transferable Probe for Foreseeing Non-Factuality in Fact-Seeking Question Answering of Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing non-factuality detection methods require response generation, which incurs significant computational overhead. |
| Approach: | They propose a lightweight model called Factuality Lens which effectively probes hidden representations of fact-seeking questions for the NFP task. |
| Outcome: | The proposed model is able to probe hidden representations of fact-seeking questions and reduce development costs. |
Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer (2025.acl-long)
Copied to clipboard
Guodong Du, Zitao Fang, Jing Li, Junlin Li, Runhua Jiang, Shuyang Yu, Yifei Guo, Yangneng Chen, Sim Kuan Goh, Ho-Kin Tang, Daojing He, Honghai Liu, Min Zhang
| Challenge: | Foundational models and their checkpoints have advanced deep learning, boosting performance across applications. |
| Approach: | They propose a method for pruning fine-tuned models by calculating differences between them and original model. |
| Outcome: | The proposed method can improve performance across vision, NLP, and multi-modal benchmarks. |
UICOMPASS: UI Map Guided Mobile Task Automation via Adaptive Action Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Mobile task automation is an emerging technology that leverages AI to automatically execute routine tasks by users’ commands on mobile devices like Android. |
| Approach: | They propose a UI Map-guided LLM-based approach to automate mobile tasks using static analysis and LLMs. |
| Outcome: | The proposed approach achieves a 15.87% higher task execution success rate than SOTA approaches even when only APK is available. |
Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent work on aspect-level sentiment classification has shown that syntactic information is effective in capturing long-range syntaktic relations that are obscure from the surface form. |
| Approach: | They propose a graph ensemble technique that integrates syntactic structures with GNNs to better leverage syntaktic information in the face of parsing errors. |
| Outcome: | The proposed model outperforms models with single dependency tree and beats other models without adding model parameters. |
Natural-Language Policies to Executable Decisions: An Interpretable Large Language Model Framework (2026.acl-industry)
Copied to clipboard
Ziqiang Zhang, Jing Ma, Zilong Wang, Jiayuan Chen, Yi Qiao, Yu He, Wei Zhang, Dai Cheng, Xiaoyu Shen
| Challenge: | a production-grade pricing system for tourism is challenging due to unstructured nature of travel orders and ever-evolving pricing policies. |
| Approach: | They propose a production-grade pricing system with a strict decision boundary . they propose to combine structured extraction and bounded policy/path selection with interpretable condition trees . |
| Outcome: | The proposed system processed 3,960 orders in six months and reduced the order management team from 15-20 to 3 . the system reduced the per-order handling time from 10 minutes to 2 minutes. |
Answer-focused and Position-aware Neural Question Generation (D18-1)
Copied to clipboard
| Challenge: | Recent neural network-based approaches generate interrogative words that do not match the answer type. |
| Approach: | They propose an answer-focused and position-aware neural question generation model to address these issues. |
| Outcome: | The proposed model outperforms the baseline and outperformed the state-of-the-art system. |
Omni-I2C: A Holistic Benchmark for High-Fidelity Image-to-Code Generation (2026.acl-long)
Copied to clipboard
Jiawei Zhou, Chi Zhang, Xiang Feng, Qiming Zhang, Haibo Qiu, Lihuo He, Dengpan Ye, Xinbo Gao, Jing Zhang
| Challenge: | a benchmark is designed to evaluate the capability of Large Multimodal Models (LMMs) in converting complex, structured digital graphics into executable code. |
| Approach: | They propose a benchmark to evaluate the capability of Large Multimodal Models to convert digital graphics into executable code. |
| Outcome: | The proposed benchmark exposes the performance gap among leading LMMs . the benchmark features 1130 meticulously curated samples . |
ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks lack the ability to automatically evaluate from users’ perspective and lack the explainability of the results of LLM agents’ code generation capabilities. |
| Approach: | They propose a new benchmark for LLM agents' automated evaluation by simulating user interaction. |
| Outcome: | The proposed benchmark can evaluate the generated projects by user interaction simulation and by code similarity through existing objective indicators. |
Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data (2026.acl-long)
Copied to clipboard
Yuxuan Lu, Jing Huang, Yan Han, Bingsheng Yao, Sisong Bei, Yaochen Xie, Yisi Sang, Qi He, Dakuo Wang
| Challenge: | Recent research shows that LLM Agents can generate “believable” human behaviors via prompt-only methods, leaving open questions of whether they can accurately generate step-by-step actions in multi-turn interaction tasks. |
| Approach: | They propose to use shopping data to evaluate LLMs' ability to accurately generate step-by-step actions in a multi-turn interaction task. |
| Outcome: | The proposed model achieves 17.26% action generation accuracy and 33.86% F1 score on final purchase prediction, representing improvements of 5.4% and 13.85% over baselines. |
Capability Decomposition for Unified Information Extraction via Hierarchical Mixture-of-Experts (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for IE tasks suffer from inconsistent schema representation and implicitly intermediate reasoning . UC-UIE adopts a low-rank adapted hierarchical Mixture-of-Experts adapter for UIE tasks . |
| Approach: | They propose a framework that decomposes IE reasoning into three universal capabilities . UC-UIE adopts a low-rank Adaptation adapter to fine-tune LLMs for IE tasks . |
| Outcome: | The proposed framework outperforms full-parameter tuning methods with 1.24% trainable parameters and outperformed existing methods in generalization and interpretability. |
MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free (2026.findings-acl)
Copied to clipboard
Yishu Lei, Shuwei He, Hu Jing, Dan Zhang, Xianlong Luo, Danxiang Zhu, Shikun Feng, Rui Liu, Jingzhou HE, Yu Sun, Hua Wu, Haifeng Wang
| Challenge: | Existing research on Large Language Models (LLMs) limited to textual input modality . acoustic information is intrinsically heterogeneous, entangling attributes such as speech, music, and environmental context. |
| Approach: | They propose a sparse Mixture-of-Experts architecture to decouple acoustic information by routing audio tokens to specialized experts. |
| Outcome: | The proposed architecture outperforms existing models on audio semantic and paralinguistic tasks while retaining shared experts for global context. |
Not All Voices Are Rewarded Equally: Probing and Repairing Reward Models across Human Diversity (2025.findings-emnlp)
Copied to clipboard
Zihao Li, Feihao Fang, Xitong Zhang, Jiaru Zou, Zhining Liu, Wei Xiong, Ziwei Wu, Baoyu Jing, Jingrui He
| Challenge: | Using real-world datasets, we conduct the most comprehensive study to date, auditing various state-of-the-art reward models across nine sensitive attributes, including age, gender, ethnicity, etc. |
| Approach: | They propose a method to mitigate group disparities in reward modeling by using real-world data. |
| Outcome: | The proposed method is based on a population-based dataset with nine demographic attributes, including gender, ethnicity, age, gender, and ethnicity. |
MLeVLM: Improve Multi-level Progressive Capabilities based on Multimodal Large Language Model for Medical Visual Question Answering (2024.findings-acl)
Copied to clipboard
Dexuan Xu, Yanyuan Chen, Jieyi Wang, Yue Huang, Hanpin Wang, Zhi Jin, Hongxing Wang, Weihua Yue, Jing He, Hang Li, Yu Huang
| Challenge: | Existing MVQA models ignore multi-level progressive capabilities due to unspecific data and plain architecture. |
| Approach: | They propose a multi-level visual language model for medical visual question answering (MVQA) which covers multi- level questions and answers as well as reasoning processes from visual clues to semantic cognition. |
| Outcome: | The proposed model outperforms existing medical multimodal large language models on a multi-level instruction dataset and a feature alignment module. |
StereoRel: Relational Triple Extraction from a Stereoscopic Perspective (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for relational triple extraction still face challenges, including information loss and error propagation. |
| Approach: | They propose a model which maps relational triples to a three-dimensional space and leverages three decoders to extract them. |
| Outcome: | The proposed model outperforms the baselines on five public datasets. |
ECC: Synergizing Emotion, Cause and Commonsense for Empathetic Dialogue Generation (2025.coling-main)
Copied to clipboard
| Challenge: | Empathy improves human-machine dialogue systems by enhancing the user's experience. |
| Approach: | They propose a framework that leverages specialized encoders to capture the key features of emotion, cause, and commonsense and collaboratively models these through a Conditional Variational Auto-Encoder. |
| Outcome: | Empirical results show that the framework outperforms baseline models and offers a robust solution for empathetic dialogue generation. |
Multi-Modality Expansion and Retention for LLMs through Parameter Merging and Decoupling (2025.acl-long)
Copied to clipboard
Junlin Li, Guodong Du, Jing Li, Sim Kuan Goh, Wenya Wang, Yequan Wang, Fangming Liu, Ho-Kin Tang, Saleh Alharbi, Daojing He, Min Zhang
| Challenge: | Large Language Models (LLMs) are a cornerstone in artificial intelligence due to their exceptional performance. |
| Approach: | They propose a training-free approach that integrates existing MLLMs for effective multimodal expansion while retaining their original performance. |
| Outcome: | The proposed approach can expand LLMs' multimodal capabilities while retaining original performance. |
RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems (2025.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to combat character hallucination are vulnerable to attack . large language models (LLMs) are capable of generating responses inconsistent with intended personas . |
| Approach: | They propose a novel defence strategy that generates supplemental context through narration to mitigate role-query conflicts and improve query generalization. |
| Outcome: | The proposed defence strategy outperforms refusal-based strategies in character hallucinations and query generalization. |
GraDaSE: Graph-Based Dataset Search with Examples (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods address ad hoc dataset search, but dataset search presents in diverse and complex forms. |
| Approach: | They propose a graph-based approach to retrieve relevant datasets from textual queries . they identify provenance-based and topic-based relationships to construct a diagram . |
| Outcome: | The proposed approach outperforms strong baselines on two test collections. |
Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding (2020.acl-main)
Copied to clipboard
| Challenge: | Existing knowledge graph embeddings have improved the knowledge graph link prediction task, but complex relations such as N-to-1, 1-to-N and N- to-N remain challenging to predict. |
| Approach: | They propose to extend RotatE from 2D complex domain to high dimensional space with orthogonal transforms to model relations. |
| Outcome: | The proposed method improves on N-to-1, 1-to-N and N- to-N cases while maintaining the capability for modeling symmetric/anti-symmetric, inverse and compositional relations. |
Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification (P18-1)
Copied to clipboard
| Challenge: | Recent years have seen rapid growth in the MRC community . MRC is believed to be a crucial step in building a general intelligent agent . |
| Approach: | They propose an end-to-end neural model that enables multiple passages to verify each other based on their content representations. |
| Outcome: | The proposed model outperforms the baseline on the English MS-MARCO dataset and the Chinese DuReader dataset, and achieves state-of-the-art performance on both datasets. |
DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models (2025.naacl-long)
Copied to clipboard
Jianyu Liu, Hangyu Guo, Ranjie Duan, Xingyuan Bu, Yancheng He, Shilong Li, Hui Huang, Jiaheng Liu, Yucheng Wang, Chenchen Jing, Xingwei Qu, Xiao Zhang, Pei Wang, Yanan Wu, Jihao Gu, Yangguang Li, Jianke Zhu
| Challenge: | Multimodal Large Language Models (MLLMs) pose unique safety challenges due to their integration of visual and textual data. |
| Approach: | They propose a method to disentangle risks through step-by-step reasoning within multimodal inputs. |
| Outcome: | The proposed approach improves safety alignment in MLLMs by fine-tuning and iterative Reinforcement Learning from AI feedback. |
A Simple and Efficient Learning-Style Prompting for LLM Jailbreaking (2026.findings-eacl)
Copied to clipboard
| Challenge: | Learning-style queries can reliably elicit harmful responses, highlighting a critical safety blind spot in modern LLMs. |
| Approach: | They propose a new reframing paradigm that hides intention by learning from LLMs and uses 4 conceptual components to construct learning-style queries. |
| Outcome: | The proposed framework achieves top attack success rates on most models and across malicious categories while maintaining high efficiency with concise prompts. |
RoR: Read-over-Read for Long Document Machine Reading Comprehension (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models for machine reading comprehension are limited to individual chunks due to encoding length constraint. |
| Approach: | They propose a read-over-read method that expands the reading field from chunk to document by predicting regional answers for each chunk. |
| Outcome: | Extensive experiments on QuAC and TriviaQA show that the proposed model performs well for long document reading. |
OPERA: Operation-Pivoted Discrete Reasoning over Text (2022.naacl-main)
Copied to clipboard
Yongwei Zhou, Junwei Bao, Chaoqun Duan, Haipeng Sun, Jiahui Liang, Yifan Wang, Jing Zhao, Youzheng Wu, Xiaodong He, Tiejun Zhao
| Challenge: | Existing methods to predict logical forms ignore the utilization of symbolic operations and lack reasoning ability and interpretability. |
| Approach: | They propose an operation-pivoted discrete reasoning framework that uses symbolic operations as neural modules to facilitate reasoning ability and interpretability. |
| Outcome: | Extensive experiments on DROP and RACENum datasets show the reasoning ability of OPERA. |
LMR-BENCH: Evaluating LLM Agent’s Ability on Reproducing Language Modeling Research (2025.emnlp-main)
Copied to clipboard
Shuo Yan, Ruochen Li, Ziming Luo, Zimu Wang, Daoyang Li, Liqiang Jing, Kaiyu He, Peilin Wu, Juntong Ni, George Michalopoulos, Yue Zhang, Ziyang Zhang, Mian Zhang, Zhiyu Chen, Xinya Du
| Challenge: | Large language model (LLM) agents have demonstrated remarkable potential in advancing scientific discovery, but their capability in reproducing code from research papers remains underexplored. |
| Approach: | They propose to evaluate LLM agents' ability to reproduce scientific research papers by analyzing code reproduction tasks from 23 research papers published in top-tier NLP venues. |
| Outcome: | The proposed benchmark systematically evaluates the capability of large language model (LLM) agents on code reproduction from Language Modeling Research. |
Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision? (2025.acl-long)
Copied to clipboard
| Challenge: | Graph Neural Networks (GNNs) with CLIP pipeline are difficult because of the scarcity of labeled data and text supervision, different levels of downstream tasks, and conceptual gaps between domains. |
| Approach: | They propose a multi-modal prompt learning paradigm to adapt pre-trained GNNs to downstream tasks with weak text supervision. |
| Outcome: | The proposed model can generalize graphs to unseen classes with weak text supervision. |
ViPE: Visual Perception in Parameter Space for Efficient Video-Language Understanding (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing video-language models rely on concatenating visual tokens with textual inputs for joint modeling, but this method suffers from significant inefficiency when scaling to long videos with dense visual inputs. |
| Approach: | They propose a video-to-parameter efficiency paradigm called ViPE that transforms video content into visual perceptual weights, which are directly injected into the LLM’s parameters. |
| Outcome: | The proposed model reduces FLOPs by 85% and inference time by up to 65% while reducing FLOP and FLOP inference times by up-to-65%. |
P3LM: Probabilistically Permuted Prophet Language Modeling for Generative Pre-Training (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing autoregressive left-to-right (L2R) models are limited to unidirectional information and constrained on strong local dependencies. |
| Approach: | They propose a probabilistically permuted prophet language model which strengthens the modeling of bidirectional information and long token dependencies for sequence generation. |
| Outcome: | Experiments on GLGE dataset show that P3LM improves on natural language generation tasks. |
LUNA: Learning Slot-Turn Alignment for Dialogue State Tracking (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing methods exploit the utterances of all dialogue turns to assign value to slots . this can lead to suboptimal results due to information introduced from irrelevant utterrances . |
| Approach: | They propose a SLot-TUrN Alignment enhanced approach to assign slot value . they explicitly align each slot with its most relevant utterance and then predict the corresponding value based on this aligned utteration. |
| Outcome: | The proposed approach achieves state-of-the-art on three multi-domain task-oriented dialogue datasets. |
Global and Local Hierarchical Prompt Tuning Framework for Multi-level Implicit Discourse Relation Recognition (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent methods to recognize hierarchical discourse relations without explicit connectives are inefficient and ignore the utilization of the output probability distribution information of the verbalizer. |
| Approach: | They propose a global and local hierarchical prompt tuning framework which leverages top-up propagated probability as the global hierarchy to inject it into multi-level verbalizer. |
| Outcome: | The proposed framework achieves competitive results on two benchmacks. |
A Pretraining Numerical Reasoning Model for Ordinal Constrained Question Answering on Knowledge Base (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing knowledge bases (KBs) can explicitly facilitate the QA process. |
| Approach: | They propose a numerical reasoning model pretraining NumGNN and NumTransformer, guided by explicit self-supervision signals, to enhance numerical reasoning ability for IR-based KBQA models. |
| Outcome: | Extensive experiments on two KBQA benchmarks confirm the effectiveness of the proposed model. |
Rethinking Word-level Adversarial Attack: The Trade-off between Efficiency, Effectiveness, and Imperceptibility (2024.lrec-main)
Copied to clipboard
| Challenge: | Neural language models have demonstrated impressive performance but remain vulnerable to word-level adversarial attacks. |
| Approach: | They propose two standardized search spaces to address the problem of word-level adversarial attacks. |
| Outcome: | The proposed search spaces improve performance and trade-offs in different scenarios. |
Evaluating and Mitigating Object Hallucination in Large Vision-Language Models: Can They Still See Removed Objects? (2025.naacl-long)
Copied to clipboard
| Challenge: | LVLMs often mistakenly determine objects as present in images where they do not exist . authors propose a new benchmark to evaluate object hallucinations by removing objects from images and asking the model whether it can still see the removed objects. |
| Approach: | They propose a benchmark to evaluate object hallucinations by removing objects from images . they propose oDPO, a direct preference optimization objective based on visual objects . |
| Outcome: | The proposed benchmark reduces the likelihood of object hallucinations by removing objects from images and asking the model whether it can still see the removed objects. |
Safety Alignment via Constrained Knowledge Unlearning (2025.acl-long)
Copied to clipboard
Zesheng Shi, Yucheng Zhou, Jing Li, Yuxin Jin, Yu Li, Daojing He, Fangming Liu, Saleh Alharbi, Jun Yu, Min Zhang
| Challenge: | Existing defense mechanisms have not fully deleted harmful knowledge in large language models (LLMs) Existing methods to address safety alignment have not completely deleted harmful information in LLMs. |
| Approach: | They propose a safety alignment strategy that uses scoring neurons to identify useful knowledge in LLMs and pruning the gradients of neurons in U to preserve beneficial information. |
| Outcome: | The proposed method significantly improves model safety while maintaining utility compared to existing methods. |
E3-TIR: Enhanced Experience Exploitation for Tool-Integrated Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing training paradigms for Large Language Models (LLMs) suffer from inefficient exploration and mode degradation due to a lack of prior guidance, while SFT-then-RL is limited by high data costs and capability plateaus caused by low-entropy collapse. |
| Approach: | They propose an Enhanced Experience Exploitation paradigm that integrates expert prefixes, expert guided, and self-exploration to improve agent training. |
| Outcome: | The proposed model achieves a 6% performance improvement over traditional paradigms on tool-use tasks while requiring less than 10% of the synthetic data. |