Papers by Aixin Sun
From Speculation Detection to Trustworthy Relational Tuples in Information Extraction (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on speculation detection are defined at sentence level, but not all factual tuples extracted from a sentence are speculative. |
| Approach: | They propose to study speculations in OIE tuples and determine whether a tample is speculative. |
| Outcome: | The proposed model is based on the LSOIE dataset and provides labels for speculative tuples. |
Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings (2025.findings-acl)
Copied to clipboard
Yubo Ma, Jinsong Li, Yuhang Zang, Xiaobao Wu, Xiaoyi Dong, Pan Zhang, Yuhang Cao, Haodong Duan, Jiaqi Wang, Yixin Cao, Aixin Sun
| Challenge: | Visualized Document Retrieval (VDR) uses large vision-language models to encode document pages into embeddings. |
| Approach: | They evaluate methods to reduce patch embeddings per page while minimizing performance degradation. |
| Outcome: | The proposed method maintains 98.2% of retrieval performance with only 11.8% of original memory usage and preserves 94.6% effectiveness at 2% memory footprint. |
Robust Representation Learning of Biomedical Names (P19-1)
Copied to clipboard
| Challenge: | Biomedical concepts are often mentioned in medical documents under different name variations. |
| Approach: | They propose a framework for learning robust representations of biomedical names and terms . they encode contextual meaning, conceptual meaning, and similarity between synonyms . |
| Outcome: | The proposed framework outperforms baselines on retrieval, similarity and relatedness benchmarks. |
On Context Utilization in Summarization with Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models excel in abstractive summarization tasks, delivering fluent and pertinent summaries. |
| Approach: | They conduct the first comprehensive study on context utilization and position bias in summarization. |
| Outcome: | The proposed benchmark compares two methods to alleviate position bias in summarization tasks. |
DocOIE: A Document-level Context-Aware Dataset for OpenIE (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing solutions focus on extracting tuples at sentence level, but sentences exist as part of a document rather than standalone. |
| Approach: | They propose to annotate 800 sentences from 80 documents to form a DocOIE dataset . they propose to use document-level context to improve OpenIE performance . |
| Outcome: | The proposed OpenIE model improves performance by incorporating documentlevel context into the dataset. |
CofeNet: Context and Former-Label Enhanced Net for Complicated Quotation Extraction (2022.coling-1)
Copied to clipboard
| Challenge: | Existing solutions for quotation extraction use rule-based approaches and sequence labeling models. |
| Approach: | They propose a Context and Former-Label Enhanced Net for quotation extraction. |
| Outcome: | The proposed method achieves state-of-the-art performance on complicated quotation extraction on two public datasets and one proprietary dataset. |
If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs (2026.acl-long)
Copied to clipboard
Siqi Fan, Xiusheng Huang, Yiqun Yao, Xuezhi Fang, Kang Liu, Peng Han, Shuo Shang, Aixin Sun, Yequan Wang
| Challenge: | Existing benchmarks for large language models (LLMs) fail to capture these dynamics, focusing on static, open-ended evaluations. |
| Approach: | They propose a benchmark to assess lifelong learning in large language models . they use two episodic datasets rich in narrative structure and character interactions . |
| Outcome: | Experiments on LLMs show that non-parametric methods outperform parametric ones in managing stateful learning. |
Span-based Localizing Network for Natural Language Video Localization (2020.acl-main)
Copied to clipboard
| Challenge: | Existing approaches to NLVL are either ranking tasks or regressing the target video span. |
| Approach: | They propose a video span localizing network to solve a natural language video localization task using a span-based QA approach. |
| Outcome: | The proposed network outperforms the state-of-the-art methods on three benchmark datasets. |
FinMaster: A Holistic Benchmark for Full-Pipeline Financial Management with Large Language Models (2026.findings-acl)
Copied to clipboard
Junzhe Jiang, Chang Yang, Aixin Cui, Sihan Jin, Yujing Zhang, Yilin Xiao, Ruiyu Wang, Bo Li, Xiao Huang, Danny Dongning Sun, Xinrun Wang
| Challenge: | Existing benchmarks lack domain-specific data, realistic workflow-level task design, and standardized workflow- level evaluation. |
| Approach: | a new benchmark evaluates large language models on financial management workflows . the global financial services market is projected to grow to $37 trillion by 2027 . |
| Outcome: | a new benchmark for large language models on financial management workflows reveals critical capability gaps . accuracy drops from 90% on basic tasks to 40% on complex scenarios requiring multi-step reasoning . the global financial services market reached $25.8 trillion in 2022 and is projected to grow to $37 trillion by 2027 . |
Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script Generation (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing work assumes that events are sequentially arranged in a script, while this assumption leads to linear generation that is far from sufficient for comprehensively acquiring the representation about how events are organized towards a task goal. |
| Approach: | They propose to extend goal-oriented Script Generation task from the perspective of cognitive theory by incorporating subgoals into hierarchical script generation. |
| Outcome: | The proposed task is based on a new dataset and human evaluation metrics. |
Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples! (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models have made remarkable strides in various tasks, but whether they are competitive few-shot solvers remains an open question. |
| Approach: | They propose an adaptive filter-then-rerank paradigm to combine the strengths of LLMs and SLMs. |
| Outcome: | The proposed system achieves promising improvements on various IE tasks with acceptable time and cost investment. |
MS-DETR: Natural Language Video Localization with Sampling Moment-Moment Interaction (2023.acl-long)
Copied to clipboard
| Challenge: | Natural language video localization (NLVL) aims to localize a temporal moment from an untrimmed video that semantically corresponds to a given text query. |
| Approach: | They propose a proposal-based solution that generates proposals and selects the best matching proposal. |
| Outcome: | The proposed solution is faster than existing approaches on three public datasets. |
Humans Need Context, What about Machines? Investigating Conversational Context in Abusive Language Detection (2024.lrec-main)
Copied to clipboard
| Challenge: | In this paper, we examine the role of conversational context in abusive language detection . prior studies have ignored the contextual nature of abusive language, ignoring this aspect . toxicity, hate speech, harmful stereotypes are among the forms of harmful language . |
| Approach: | They propose to use conversational context to analyze abusive language detection using two methods . they use "abusive language" as an umbrella term to refer to various forms of harmful language . |
| Outcome: | The proposed approach is based on two datasets in English and a new dataset of French tweets annotated for hate speech and stereotypes. |
MMEKG: Multi-modal Event Knowledge Graph towards Universal Representation across Modalities (2022.acl-demo)
Copied to clipboard
Yubo Ma, Zehao Wang, Mukai Li, Yixin Cao, Meiqi Chen, Xinze Li, Wenqi Sun, Kunquan Deng, Kun Wang, Aixin Sun, Jing Shao
| Challenge: | Recent Knowledge Graphs (KGs) store billions of world facts in a directed graph, but expression ability of such entity-centric KGs is limited. |
| Approach: | They propose a large-scale multi-modal event knowledge graph named MMEKG that unifies different modalities of knowledge via events. |
| Outcome: | The proposed system unifies different modalities of knowledge via events, which complement and disambiguate each other. |
Negation Scope Refinement via Boundary Shift Loss (2023.findings-acl)
Copied to clipboard
| Challenge: | Negation detection is a complex linguistic phenomenon with long spans . existing methods tend to make wrong predictions around the scope boundaries . |
| Approach: | They propose a model which engages the Boundary Shift Loss to refine the predicted boundary. |
| Outcome: | The proposed model refines the predicted boundary on multiple datasets. |
Subtopic-driven Multi-Document Summarization (D19-1)
Copied to clipboard
| Challenge: | Experimental results show that the proposed model outperforms state-of-the-art methods on benchmark datasets. |
| Approach: | They propose a multi-document summarization model that assumes a set of documents to be summarized is on the same topic. |
| Outcome: | The proposed model outperforms state-of-the-art methods on benchmark datasets. |
CORT: A New Baseline for Comparative Opinion Classification by Dual Prompts (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Comparative opinion classification is a common linguistic phenomenon. |
| Approach: | They propose a framework for comparative opinion classification using embedded knowledge in pre-trained language models. |
| Outcome: | The proposed framework delivers state-of-the-art and robust performance on all benchmark datasets. |
ChID: A Large-scale Chinese IDiom Dataset for Cloze Test (P19-1)
Copied to clipboard
| Challenge: | cloze-style reading comprehension in Chinese is limited due to the lack of various corpora. |
| Approach: | They propose a large-scale Chinese cloze test dataset ChID which studies the comprehension of idiom in Chinese. |
| Outcome: | The proposed dataset compares the performance of the proposed model with human models. |
Can LLM Safety Be Ensured by Constraining Parameter Regions? (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are often assumed to contain parameter subsets whose modification directly influences safety behaviors. |
| Approach: | They evaluate four methods to identify parameter subsets with "safety regions" they find low overlap, but overlap drops when refinement is done using utility datasets . |
| Outcome: | The proposed methods show low overlap and drop significantly when refined using utility datasets. |
Parallel Attention Network with Sequence Matching for Video Grounding (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to video grounding are sensitive to quality of proposals and inefficient because all proposal-query pairs are compared. |
| Approach: | They propose a Parallel Attention Network with Sequence matching to capture selfmodal contexts and cross-modal attentive information between video and text. |
| Outcome: | The proposed approach is superior to state-of-the-art methods on three datasets. |
Towards Verifiable Generation: A Benchmark for Knowledge-aware Language Model Attribution (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation metrics and benchmarks to attribute large language models to structured knowledge are lacking. |
| Approach: | They propose a task of Knowledge-aware Language Model Attribution that improves upon three core concerns with conventional attributed LMs. |
| Outcome: | The proposed model improves upon core concerns with conventional attributed LMs. |
Syntactic Multi-view Learning for Open Information Extraction (2022.emnlp-main)
Copied to clipboard
| Challenge: | Open Information Extraction (OpenIE) aims to generate structured tuples from unstructured open-domain text. |
| Approach: | They propose to model constituency and dependency trees into word-level graphs and combine them with sentential semantic representations to extract relational tuples. |
| Outcome: | The proposed model integrates constituency and dependency trees into word-level graphs and enables neural OpenIE to learn from syntactic structures. |
Parameter-Efficient Conversational Recommender System as a Language Processing Task (2024.eacl-long)
Copied to clipboard
| Challenge: | Existing methods to recommend items are categorized into attribute-based and generation-based methods. |
| Approach: | They propose to represent items in natural language and formulate a conversational recommender system that can be optimized in a single stage without relying on non-textual metadata. |
| Outcome: | The proposed model can be optimized in a single stage, without relying on non-textual metadata such as a knowledge graph. |
A Synthetic Data Generation Framework for Grounded Dialogues (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to train grounded dialogues require large amounts of data. |
| Approach: | They propose a synthetic data generation framework for grounded dialogues that takes knowledge data and heuristics to determine a dialogue flow and incrementally turn it into a dialog. |
| Outcome: | The proposed framework significantly boosts model performance in training data and low-resource scenarios. |
SciAgent: Tool-augmented Language Models for Scientific Reasoning (2024.emnlp-main)
Copied to clipboard
Yubo Ma, Zhibin Gou, Junheng Hao, Ruochen Xu, Shuohang Wang, Liangming Pan, Yujiu Yang, Yixin Cao, Aixin Sun
| Challenge: | SciAgent surpasses other LLMs with the comparable size by more than 8.0% in absolute accuracy. |
| Approach: | They propose a tool-augmented scientific reasoning setting that supplements LLMs with scalable toolsets and builds a benchmark to evaluate LLM’s abilities with tool assistance. |
| Outcome: | The proposed setting augments LLMs with scalable toolsets and shifts the focus from pursuing an omniscient problem solver to a proficient tool-user. |
A Dual-Channel Framework for Sarcasm Recognition by Detecting Sentiment Conflict (2022.findings-naacl)
Copied to clipboard
| Challenge: | Sarcasm employs ambivalence, where one says something positive but actually means negative . linguistically, it is difficult to recognize such sentiment conflict because the sentiments are mixed or even implicit . |
| Approach: | They propose a Dual-Channel Framework to model literal and implied sentiments separately . they propose sarcastic networks that can detect sarcasm sentiments in political debates . |
| Outcome: | The proposed framework achieves state-of-the-art on political debates and Twitter datasets. |
Open Information Extraction via Chunks (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing OIE systems split a sentence into tokens and recognize token spans as tuple relations and arguments. |
| Approach: | They propose to split a sentence into tokens and recognize token spans as tuple relations and arguments. |
| Outcome: | The proposed model achieves state-of-the-art on multiple OIE datasets showing that SaC has better properties than sentence as token sequence. |
Dipping PLMs Sauce: Bridging Structure and Text for Effective Knowledge Graph Completion via Conditional Soft Prompting (2023.findings-acl)
Copied to clipboard
| Challenge: | Knowledge Graph Completion (KGC) often requires both KG structural and textual information to be effective. |
| Approach: | They propose a system which tunes the parameters of Conditional Soft Prompts generated by entities and relations representations to maintain a balance between textual and structural knowledge. |
| Outcome: | The proposed components outperform baseline models on three static and temporal benchmarks. |
Few-shot Event Detection: An Empirical Study and a Unified View (2023.acl-long)
Copied to clipboard
| Challenge: | Extensive studies have been carried out on fewshot event detection (ED) however, there are noticeable discrepancies among existing methods from three aspects. |
| Approach: | They propose a unified view of ED models and a better unified baseline for fair evaluation. |
| Outcome: | The proposed framework outperforms existing methods by a large margin on three datasets. |