TEXT UNDERSTANDING

Automatic Assessment of Conceptual Text Complexity Using Knowledge Graphs (C18-1)

Challenge:	Recent coreference resolvers have notable improvements on the CoNLL evaluation sets, but struggle to generalize properly to new datasets.
Approach:	They investigate the role of linguistic features in building more generalizable coreference resolvers . they show that employing features and subsets of their values that are informative for coreference resolution improves generalization .
Outcome:	The proposed system achieves state-of-the-art results on WikiCoref, compared with a system trained on CoNLL.

Copied to clipboard

Sanja Štajner, Ioana Hulpuş

Reverse Modeling in Large Language Models (2025.naacl-short)

Challenge:	Existing methods to assess text complexity only at lexical and syntactic levels have not been attempted.
Approach:	They propose to automatically estimate conceptual complexity using graph-based measures on a large knowledge base.
Outcome:	The proposed measures achieve high discriminative power even in a default setup.

Copied to clipboard

Sicheng Yu, Xu Yuanchen, Cunxiao Du, Yanying Zhou, Minghui Qiu, Qianru Sun, Hao Zhang, Jiawei Wu

LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linking (2021.acl-long)

Challenge:	Using pre-trained LLMs with reversed text inputs can improve their performance across multiple languages.
Approach:	They propose a way to determine whether LLMs can understand reversed text inputs by reversing entire paragraphs or documents at the token level.
Outcome:	The proposed model can be used to improve understanding across multiple languages.

Copied to clipboard

Hang Jiang, Sairam Gurajada, Qiuhao Lu, Sumit Neelam, Lucian Popa, Prithviraj Sen, Yunyao Li, Alexander Gray

When Shallow is Good Enough: Automatic Assessment of Conceptual Text Complexity using Shallow Semantic Features (2020.lrec-1)

Challenge:	Existing work deals with EL in the context of longer text, such as a sentence.
Approach:	They propose a neuro-symbolic approach that uses interpretable rules based on first-order logic to achieve better performance with black-box neural approaches.
Outcome:	The proposed approach achieves better performance than heuristics-based approaches on short-text EL . it can easily blend existing rule templates with multiple types of features, and even with scores resulting from previous EL methods.

Copied to clipboard

Sanja Stajner, Ioana Hulpuș

CTTA-T: Continual Test-Time Adaptation for Text Understanding via Teacher-Student with a Domain-aware and Generalized Teacher (2026.acl-long)

Challenge:	Existing approaches to automatic assessment of text complexity focus on syntactic and lexical complexity.
Approach:	They propose to use graph-based deep semantic features to automatically assess conceptual text complexity by using DBpedia as a proxy to human knowledge.
Outcome:	The proposed features outperform the state-of-the-art features on pairwise comparison of two versions of the same text and five-level classification task.

Copied to clipboard

Tianlun Liu, Zhiliang Tian, Zhen Huang, Xingzhi Zhou, Wanlong Yu, Tianle Liu, Feng Liu, Dongsheng Li

Responsible & Trustworthy NLP

Challenge:	Existing models for text understanding fail to adapt to domain shifts in real-world applications . current models do not improve themselves as they are applied to new domains .
Approach:	They propose a continual test-time adaptation framework that adapts to evolving domains . they propose accumulating domains and a refine-then-filter framework to calibrate teacher predictions .
Outcome:	The proposed model excels in a teacher-student framework adaptable to evolving domains.

Domain-Specific NER via Retrieving Correlated Samples (2022.coling-1)

Copied to clipboard

Xin Zhang, Yong Jiang, Xiaobin Wang, Xuming Hu, Yueheng Sun, Pengjun Xie, Meishan Zhang

Incorporating Syntax and Frame Semantics in Neural Network for Machine Reading Comprehension (2020.coling-main)

Challenge:	Successful Named Entity Recognition models fail on texts from some special domains, for example, Chinese addresses and e-commerce titles.
Approach:	They propose to enhance NER models with correlated samples to help the text understanding . they draw correlated texts by the sparse BM25 retriever from large-scale in-domain unlabeled data .
Outcome:	Empirical results show that NER models can be enhanced with correlated samples . the proposed model can be used to reason out the correct answer on hard cases .

Copied to clipboard

Shaoru Guo, Yong Guan, Ru Li, Xiaoli Li, Hongye Tan

Syntactic Text Processing

Challenge:	Existing methods for machine reading comprehension rely on manually defined features and are difficult to generalize to other tasks.
Approach:	They propose a Syntax and Frame Semantics model for Machine Reading Comprehension which takes full advantage of syntax and frame semantics to get richer text representation.
Outcome:	The proposed model outperforms ten state-of-the-art models on machine reading comprehension tasks.

What Does This Acronym Mean? Introducing a New Dataset for Acronym Identification and Disambiguation (2020.coling-main)

Copied to clipboard

Amir Pouran Ben Veyseh, Franck Dernoncourt, Quan Hung Tran, Thien Huu Nguyen

Challenge:	Acronyms are short forms of phrases that facilitate conveying lengthy sentences in documents.
Approach:	They propose to annotate a large dataset for scientific domain and a new deep learning model which expands an ambiguous acronym in a sentence.
Outcome:	The proposed model outperforms the state-of-the-art models on the new dataset.

Forgetting before Learning: Utilizing Parametric Arithmetic for Knowledge Updating in Large Language Models (2024.acl-long)

Copied to clipboard

Shiwen Ni, Dingwei Chen, Chengming Li, Xiping Hu, Ruifeng Xu, Min Yang

Automated Evaluation of Out-of-Context Errors (L18-1)

Challenge:	Existing methods of model editing and knowledge updating add additional network parameters, knowledge bases, knowledge base, and model parameters.
Approach:	They propose a new paradigm for fine-tuning called F-Learning that employs parametric arithmetic to facilitate the forgetting of old knowledge and learning of new knowledge.
Outcome:	The proposed model outperforms existing models on two datasets and is comparable to full fine-tuning and LoRA fine-uning.

Copied to clipboard

Patrick Huber, Jan Niehues, Alex Waibel

Challenge:	Existing methods to modify text understanding systems use only one sentence at a time . however, considering a larger context can improve performance for text understanding tasks.
Approach:	They propose to modify existing text data to insert out-of-context errors . they use a 2016 TEDTalk corpus to evaluate computational models for text understanding .
Outcome:	The proposed method targets real-world problems of transcription and translation systems by inserting authentic out-of-context errors.

Zero-Shot Open-Schema Entity Structure Discovery (2026.eacl-long)

Copied to clipboard

Xueqiang Xu, Jinfeng Xiao, James Barry, Mohab Elkaref, Jiaru Zou, Pengcheng Jiang, Yunyi Zhang, Maxwell J Giammona, Geeth De Mel, Jiawei Han

Automatically Building a Multilingual Lexicon of False Friends With No Supervision (2020.lrec-1)

Challenge:	Existing methods based on large language models (LLMs) rely heavily on predefined entity attribute schemas or annotated datasets, often leading to incomplete extraction results.
Approach:	They propose a novel approach to entity structure extraction that does not require any schema or annotated datasets.
Outcome:	Experiments show that ZOES improves LLMs’ ability to extract more complete entity structures across three different domains, showcasing both the effectiveness and generalizability of the method.

Copied to clipboard

Ana Sabina Uban, Liviu P. Dinu

Multilinguality

Challenge:	a method to detect false friends from cognates is developed . cognates are words in genetically related languages with a common proto-word . in some cases, cognates have diverged from the common etymon and their meanings became different from each other.
Approach:	They propose an automatic method to detect false friends from a set of cognates . cognates are words in genetically related languages which derive from etymons . authors propose a measure of "falseness" of a false friends pair based on cross-lingual word embeddings based in the system .
Outcome:	The proposed method can be extended to any language pair, with monolingual corpora and a bilingual dictionary.

Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark (2023.acl-long)

Copied to clipboard

Wenjun Peng, Jingwei Yi, Fangzhao Wu, Shangxi Wu, Bin Bin Zhu, Lingjuan Lyu, Binxing Jiao, Tong Xu, Guangzhong Sun, Xing Xie

Combinatory Grammar Tells Underlying Relevance among Entities (2022.findings-emnlp)

Challenge:	Large language models (LLMs) have demonstrated exceptional abilities in both text understanding and generation.
Approach:	They propose an Embedding Watermark method that implants backdoors on embeddings to protect copyright of large language models.
Outcome:	The proposed method protects the copyright of large language models without compromising service quality while minimizing the adverse impact on the original embeddings’ utility.

Copied to clipboard

Yuanhe Tian, Yan Song

Human vs. Muppet: A Conservative Estimate of Human Performance on the GLUE Benchmark (P19-1)

Challenge:	Existing approaches focus on dependencies among words while paying limited attention to other types of syntactic structure.
Approach:	They propose an alternative approach that takes advantage of combinatory categorial grammar to detect the relation between entities.
Outcome:	The proposed model performs state-of-the-art on two widely used English benchmark datasets.

Copied to clipboard

Nikita Nangia, Samuel R. Bowman

Challenge:	GLUE is a suite of language understanding tasks that has seen dramatic progress in the past year . average performance on the benchmark is 83.9, state of the art at the time of writing .
Approach:	They use crowdsourcing to measure human performance on a set of language understanding tasks and 20 examples to determine whether there is room for improvement.
Outcome:	The GLUE benchmark outperforms state-of-the-art models on six of the nine tasks and achieves an average score of 87.1.

Detecting Subevents using Discourse and Narrative Features (P19-1)

Copied to clipboard

Mohammed Aldawsari, Mark Finlayson

Challenge:	Existing models for detecting events as subevents have been developed for analyzing textual understanding.
Approach:	They propose a supervised model that automatically identifies when one event is a subevent of another.
Outcome:	The proposed model outperforms previous systems on two annotated corpora with event hierarchies, achieving 0.74 BLANC F1 on the Intelligence Community corpus and 0.70 F1 for the HiEve corpus, respectively a 15 and 5 percentage point improvement over previous models.

GSAP-NER: A Novel Task, Corpus, and Baseline for Scholarly Entity Extraction Focused on Machine Learning Models and Datasets (2023.findings-emnlp)

Copied to clipboard

Wolfgang Otto, Matthäus Zloch, Lu Gan, Saurav Karmakar, Stefan Dietze

Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolation (2025.emnlp-main)

Challenge:	Named Entity Recognition (NER) models are crucial for academic writing . existing ground truth datasets do not treat fine-grained types like ML model and model architecture as separate entity types .
Approach:	They propose to annotate 100 full-text scientific publications and a first baseline model for 10 entity types centered around ML models and datasets.
Outcome:	The proposed model can be used to identify 10 entity types in scientific articles . existing models cannot recognize fine-grained models like ML models and model architecture .

Copied to clipboard

Dingwei Chen, Ziqiang Liu, Feiteng Fang, Chak Tou Leong, Shiwen Ni, Ahmadreza Argha, Hamid Alinejad-Rokny, Min Yang, Chengming Li

Stable Signer: Hierarchical Sign Language Generative Model (2026.acl-long)

Challenge:	Existing approaches to generating factually inconsistent outputs are resource-intensive.
Approach:	They propose a plug-and-play intervention designed to enhance factuality by inserting premature layers formed through mathematical interpolation with adjacent layers.
Outcome:	The proposed intervention reduces hallucinations while outperforming baselines on four datasets.

Copied to clipboard

Sen Fang, Yalin Feng, Hongbin Zhong, Yanxin Zhang, Dimitris N. Metaxas

Multimodality

Challenge:	Sign Language Production (SLP) is the process of converting complex input text into a real video.
Approach:	They propose a new sign language generative model that streamlines redundant structure and optimizes the task objective.
Outcome:	The proposed model streamlines redundant structure and optimizes objective . it generates high-quality and multi-style sign language videos with hand gestures .

Learning Interpretable Relationships between Entities, Relations and Concepts via Bayesian Structure Learning on Open Domain Facts (2020.acl-main)

Copied to clipboard

Jingyuan Zhang, Mingming Sun, Yue Feng, Ping Li

Explainability & Interpretability in NLP

Challenge:	Concept graphs are created as universal taxonomies for text understanding in the open domain knowledge.
Approach:	They propose to learn interpretable relationships from open-domain facts to enrich concept graphs.
Outcome:	The proposed method improves the identification of concepts for entities based on relations between entities on public English and Chinese datasets.

FAC2E: Better Understanding Large Language Model Capabilities by Dissociating Language and Cognition (2024.emnlp-main)

Copied to clipboard

Xiaoqiang Wang, Lingfei Wu, Tengfei Ma, Bang Liu

KoRC: Knowledge Oriented Reading Comprehension Benchmark for Deep Text Understanding (2023.findings-acl)

Challenge:	Large language models (LLMs) are evaluated by overall performance on various text understanding and generation tasks.
Approach:	They propose a framework for Fine-grAined and Cognition-grounded LLMs’ Capability Evaluation that dissociates the language-related capabilities from cognition-related ones.
Outcome:	The proposed framework dissociates the language-related capabilities from cognition-related ones and breaks down the process of applying a specific capability into three sub-steps: recalling relevant knowledge, utilizing knowledge, and solving problems.

Copied to clipboard

Zijun Yao, Yantao Liu, Xin Lv, Shulin Cao, Jifan Yu, Juanzi Li, Lei Hou

Reasoning

Challenge:	Existing benchmarks for deep text understanding have encountered two major limitations . most require human annotation of knowledge, which leads to limited knowledge coverage .
Approach:	They propose a benchmark to help readers understand a document with prior knowledge . they use massive knowledge bases to guide annotators and large language models to construct knowledgable questions .
Outcome:	The proposed benchmarks have limited knowledge coverage and use choices or spans as answers, which results in narrow answer space.

Building Large-Scale Japanese Pronunciation-Annotated Corpora for Reading Heteronymous Logograms (2022.lrec-1)

Copied to clipboard

Fumikazu Sato, Naoki Yoshinaga, Masaru Kitsuregawa

Challenge:	Especially in Japanese, there are many common heteronyms expressed by logograms (Chinese characters or kanji) that have totally different pronunciations.
Approach:	They construct large-scale Japanese corpora that annotate kanji characters with their pronunciations to improve the accuracy of pronunciation prediction models.
Outcome:	The proposed models achieve an average accuracy of 0.939 for 203 common heteronyms and a 0.938 for 93 heters.

JDocQA: Japanese Document Question Answering Dataset for Generative Language Models (2024.lrec-main)

Copied to clipboard

Eri Onami, Shuhei Kurita, Taiki Miyanishi, Taro Watanabe

Multimodality

Challenge:	Document question answering is a task of question answering on given documents such as reports, slides, pamphlets, and websites.
Approach:	They propose a large-scale document-based QA dataset that requires both visual and textual information to answer questions.
Outcome:	The proposed dataset incorporates multiple categories of questions and unanswerable questions from the document for realistic question-answering applications.

DP3: Differentially Private Prompt Perturbation for Multi-turn LLM Inference (2026.findings-acl)

Copied to clipboard

Lele Zheng, Chao Zhang, Feiyang Yuan, Ke Cheng, Tao Zhang, Anxiao Song, Yulong Shen

Responsible & Trustworthy NLP

Challenge:	Large language models (LLMs) are widely used for text understanding and generation . existing methods that assume single-turn interactions break down in multi-turn settings .
Approach:	They propose a differentially private prompt perturbation framework for multi-turn LLM inference . DP3 constructs a perturbation mapping table to reuse perturbations for recurring tokens .
Outcome:	The proposed framework reduces privacy costs and degrades cross-turn semantic coherence . it also provides a context-aware utility function to maintain semantic consistency across turns .

Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities (2025.findings-acl)

Copied to clipboard

Wenyue Hua, Kaijie Zhu, Lingyao Li, Lizhou Fan, Mingyu Jin, Shuhang Lin, Haochen Xue, Zelong Li, Jindong Wang, Yongfeng Zhang

Datasets for Scientific Literature Understanding: A Survey (2026.findings-acl)

Challenge:	Using large language models, large language model models can be used to evaluate reasoning abilities in context-rich scenarios.
Approach:	They construct datasets for both propositional logic and abductive logic reasoning with four difficulty levels across 12 distinct domains based on Wikipedia categorization and those with purely abstract variables.
Outcome:	The proposed model can be used to benchmark LLMs in real-world scenarios, but not in context-rich scenarios.

Copied to clipboard

Yuanzhe Zhang, Xun Zhao, Maodi Hu, Xi Sun, Donghuan Song, Zhixiong Zhang

Challenge:	Empowering machines to understand scientific literature is crucial for accelerating scientific discovery and advancing the AI for Science paradigm.
Approach:	They propose a systematic taxonomy that organizes resources spanning structural understanding, text understanding, multimodal understanding and pre-training/instruction fine-tuning.
Outcome:	The proposed taxonomy organizes resources spanning structural understanding, text understanding, multimodal understanding and pre-training/instruction fine-tuning.

ViLegalLM: Language Models for Vietnamese Legal Text (2026.findings-acl)

Copied to clipboard

Truong-Phuc Nguyen, Quy-Nhan Nguyen, Minh-Tien Nguyen