Papers by Sophia Ananiadou

A Walk-based Model on Entity Graphs for Relation Extraction (P18-2)

Challenge:	Existing models for extracting relation triplets suffer from incompletion and disorder problems when they extract multi-token entities from input sentences.
Approach:	They propose a special entity labelling method that fine-tunes the pre-trained model and learns the special entity labels simultaneously.
Outcome:	The proposed model achieves 4.6% and 0.9% improvement over current methods in the NYT24 and NYT29 benchmark datasets.

Copied to clipboard

Fenia Christopoulou, Makoto Miwa, Sophia Ananiadou

Incorporating Zoning Information into Argument Mining from Biomedical Literature (2022.lrec-1)

Challenge:	Existing models treat each relation in a sentence individually, but a graph-based model needs to consider multiple relations between entities to model the dependencies among them.
Approach:	They propose a graph-based neural network model that treats multiple pairs in a sentence simultaneously and considers interactions among them.
Outcome:	The proposed model performs comparable to the state-of-the-art systems on the ACE 2005 dataset without external tools.

Copied to clipboard

Boyang Liu, Viktor Schlegel, Riza Batista-Navarro, Sophia Ananiadou

Reasoning

Challenge:	Argumentative zoning is a text zonation scheme that is used to segment text into zones that serve distinct functions.
Approach:	They propose to use zoning information to incorporate into argument mining tasks . they add zonation labels predicted by an off-the-shelf model to the beginning of each sentence .
Outcome:	The proposed models improve argument mining models without additional annotation cost.

Span-based Named Entity Recognition by Generating and Compressing Information (2023.eacl-main)

Copied to clipboard

Nhung T. H. Nguyen, Makoto Miwa, Sophia Ananiadou

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models (2026.findings-acl)

Challenge:	Existing work on Named Entity Recognition (NER) only used generative or information compression models to improve performance.
Approach:	They propose to combine two types of IB models into one system to enhance Named Entity Recognition (NER) they incorporate unsupervised generative components span reconstruction and synonym generation into a span-based NER system.
Outcome:	The proposed model focuses on learning span representation, which is applicable not only to span-based NER but also to other span-related tasks such as event coreference resolution and question answering.

Copied to clipboard

Hengyuan Zhang, Zhihao Zhang, Ercong Nie, Mingyang Wang, Zunhai Su, Yiwei Wang, Qianli Wang, Shuzhou Yuan, Xufeng Duan, Qibo Xue, Zeping Yu, Chenming Shang, Xiao Liang, Jing Xiong, Hui Shen, Chaofan Tao, Zhengwu Liu, Senjie Jin, Zhiheng Xi, Dongdong Zhang, Sophia Ananiadou, Tao Gui, Ruobing Xie, Hayden Kwok-Hay So, Hinrich Schuetze, Xuanjing Huang, Qi Zhang, Ngai Wong

Explainability & Interpretability in NLP

Challenge:	Existing literature on mechanistic interpretation (MI) treats it as an observational science, leaving practical applications underexplored.
Approach:	They propose a survey structured around the pipeline to identify and improve MI models.
Outcome:	The proposed framework enables tangible improvements in Alignment, Capability, and Efficiency.

Neuron-Level Knowledge Attribution in Large Language Models (2024.emnlp-main)

Copied to clipboard

Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis (2024.emnlp-main)

Challenge:	Existing methods for attribution of knowledge in large language models struggle to operate at neuron level due to computational constraints.
Approach:	They propose a static method for pinpointing significant neurons using three metrics . they also propose identifying "query neurons" which activate these "value neurons"
Outcome:	The proposed method shows superior performance across three metrics compared to seven other methods . it analyzes six types of knowledge across attention and feed-forward network layers .

Copied to clipboard

Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Network (P19-1)

Challenge:	Existing studies have found that arithmetic ability is limited to a few attention heads . existing studies do not elaborate on the mechanisms of these heads or how they influence FFN layers.
Approach:	They propose a method that identifies an internal logic chain consisting of four stages from input to prediction.
Outcome:	The proposed method improves prediction probabilities by amplifying coefficient scores of FFN neurons related to predictions.

Copied to clipboard

Sunil Kumar Sahu, Fenia Christopoulou, Makoto Miwa, Sophia Ananiadou

Semantic Annotation for Improved Safety in Construction Work (2020.lrec-1)

Challenge:	Existing methods for inter-sentence relation extraction do not fully exploit such dependencies.
Approach:	They propose a model that captures local and non-local dependencies using multi-instance learning and bi-affine pairwise scoring to predict the relation of an entity pair.
Outcome:	The proposed model performs comparable to state-of-the-art models on biochemistry datasets.

Copied to clipboard

Paul Thompson, Tim Yates, Emrah Inan, Sophia Ananiadou

FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning (2026.acl-long)

Challenge:	a number of documents provide evidence of previous incidents and mitigation strategies . but information about previous projects with similar attributes is often hidden within . a new named entity annotation scheme is being developed for construction safety .
Approach:	a team of four health and safety experts have developed a named entity annotation scheme for construction safety documents.
Outcome:	a new named entity annotation scheme annotates 600 sentences from accident reports . the scheme has an average agreement rate of 0.79 F-Score .

Copied to clipboard

Zhuohan Xie, Daniil Orel, Rushil Thareja, Dhruv Sahnan, Hachem Madmoun, Fan Zhang, Debopriyo Banerjee, Georgi Nenkov Georgiev, Xueqing Peng, Lingfei Qian, Jimin Huang, Jinyan Su, Aaryamonvikram Singh, Rui Xing, Rania Elbadry, Chen Xu, Haonan Li, Fajri Koto, Ivan Koychev, Tanmoy Chakraborty, Yuxia Wang, Salem Lahlou, Veselin Stoyanov, Sophia Ananiadou, Preslav Nakov

Reasoning

Challenge:	Existing benchmarks emphasize final numerical answers while neglecting intermediate reasoning steps.
Approach:	They propose a symbolic benchmark for verifiable Chain-of-Thought evaluation in finance . FINCHAIN spans 58 topics across 12 financial domains and three difficulty levels .
Outcome:	The proposed benchmark aims to bridge symbolic reasoning and factual verification.

A New Corpus to Support Text Mining for the Curation of Metabolites in the ChEBI Database (L18-1)

Copied to clipboard

Matthew Shardlow, Nhung Nguyen, Gareth Owen, Claire O’Donovan, Andrew Leach, John McNaught, Steve Turner, Sophia Ananiadou

Challenge:	a corpus of 200 abstracts and 100 full text papers which have been annotated with named entities and relations in the biomedical domain is part of the OpenMinTeD project.
Approach:	They propose to annotate 200 abstracts and 100 full text papers with entities and relations in the biomedical domain as part of the OpenMinTeD project.
Outcome:	The proposed corpus can be used within ChEBI to facilitate text and data mining and integrate with the OpenMinTeD text and database platform.

Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models (2025.emnlp-main)

Copied to clipboard

Zeping Yu, Yonatan Belinkov, Sophia Ananiadou

EMPEC: A Comprehensive Benchmark for Evaluating Large Language Models Across Diverse Healthcare Professions (2025.findings-acl)

Challenge:	Increasing the ability of large language models to perform latent multihop reasoning is crucial for reducing the cost and deployment challenges.
Approach:	They propose an interpretability method that traces how logits propagate across layers and positions toward the final prediction.
Outcome:	The proposed method improves accuracy on five reasoning datasets.

Copied to clipboard

Zheheng Luo, Chenhan Yuan, Qianqian Xie, Sophia Ananiadou

From n-gram to Attention: How Model Architectures Learn and Propagate Bias in Language Modeling (2025.findings-emnlp)

Challenge:	Recent advances in Large Language Models (LLMs) show their potential in accurately answering biomedical questions, yet current healthcare benchmarks primarily assess knowledge mastered by medical doctors, neglecting other essential professions.
Approach:	They evaluated 17 LLMs including proprietary and open-source models and found they struggled with specialized fields and alternative medicine.
Outcome:	The examinations for medical PErsonnel in Chinese (EMPEC) features 157,803 exam questions across 124 subjects and 20 healthcare professions.

Copied to clipboard

Mohsinul Kabir, Tasfia Tahsin, Sophia Ananiadou

FLAG-TRADER: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading (2025.findings-acl)

Challenge:	Current research on bias in language models focuses on data quality, not temporal influences of data.
Approach:	They propose a methodology to interpret the interaction between training data and model architecture in bias propagation during language modeling.
Outcome:	The proposed method analyzes the interaction between training data and model architecture in bias propagation during language modeling.

Copied to clipboard

Guojun Xiong, Zhiyang Deng, Keyi Wang, Yupeng Cao, Haohang Li, Yangyang Yu, Xueqing Peng, Mingquan Lin, Kaleb E Smith, Xiao-Yang Liu, Jimin Huang, Sophia Ananiadou, Qianqian Xie

Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs (D19-1)

Challenge:	Large language models (LLMs) have impressive reasoning capabilities in financial tasks, but struggle with multi-step, goal-oriented scenarios in interactive financial markets.
Approach:	They propose a framework that integrates large language models with gradient-driven reinforcement learning (RL) policy optimization.
Outcome:	The proposed framework improves performance in trading and other financial domain tasks.

Copied to clipboard

Fenia Christopoulou, Makoto Miwa, Sophia Ananiadou

Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection (2026.findings-acl)

Challenge:	Existing approaches to document-level relation extraction use nodes and edges as relations between nodes.
Approach:	They propose an edge-oriented graph neural model for document-level relation extraction that uses different types of nodes and edges to create a document-based graph.
Outcome:	The proposed model can learn intra- and inter-sentence relations using multi-instance learning internally.

Copied to clipboard

Zhiwei Liu, Yupeng Cao, Yuechen Jiang, Mohsinul Kabir, Polydoros Giannouris, Chen Xu, Ziyang Xu, Tianlei Zhu, Md. Tariquzzaman, Triantafillos Papadopoulos, Yan Wang, Lingfei Qian, Xueqing Peng, Zhuohan Xie, Ye Yuan, Saeed Almheiri, Abdulrazzaq Alnajjar, Ming-Bin Chen, Harry Stuart, Paul Thompson, Prayag Tiwari, Alejandro Lopez-Lira, Xue Liu, Jimin Huang, Sophia Ananiadou

APLenty: annotation tool for creating high-quality datasets using active and proactive learning (D18-2)

Challenge:	Existing research on LLM biases has focused on direct questioning or general-purpose settings . pronounced behavioral biase despite their growing deployment in financial analysis, forecasting, and decision support.
Approach:	They propose a benchmark to evaluate behavioral biases of large language models in MFMD . they use a multilingual financial misinformation dataset to integrate these with misinformation claims .
Outcome:	The proposed benchmark evaluates behavioral biases of large language models across economic scenarios.

Copied to clipboard

Minh-Quoc Nghiem, Sophia Ananiadou

Low-Resource NLP

Challenge:	APLenty is an annotation tool for creating high-quality sequence labeling datasets using active and proactive learning.
Approach:	They present APLenty, an annotation tool for creating high-quality sequence labeling datasets using active and proactive learning.
Outcome:	The proposed tool is highly flexible and can be adapted to various other tasks.

A Neural Layered Model for Nested Named Entity Recognition (N18-1)

Copied to clipboard

Meizhi Ju, Makoto Miwa, Sophia Ananiadou

Text Classification and Prediction in the Legal Domain (2022.lrec-1)

Challenge:	Entity mentions embedded in longer entity mentions are referred to as nested entities due to the properties of natural language.
Approach:	They propose a neural model that dynamically stacks flat NER layers to identify nested entities by capturing sequential context representation with bidirectional long-term memory.
Outcome:	The proposed model outperforms state-of-the-art feature-based systems on nested NER, achieving 74.7% and 72.2% on GENIA and ACE2005 datasets, respectively in terms of F-score.

Copied to clipboard

Minh-Quoc Nghiem, Paul Baylis, André Freitas, Sophia Ananiadou

Information Retrieval

Challenge:	a case study combines text classification and legal judgment prediction for flight compensation . a human-in-the-loop model outperformed human prediction when predicting a claim being successful .
Approach:	They combine transformer-based classification models with human-in-the-loop data to classify airlines' responses to flight compensation claims.
Outcome:	The proposed models outperform human prediction when predicting a legal claim success.

Investigating Text Simplification Evaluation (2021.findings-acl)

Copied to clipboard

Laura Vásquez-Rodríguez, Matthew Shardlow, Piotr Przybyła, Sophia Ananiadou

Text Generation

Challenge:	Existing studies show that parallel TS corpora contain inaccurate simplifications and incorrect alignments.
Approach:	They propose to improve the distribution of parallel text simplification corpora to build more robust TS models.
Outcome:	The proposed models can be improved by improving the distribution of TS datasets.

Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs (2025.findings-emnlp)

Copied to clipboard

SAHM: A Benchmark for Arabic Financial and Shari’ah-Compliant Reasoning (2026.acl-long)

Multimodality

Challenge:	Multimodal instruction tuning often causes catastrophic forgetting of the base LLM’s language ability, even in strong models like Llama3.
Approach:	They propose a training-free parameter fusion framework that locates important parameters and selectively merges them.
Outcome:	The proposed framework preserves the influence of neurons with large parameter shifts while attenuating the influence . of neurons likely responsible for newly acquired visual capabilities while mitigating language degradation.

Copied to clipboard

Rania Elbadry, Sarfraz Ahmad, Ahmed Heakl, Dani Bouch, Momina Ahsan, Muhra AlMahri, Marwa Elsaid Khalil, Yuxia Wang, Salem Lahlou, Sophia Ananiadou, Veselin Stoyanov, Jimin Huang, Xueqing Peng, Preslav Nakov, Zhuohan Xie

All That Glisters Is Not Gold: A Benchmark for Reference-Free Counterfactual Financial Misinformation Detection (2026.acl-long)

Challenge:	English financial NLP has progressed rapidly through benchmarks for sentiment, document understanding, and financial question answering.
Approach:	They propose a document-grounded benchmark and instruction-tuning dataset for Arabic financial NLP and Shari’ah-compliant reasoning.
Outcome:	The proposed dataset contains 14,380 expert-verified instances spanning seven tasks . it includes financial sentiment analysis, extractive summarization, and event–cause reasoning .

Copied to clipboard

Yuechen Jiang, Zhiwei Liu, Yupeng Cao, Yueru He, Ziyang Xu, Chen Xu, Zhiyang Deng, Prayag Tiwari, Xi Chen, Alejandro Lopez-Lira, Jimin Huang, Junichi Tsujii, Sophia Ananiadou

Paladin: an annotation tool based on active and proactive learning (2021.eacl-demos)

Challenge:	RFC-Bench evaluates large language models on financial misinformation under realistic news . current models struggle to maintain coherent belief states without external grounding, study finds .
Approach:	They propose a benchmark for evaluating large language models on financial misinformation under realistic news.
Outcome:	The proposed model performs better when context is available, while reference-free settings expose significant weaknesses.

Copied to clipboard

Minh-Quoc Nghiem, Paul Baylis, Sophia Ananiadou

Low-Resource NLP

Challenge:	Existing tools for active learning focus on the active learning algorithms and provide no user interface thus making it difficult to use for the end-users.
Approach:	They present an open-source web-based annotation tool for creating high-quality multi-label document-level datasets that integrates active learning and proactive learning.
Outcome:	The proposed tool is designed for multi-label annotation, but it can be adapted to other tasks in single-l Label settings.

Readability Controllable Biomedical Document Summarization (2022.findings-emnlp)

Copied to clipboard

Zheheng Luo, Qianqian Xie, Sophia Ananiadou

GRETEL: Graph Contrastive Topic Enhanced Language Model for Long Document Extractive Summarization (2022.coling-1)

Challenge:	Existing controllable summarization systems for biomedical documents have little attention to readability control, leaving users with incompatible summaries .
Approach:	They propose a task of readability controllable summarization for biomedical documents to generate summaries that are incompatible with users' levels of expertise.
Outcome:	The proposed model is based on pre-trained language models with prevalent controlling and generation techniques and evaluates the readability discrepancy between lay and technical summaries.

Copied to clipboard

Qianqian Xie, Jimin Huang, Tulika Saha, Sophia Ananiadou

Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base Priors (2021.naacl-main)

Challenge:	Existing approaches to capture and integrate global semantic information are limited due to their limited ability to capture long-range dependencies.
Approach:	They propose a graph contrastive topic enhanced language model that integrates a neural topic model with a pre-trained language model to capture global contextual semantics.
Outcome:	The proposed model outperforms existing methods on general domain and biomedical datasets.

Copied to clipboard

Fenia Christopoulou, Makoto Miwa, Sophia Ananiadou

Semantic Text Processing

Challenge:	Existing methods to facilitate distantly supervised relation extraction are noisy instances, long-tail relations and unbalanced bag sizes.
Approach:	They propose a multi-task approach to facilitate distantly supervised relation extraction by bringing closer the representations of sentences that contain the same Knowledge Base pairs.
Outcome:	The proposed approach improves performance on two datasets created via distant supervision.

MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)

Copied to clipboard

Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie

Multimodality

Challenge:	Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models.
Approach:	They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts.
Outcome:	The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings .

SynGraph: A Dynamic Graph-LLM Synthesis Framework for Sparse Streaming User Sentiment Modeling (2025.findings-acl)

Copied to clipboard

Xin Zhang, Qiyu Wei, Yingjie Zhu, Linhai Zhang, Deyu Zhou, Sophia Ananiadou

Multimodality

Challenge:	Traditional sentiment analysis methods focus on static reviews, failing to capture temporal relationship between user sentiment rating and textual content.
Approach:	They propose a dynamic graph-based framework that addresses data sparsity in streaming reviews.
Outcome:	The proposed framework reduces data sparsity by categorizing users into mid-tail, long-tail and extreme scenarios and incorporating LLM enhancements within a dynamic graph-based structure.

Towards Interpretable Mental Health Analysis with Large Language Models (2023.emnlp-main)

Copied to clipboard

Kailai Yang, Shaoxiong Ji, Tianlin Zhang, Qianqian Xie, Ziyan Kuang, Sophia Ananiadou

HiRAS: A Hierarchical Multi-Agent Framework for Paper-to-Code Generation and Execution (2026.findings-acl)

Challenge:	Existing studies on large language models lack adequate evaluations and prompting strategies for explainability.
Approach:	They evaluate the mental health analysis and emotional reasoning ability of large language models (LLMs) using 11 datasets across 5 tasks.
Outcome:	The proposed model shows strong in-context learning ability but still has a significant gap with advanced task-specific methods.

Copied to clipboard

Hanhua Hong, Yizhi LI, Jiaoyan Chen, Sophia Ananiadou, Xiaoli Li, Jung-jae Kim, Chenghua Lin

Text Generation

Challenge:	Existing approaches to automate computational research use fixed sequential agent pipelines with weak global coordination, which limits their robustness and overall performance.
Approach:	They propose a hierarchical multi-agent framework for end-to-end paper reproduction that employs supervisory manager agents to coordinate specialised agents across fine-grained stages.
Outcome:	The proposed framework improves the paper2code benchmark and significantly reduces hallucination in the evaluation.

Selective Preference Optimization via Token-Level Reward Function Estimation (2025.emnlp-main)

Copied to clipboard

Kailai Yang, Zhiwei Liu, Qianqian Xie, Jimin Huang, Erxue Min, Sophia Ananiadou

Green & Sustainable NLP

Challenge:	Existing methods for maximizing preference optimization on all available tokens are noisy and inefficient.
Approach:	They propose a selective alignment strategy that centers on efficient key token selection without strong, fine-grained supervision signals.
Outcome:	The proposed strategy outperforms baseline methods on three benchmarks with up to 60% reduction in training hours.

A Neural Model for Aggregating Coreference Annotation in Crowdsourcing (2020.coling-main)

Copied to clipboard

Maolin Li, Hiroya Takamura, Sophia Ananiadou

A Search-based Neural Model for Biomedical Nested and Overlapping Event Detection (D19-1)

Challenge:	Existing studies of natural language labelling tasks have shown that crowd-sourced labels can be noisy.
Approach:	They split the aggregation into mention classification and coreference chain inference tasks to predict the correct labels.
Outcome:	The proposed model predicts the class of each mention using an autoencoder while taking into account the mention’s annotation complexity and annotators’ reliability at different levels.

Copied to clipboard

Kurt Junshean Espinosa, Makoto Miwa, Sophia Ananiadou

RAEmoLLM: Retrieval Augmented LLMs for Cross-Domain Misinformation Detection Using In-Context Learning Based on Emotional Information (2025.acl-long)

Challenge:	Existing structured prediction tasks target nested and overlapping events . a new structured prediction model is proposed that uses a relation graph to detect overlapping and nesting events.
Approach:	They propose a search-based neural network structured prediction model that treats the task as a searching problem on a relation graph of trigger-argument structures.
Outcome:	The proposed model performs comparable to the state-of-the-art model Turku Event Extraction System (TEES) on the BioNLP Cancer Genetics (CG) Shared Task 2013 without the use of syntactic and hand-engineered features.

Copied to clipboard

Zhiwei Liu, Kailai Yang, Qianqian Xie, Christine de Kock, Sophia Ananiadou, Eduard Hovy

Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs (2025.emnlp-main)

Challenge:	Current methods for cross-domain misinformation detection focus on in-domain tasks and do not incorporate significant sentiment and emotion features.
Approach:	They propose a retrieval augmented (RAG) LLM framework that incorporates affective information into retrieval databases.
Outcome:	The proposed framework improves on three misinformation benchmarks.

Copied to clipboard

Mohsinul Kabir, Ajwad Abrar, Sophia Ananiadou

Challenge:	a large number of studies rely on closed-style multiple-choice surveys to evaluate cultural alignment in Large Language Models . however, these methods are constrained and lack nuanced and accurate evaluations based on specific cultural proxies.
Approach:	They propose to use the World Values Survey and Hofstede Cultural Dimensions as case studies to examine cultural alignment in Large Language Models.
Outcome:	The findings advocate for more robust evaluation frameworks that focus on cultural proxies.

THCM-CAL: Temporal-Hierarchical Causal Modelling with Conformal Calibration for Clinical Risk Prediction (2025.findings-emnlp)

Copied to clipboard

Xin Zhang, Qiyu Wei, Yingjie Zhu, Fanyi Wu, Sophia Ananiadou

Challenge:	Existing approaches to risk prediction from EHRs handle structured diagnostic codes and unstructured narrative notes separately.
Approach:	They propose a Temporal-Hierarchical Causal Model with Conformal Calibration . they construct a multimodal causal graph where nodes represent clinical entities from two modalities .
Outcome:	The proposed model infers three clinically grounded interactions from textual propositions and ICD codes mapped to textual descriptions.

ELAINE-medLLM: Lightweight English Japanese Chinese Trilingual Large Language Model for Bio-medical Domain (2025.coling-main)

Copied to clipboard

Ken Yano, Zheheng Luo, Jimin Huang, Qianqian Xie, Masaki Asada, Chenhan Yuan, Kailai Yang, Makoto Miwa, Sophia Ananiadou, Jun’ichi Tsujii

How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning (2024.emnlp-main)

Challenge:	Existing bilingual or multilingual medical LLMs are limited in multilingual data and therefore perform poorly in non-English languages such as Japanese and Chinese.
Approach:	They propose to use a trilingual (English, Japanese, Chinese) large language model adapted for the bio-medical domain to harness the knowledge and abilities of the base model.
Outcome:	The proposed model can support English, Japanese, and Chinese and is adapted for a bio-medical domain.

Copied to clipboard

Learning Disentangled Representations of Negation and Uncertainty (2022.acl-long)

Challenge:	In-context learning (ICL) is an emergent ability of large language models.
Approach:	They propose to use in-context learning to predict sentences with semantically-unrelated labels on 1% heads to investigate the mechanism.
Outcome:	The proposed methods reduce the majority label bias and recency bias by 22% and 17%, respectively.

Copied to clipboard

Jake Vasilakes, Chrysoula Zerva, Makoto Miwa, Sophia Ananiadou

Representation Learning

Challenge:	Negation and uncertainty modeling are long-standing tasks in natural language processing.
Approach:	They propose to disentangle negation, uncertainty, and content using a Variational Autoencoder by supervising latent representations using auxiliary objectives.
Outcome:	The proposed model can disentangle negation, uncertainty, and content using a Variational Autoencoder.

Modelling Instance-Level Annotator Reliability for Natural Language Labelling Tasks (N19-1)

Copied to clipboard

Maolin Li, Arvid Fahlström Myrman, Tingting Mu, Sophia Ananiadou

Challenge:	Existing models that estimate annotators' reliability only consider binary labels and multi-class labels.
Approach:	They propose an unsupervised model which can handle binary and multi-class labels and integrate neural networks to model the dependency between latent variables and instances.
Outcome:	The proposed model can handle binary and multi-class labels and can estimate reliability of annotators across instances.

Revisiting Unsupervised Relation Extraction (2020.acl-main)

Copied to clipboard

Thy Thy Tran, Phong Le, Sophia Ananiadou

RELATE: Generating a linguistically inspired Knowledge Graph for fine-grained emotion classification (2022.lrec-1)

Challenge:	Unsupervised relation extraction (URE) extracts relations between named entities from raw text without manually-labelled data and existing knowledge bases (KBs).
Approach:	They compare unsupervised relation extraction methods to generative and discriminative approaches . they conclude that entity types provide a strong inductive bias for URE .
Outcome:	The proposed method outperforms generative and discriminative approaches on two popular datasets.

Copied to clipboard

Annika Marie Schoene, Nina Dethlefs, Sophia Ananiadou

Sentiment Analysis

Challenge:	Existing knowledge resources for sentiment analysis (SA) tasks are either large, common-sense knowledge graphs (KGs) that cover a limited amount of polarities/emotions or they are smaller in size (e.g. lexicons) . however, these resources are limited by the low coverage of e.t. and scalability.
Approach:	They propose a new directed KG called ‘RELATE’ which incorporates the benefit of semantics without relying on costly human annotation.
Outcome:	The proposed KG overcomes low coverage of emotions and scalability issues . it is the first KG of its size to cover Ekman’s six basic emotions that are directed towards entities.

Coreference Resolution in Full Text Articles with BERT and Syntax-based Mention Filtering (D19-57)

Copied to clipboard

Hai-Long Trieu, Anh-Khoa Duong Nguyen, Nhung Nguyen, Makoto Miwa, Hiroya Takamura, Sophia Ananiadou

Argument mining as a multi-hop generative machine reading comprehension task (2023.findings-emnlp)

Challenge:	Existing systems for coreference resolution are difficult because of their long coreferent chains.
Approach:	They propose to use an existing span-based neural coreference resolution system as a baseline . they filter noisy mentions based on parse trees and integrate a highly expressive language model into the system .
Outcome:	The proposed system outperforms the baseline system on the CRAFT Shared Tasks 2019 task.

Copied to clipboard

Boyang Liu, Viktor Schlegel, Riza Batista-Navarro, Sophia Ananiadou

Reasoning

Challenge:	Argument mining is a natural language processing task that aims to generate an argumentative graph given an unstructured argumentative text.
Approach:	They propose a new approach which transfers the argument mining task into a multi-hop reading comprehension task by incorporating a "chain of thought" information into the model.
Outcome:	The proposed approach surpasses SOTA results on two arguments mining benchmarks.

Plutus: Benchmarking Large Language Models in Low-Resource Greek Finance (2025.emnlp-main)

Copied to clipboard

Xueqing Peng, Triantafillos Papadopoulos, Efstathia Soufleri, Polydoros Giannouris, Ruoyu Xiang, Yan Wang, Lingfei Qian, Jimin Huang, Qianqian Xie, Sophia Ananiadou