Papers by Evangelos Kanoulas
Extracting, Detecting, and Generating Research Questions for Scientific Articles (2025.coling-main)
Copied to clipboard
Sina Taslimi, Artemis Capari, Hosein Azarbonyad, Zi Long Zhu, Zubair Afzal, Evangelos Kanoulas, George Tsatsaronis
| Challenge: | Existing tools to generate and extract RQs from scientific articles lack a definition of RQ in articles. |
| Approach: | They propose to use a set of regular expressions to identify articles with well-defined RQs and a detection component to identify more complex RQ's in articles. |
| Outcome: | The proposed pipeline can detect and generate RQs from scientific articles and generate high-quality ones. |
MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering (2023.acl-long)
Copied to clipboard
| Challenge: | Recent tabular question answering models only answer questions over a single table . multi-table operations often result in tabular outputs . |
| Approach: | They propose a model that answers questions over multiple tables and generalizes to generate tabular answers. |
| Outcome: | The proposed model outperforms state-of-the-art single table QA models on a multi-table QA setting. |
WN-Salience: A Corpus of News Articles with Entity Salience Annotations (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing work on entity salience does not distinguish between salient and non-salient entities. |
| Approach: | They propose a dataset to measure entity salience using WikiNews dataset . WN-Salience is built on top of Wikinews, a Wikimedia project . |
| Outcome: | The proposed dataset can be used to benchmark tasks such as entity salience detection and salient entity linking. |
ChatR1: Reinforcement Learning for Conversational Reasoning and Retrieval Augmented Question Answering (2026.acl-long)
Copied to clipboard
| Challenge: | Unlike static ‘rewrite, retrieve, and generate’ pipelines, ChatR1 interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through RL. |
| Approach: | They propose a reasoning framework based on reinforcement learning (RL) for conversational question answering that interleaves search and reasoning across turns and provides turn-level feedback. |
| Outcome: | The proposed framework outperforms competing models on five CQA datasets, measured by different metrics (F1, BERTScore, and LLM-as-judge). |
A Comprehensive Taxonomy of Negation for NLP and Neural Retrievers (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a new taxonomy of negation is proposed to improve neural information retrieval models . negation types are covered in existing datasets, allowing for faster convergence . |
| Approach: | They propose a taxonomy of negation that derives from philosophical, linguistic, and logical definitions . they also propose analyzing the performance of retrieval models on existing datasets using a logic-based classification mechanism. |
| Outcome: | The proposed taxonomy produces a balanced data distribution over negation types . it also provides a better training setup that leads to faster convergence on the NevIR dataset . |
Query Decomposition for RAG: Balancing Exploration-Exploitation (2026.eacl-long)
Copied to clipboard
Roxana Petcu, Kenton Murray, Daniel Khashabi, Evangelos Kanoulas, Maarten de Rijke, Dawn Lawrie, Kevin Duh
| Challenge: | Complex user queries often involve the exclusion of information, negation, or missing entities. |
| Approach: | They propose to decompose user requests into subqueries, retrieve potentially relevant documents for each and then aggregate them to generate an answer. |
| Outcome: | The proposed method achieves 35% gain in document-level precision and 15% increase in -nDCG . it also improves the downstream task of long-form generation. |
Robustness Evaluation of Entity Disambiguation Using Prior Probes: the Case of Entity Overshadowing (2021.emnlp-main)
Copied to clipboard
| Challenge: | Entity disambiguation (ED) is the last step of entity linking when candidate entities are reranked according to the context they appear in. |
| Approach: | They propose a dataset that includes 16K short text snippets annotated with entity mentions to evaluate EL models. |
| Outcome: | The proposed dataset shows that the performance of EL systems is overestimated . the results show that the EL system performance is significantly better on the ShadowLink benchmark . |
Why Uncertainty Estimation Methods Fall Short in RAG: An Axiomatic Analysis (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing UE methods cannot reliably estimate the correctness of LLM responses in Retrieval-Augmented Generation (RAG) . Existing methods generate low uncertainty values without considering relevance of context to query . |
| Approach: | They propose an axiomatic framework to identify deficiencies in existing UE methods and introduce five constraints that an effective UE method should meet after incorporating retrieved documents into the LLM’s prompt. |
| Outcome: | The proposed framework satisfies all the axioms and improves correlation between uncertainty estimates and correctness. |
Table Question Answering for Low-resourced Indic Languages (2024.emnlp-main)
Copied to clipboard
| Challenge: | TableQA is the task of answering questions over tables of structured information, returning individual cells or tables as output. |
| Approach: | They propose a fully automatic large-scale tableQA data generation process for low-resource languages with limited budget. |
| Outcome: | The proposed method outperforms state-of-the-art LLMs on two Indic languages with no tableQA datasets and models on different aspects including mathematical reasoning capabilities and zero-shot cross-lingual transfer. |
Summarize-Exemplify-Reflect: Data-driven Insight Distillation Empowers LLMs for Few-shot Tabular Classification (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies show the promise of large language models for few-shot tabular classification but highlight challenges due to the variability in structured data. |
| Approach: | They propose a framework that distills data into actionable insights to enable robust and effective classification by large language models. |
| Outcome: | The proposed framework integrates rule summarization, strategic exemplification, and insight reflection through deep collaboration between LLMs and data modeling techniques. |
Expand, Highlight, Generate: RL-driven Document Generation for Passage Reranking (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies use large language models to generate training data for ranking models. |
| Approach: | They propose a pipeline that generates synthetic documents from queries using large language models . they propose RL-based reinforcement learning to optimize the pipeline . |
| Outcome: | The proposed pipeline outperforms existing state-of-the-art methods in generating synthetic documents more effectively. |
SOLID: Self-seeding and Multi-intent Self-instructing LLMs for Generating Intent-aware Information-Seeking Dialogs (2025.findings-naacl)
Copied to clipboard
Arian Askari, Roxana Petcu, Chuan Meng, Mohammad Aliannejadi, Amin Abolghasemi, Evangelos Kanoulas, Suzan Verberne
| Challenge: | Existing methods for intent prediction rely on human feedback and are tailored to structured intents. |
| Approach: | They propose a method that generates dialogs turn-by-turn using self-seeding and multi-intent self-instructing strategies. |
| Outcome: | The proposed methods generate dialogs turn-by-turn using self-seeding and multi-intent self-instructing strategies. |