3 citations · 13 across the 31 of their papers we have counts for
33 papers
Overview of the TREC 2025 Million Large Language Models track
Evangelos Kanoulas, Panagiotis Eustratiadis, Jamie Callan +5
Agentic AI envisions ecosystems of intelligent agents collaboratively solving complex tasks with minimal human intervention. In such ecosystems, each agent possesses specialized ex…
Detecting Data Contamination in Large Language Models
Juliusz Janicki, Savvas Chamezopoulos, Evangelos Kanoulas +1
Large Language Models (LLMs) utilize large amounts of data for their training, some of which may come from copyrighted sources. Membership Inference Attacks (MIA) aim to detect tho…
On the Robustness of LLM-Based Dense Retrievers: A Systematic Analysis of Generalizability and Stability
Yongkang Li, Panagiotis Eustratiadis, Yixing Fan +1
Decoder-only large language models (LLMs) are increasingly replacing BERT-style architectures as the backbone for dense retrieval, achieving substantial performance gains and broad…
Spectral Tempering for Embedding Compression in Dense Passage Retrieval
Yongkang Li, Panagiotis Eustratiadis, Evangelos Kanoulas
Dimensionality reduction is critical for deploying dense retrieval systems at scale, yet mainstream post-hoc methods face a fundamental trade-off: principal component analysis (PCA…
SubSearch: Intermediate Rewards for Unsupervised Guided Reasoning in Complex Retrieval
Roxana Petcu, Evangelos Kanoulas, Maarten de Rijke
Large language models (LLMs) are probabilistic in nature and perform more reliably when augmented with external information. As complex queries often require multi-step reasoning o…
A Novel Automatic Framework for Speaker Drift Detection in Synthesized Speech
Jia-Hong Huang, Seulgi Kim, Yi Chieh Liu +5
Recent diffusion-based text-to-speech (TTS) models achieve high naturalness and expressiveness, yet often suffer from speaker drift, a subtle, gradual shift in perceived speaker id…
LLM-based Listwise Reranking under the Effect of Positional Bias
Jingfen Qiao, Jin Huang, Xinyu Ma +4
LLM-based listwise passage reranking has attracted attention for its effectiveness in ranking candidate passages. However, these models suffer from positional bias, where passages…
Query Decomposition for RAG: Balancing Exploration-Exploitation
Roxana Petcu, Kenton Murray, Daniel Khashabi +4
Retrieval-augmented generation (RAG) systems address complex user requests by decomposing them into subqueries, retrieving potentially relevant documents for each, and then aggrega…
ChatR1: Reinforcement Learning for Conversational Reasoning and Retrieval Augmented Question Answering
Simon Lupart, Mohammad Aliannejadi, Evangelos Kanoulas
We present ChatR1, a reasoning framework based on reinforcement learning (RL) for conversational question answering (CQA). Reasoning plays an important role in CQA, where user inte…
Summarize-Exemplify-Reflect: Data-driven Insight Distillation Empowers LLMs for Few-shot Tabular Classification
Yifei Yuan, Jiatong Li, Weijia Zhang +3
Recent studies show the promise of large language models (LLMs) for few-shot tabular classification but highlight challenges due to the variability in structured data. To address t…
Beyond Natural Language Plans: Structure-Aware Planning for Query-Focused Table Summarization
Weijia Zhang, Songgaojun Deng, Evangelos Kanoulas
Query-focused table summarization requires complex reasoning, often approached through step-by-step natural language (NL) plans. However, NL plans are inherently ambiguous and lack…
A Comprehensive Taxonomy of Negation for NLP and Neural Retrievers
Roxana Petcu, Samarth Bhargav, Maarten de Rijke +1
Understanding and solving complex reasoning tasks is vital for addressing the information needs of a user. Although dense neural models learn contextualised embeddings, they still…
Why Uncertainty Estimation Methods Fall Short in RAG: An Axiomatic Analysis
Heydar Soudani, Evangelos Kanoulas, Faegheh Hasibi
Large Language Models (LLMs) are valued for their strong performance across various tasks, but they also produce inaccurate or misleading outputs. Uncertainty Estimation (UE) quant…
Reproducibility, Replicability, and Insights into Visual Document Retrieval with Late Interaction
Jingfen Qiao, Jia-Huei Ju, Xinyu Ma +2
Visual Document Retrieval (VDR) is an emerging research area that focuses on encoding and retrieving document images directly, bypassing the dependence on Optical Character Recogni…
Leveraging Decoder Architectures for Learned Sparse Retrieval
Jingfen Qiao, Thong Nguyen, Evangelos Kanoulas +1
Learned Sparse Retrieval (LSR) has traditionally focused on small-scale encoder-only transformer architectures. With the advent of large-scale pre-trained language models, their ca…
Unsupervised Corpus Poisoning Attacks in Continuous Space for Dense Retrieval
Yongkang Li, Panagiotis Eustratiadis, Simon Lupart +1
This paper concerns corpus poisoning attacks in dense information retrieval, where an adversary attempts to compromise the ranking performance of a search algorithm by injecting a…
Agent-centric Information Access
Evangelos Kanoulas, Panagiotis Eustratiadis, Yongkang Li +5
As large language models (LLMs) become more specialized, we envision a future where millions of expert LLMs exist, each trained on proprietary data and excelling in specific domain…
PSCon: Product Search Through Conversations
Jie Zou, Mohammad Aliannejadi, Evangelos Kanoulas +5
Conversational Product Search ( CPS ) systems interact with users via natural language to offer personalized and context-aware product lists. However, most existing research on CPS…
Constructing Set-Compositional and Negated Representations for First-Stage Ranking
Antonios Minas Krasakis, Andrew Yates, Evangelos Kanoulas
Set compositional and negated queries are crucial for expressing complex information needs and enable the discovery of niche items like Books about non-European monarchs. Despite t…
Gradient Weight-normalized Low-rank Projection for Efficient LLM Training
Jia-Hong Huang, Yixian Shen, Hongyi Zhu +2
Large Language Models (LLMs) have shown remarkable performance across various tasks, but the escalating demands on computational resources pose significant challenges, particularly…
Reproducing HotFlip for Corpus Poisoning Attacks in Dense Retrieval
Yongkang Li, Panagiotis Eustratiadis, Evangelos Kanoulas
HotFlip is a topical gradient-based word substitution method for attacking language models. Recently, this method has been further applied to attack retrieval systems by generating…
Image2Text2Image: A Novel Framework for Label-Free Evaluation of Image-to-Text Generation with Text-to-Image Diffusion Models
Jia-Hong Huang, Hongyi Zhu, Yixian Shen +2
Evaluating the quality of automatically generated image descriptions is a complex task that requires metrics capturing various dimensions, such as grammaticality, coverage, accurac…
The art of connections: constructing a social network from the correspondence archive of Sybren Valkema
Vera Provatorova, Carlotta Capurro, Evangelos Kanoulas
Social network analysis allows researchers to discover insights from connections between people. While the process of building a social network is relatively straightforward for co…
Table Question Answering for Low-resourced Indic Languages
Vaishali Pal, Evangelos Kanoulas, Andrew Yates +1
TableQA is the task of answering questions over tables of structured information, returning individual cells or tables as output. TableQA research has focused primarily on high-res…