77 citations · 336 across the 34 of their papers we have counts for
39 papers
Computed, not Memorized: Bit-Factorized Identifiers for Efficient Generative Retrieval
I-Fan Lin, Zhen Zhang, Faegheh Hasibi +1
Generative retrieval is known for its efficient end-to-end indexing and retrieval. In particular, numeric Document Identifiers (DocIDs) are generally more efficient because they ar…
When Deep Research Agents Stagnate: Enhancing Reasoning with Retrieval-Aware Agent Control
Heydar Soudani, Elizabeth Lingg, Faegheh Hasibi +1
In this paper, we analyze the reasoning trajectories of a variety of DRAs and show that existing agents often suffer from reasoning stagnation: the majority of iterations contribut…
Uncertainty Quantification for Multimodal Retrieval Augmented Generation
Simon Binz, Heydar Soudani, Faegheh Hasibi
Retrieval Augmented Generation (RAG) improves the question answering capabilities of Large Language Models (LLMs) by incorporating external knowledge and has recently been extended…
Reproducing Complex Set-Compositional Information Retrieval
Vincent Degenhart, Dewi Timman, Arjen P. de Vries +2
Complex information needs may involve set-compositional queries using conjunction, disjunction, and exclusion, yet it remains unclear whether current retrieval paradigms genuinely…
Total Recall QA: A Verifiable Evaluation Suite for Deep Research Agents
Mahta Rafiee, Heydar Soudani, Zahra Abbasiantaeb +3
Deep research agents have emerged as LLM-based systems designed to perform multi-step information seeking and reasoning over large, open-domain sources to answer complex questions…
OrLog: Resolving Complex Queries with LLMs and Probabilistic Reasoning
Mohanna Hoveyda, Jelle Piepenbrock, Arjen P de Vries +2
Resolving complex information needs that come with multiple constraints should consider enforcing the logical operators encoded in the query (i.e., conjunction, disjunction, negati…
WildClaims: Information Access Conversations in the Wild(Chat)
Hideaki Joko, Shakiba Amirshahi, Charles L. A. Clarke +1
The rapid advancement of Large Language Models (LLMs) has transformed conversational systems into practical tools used by millions. However, the nature and necessity of information…
LUMI: Unsupervised Intent Clustering with Multiple Pseudo-Labels
I-Fan Lin, Faegheh Hasibi, Suzan Verberne
In this paper, we propose an intuitive, training-free and label-free method for intent clustering in conversational search. Current approaches to short text clustering use LLM-gene…
Uncertainty Quantification for Retrieval-Augmented Reasoning
Heydar Soudani, Hamed Zamani, Faegheh Hasibi
Retrieval-augmented reasoning (RAR) is a recent evolution of retrieval-augmented generation (RAG) that employs multiple reasoning steps for retrieval and generation. While effectiv…
LLMs Enable Bag-of-Texts Representations for Short-Text Clustering
I-Fan Lin, Faegheh Hasibi, Suzan Verberne
In this paper, we propose a training-free method for unsupervised short text clustering that relies less on careful selection of embedders than other methods. In customer-facing ch…
Towards a Large Physics Benchmark
Kristian G. Barman, Sascha Caron, Faegheh Hasibi +5
We introduce a benchmark framework developed by and for the scientific community to evaluate, monitor and steer large language model development in fundamental physics. Building on…
PromptAug: Fine-grained Conflict Classification Using Data Augmentation
Oliver Warke, Joemon M. Jose, Faegheh Hasibi +1
Given the rise of conflicts on social media, effective classification models to detect harmful behaviours are essential. Following the garbage-in-garbage-out maxim, machine learnin…
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…
Graph-Embedding Empowered Entity Retrieval
Emma J. Gerritse, Faegheh Hasibi, Arjen P. de Vries
In this research, we investigate methods for entity retrieval using graph embeddings. While various methods have been proposed over the years, most utilize a single graph embedding…
FACE: A Fine-Grained Reference-Free Evaluator for Conversational Information Access
Hideaki Joko, Faegheh Hasibi
A systematic, reliable, and low-cost evaluation of Conversational Information Access (CIA) systems remains an open challenge. Existing reference-based evaluation methods are proven…
LLM-Evaluation Tropes: Perspectives on the Validity of LLM-Evaluations
Laura Dietz, Oleg Zendel, Peter Bailey +6
Large Language Models (LLMs) are increasingly used to evaluate information retrieval (IR) systems, generating relevance judgments traditionally made by human assessors. Recent empi…
Adaptive Orchestration of Modular Generative Information Access Systems
Mohanna Hoveyda, Harrie Oosterhuis, Arjen P. de Vries +2
Advancements in large language models (LLMs) have driven the emergence of complex new systems to provide access to information, that we will collectively refer to as modular genera…
SPILL: Domain-Adaptive Intent Clustering based on Selection and Pooling with Large Language Models
I-Fan Lin, Faegheh Hasibi, Suzan Verberne
In this paper, we propose Selection and Pooling with Large Language Models (SPILL), an intuitive and domain-adaptive method for intent clustering without fine-tuning. Existing embe…
Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Models
Kristian G. Barman, Sascha Caron, Emily Sullivan +19
This paper explores ideas and provides a potential roadmap for the development and evaluation of physics-specific large-scale AI models, which we call Large Physics Models (LPMs).…
CRS Arena: Crowdsourced Benchmarking of Conversational Recommender Systems
Nolwenn Bernard, Hideaki Joko, Faegheh Hasibi +1
We introduce CRS Arena, a research platform for scalable benchmarking of Conversational Recommender Systems (CRS) based on human feedback. The platform displays pairwise battles be…
Generate then Refine: Data Augmentation for Zero-shot Intent Detection
I-Fan Lin, Faegheh Hasibi, Suzan Verberne
In this short paper we propose a data augmentation method for intent detection in zero-resource domains. Existing data augmentation methods rely on few labelled examples for each i…
AQA: Adaptive Question Answering in a Society of LLMs via Contextual Multi-Armed Bandit
Mohanna Hoveyda, Arjen P. de Vries, Maarten de Rijke +2
In question answering (QA), different questions can be effectively addressed with different answering strategies. Some require a simple lookup, while others need complex, multi-ste…
Real World Conversational Entity Linking Requires More Than Zeroshots
Mohanna Hoveyda, Arjen P. de Vries, Maarten de Rijke +1
Entity linking (EL) in conversations faces notable challenges in practical applications, primarily due to the scarcity of entity-annotated conversational datasets and sparse knowle…
Doing Personal LAPS: LLM-Augmented Dialogue Construction for Personalized Multi-Session Conversational Search
Hideaki Joko, Shubham Chatterjee, Andrew Ramsay +3
The future of conversational agents will provide users with personalized information responses. However, a significant challenge in developing models is the lack of large-scale dia…