117 citations · 587 across the 36 of their papers we have counts for
42 papers
PolyAlign: Conditional Human-Distribution Alignment
L. D. M. S. Sai Teja, Ufaq Khan, Sathira Silva +2
Post-training methods such as supervised fine-tuning (SFT) and preference optimization typically align language models toward a single global assistant behavior. While effective fo…
Beyond Output Critique: Self-Correction via Task Distillation
Hossein A. Rahmani, Mengting Wan, Pei Zhou +4
Large language models (LLMs) have shown promising self-correction abilities, where iterative refinement improves the quality of generated responses. However, most existing approach…
Fine-tuning Small Language Models as Efficient Enterprise Search Relevance Labelers
Yue Kang, Zhuoyi Huang, Benji Schussheim +19
In enterprise search, building high-quality datasets at scale remains a central challenge due to the difficulty of acquiring labeled data. To resolve this challenge, we propose an…
Overview of the TREC 2022 deep learning track
Nick Craswell, Bhaskar Mitra, Emine Yilmaz +4
This is the fourth year of the TREC Deep Learning track. As in previous years, we leverage the MS MARCO datasets that made hundreds of thousands of human annotated training labels…
Overview of the TREC 2023 deep learning track
Nick Craswell, Bhaskar Mitra, Emine Yilmaz +5
This is the fifth year of the TREC Deep Learning track. As in previous years, we leverage the MS MARCO datasets that made hundreds of thousands of human-annotated training labels a…
Overview of the TREC 2021 deep learning track
Nick Craswell, Bhaskar Mitra, Emine Yilmaz +2
This is the third year of the TREC Deep Learning track. As in previous years, we leverage the MS MARCO datasets that made hundreds of thousands of human annotated training labels a…
Judging the Judges: A Collection of LLM-Generated Relevance Judgements
Hossein A. Rahmani, Clemencia Siro, Mohammad Aliannejadi +6
Using Large Language Models (LLMs) for relevance assessments offers promising opportunities to improve Information Retrieval (IR), Natural Language Processing (NLP), and related fi…
JudgeBlender: Ensembling Judgments for Automatic Relevance Assessment
Hossein A. Rahmani, Emine Yilmaz, Nick Craswell +1
The effective training and evaluation of retrieval systems require a substantial amount of relevance judgments, which are traditionally collected from human assessors -- a process…
LLMJudge: LLMs for Relevance Judgments
Hossein A. Rahmani, Emine Yilmaz, Nick Craswell +6
The LLMJudge challenge is organized as part of the LLM4Eval workshop at SIGIR 2024. Test collections are essential for evaluating information retrieval (IR) systems. The evaluation…
Report on the 1st Workshop on Large Language Model for Evaluation in Information Retrieval (LLM4Eval 2024) at SIGIR 2024
Hossein A. Rahmani, Clemencia Siro, Mohammad Aliannejadi +6
The first edition of the workshop on Large Language Model for Evaluation in Information Retrieval (LLM4Eval 2024) took place in July 2024, co-located with the ACM SIGIR Conference…
SynDL: A Large-Scale Synthetic Test Collection for Passage Retrieval
Hossein A. Rahmani, Xi Wang, Emine Yilmaz +3
Large-scale test collections play a crucial role in Information Retrieval (IR) research. However, according to the Cranfield paradigm and the research into publicly available datas…
Synthetic Test Collections for Retrieval Evaluation
Hossein A. Rahmani, Nick Craswell, Emine Yilmaz +2
Test collections play a vital role in evaluation of information retrieval (IR) systems. Obtaining a diverse set of user queries for test collection construction can be challenging,…
MS MARCO Web Search: a Large-scale Information-rich Web Dataset with Millions of Real Click Labels
Qi Chen, Xiubo Geng, Corby Rosset +28
Recent breakthroughs in large models have highlighted the critical significance of data scale, labels and modals. In this paper, we introduce MS MARCO Web Search, the first large-s…
Towards Group-aware Search Success
Haolun Wu, Bhaskar Mitra, Nick Craswell
Traditional measures of search success often overlook the varying information needs of different demographic groups. To address this gap, we introduce a novel metric, named Group-a…
Large language models can accurately predict searcher preferences
Paul Thomas, Seth Spielman, Nick Craswell +1
Relevance labels, which indicate whether a search result is valuable to a searcher, are key to evaluating and optimising search systems. The best way to capture the true preference…
Patterns of gender-specializing query reformulation
Amifa Raj, Bhaskar Mitra, Nick Craswell +1
Users of search systems often reformulate their queries by adding query terms to reflect their evolving information need or to more precisely express their information need when th…
Less is Less: When Are Snippets Insufficient for Human vs Machine Relevance Estimation?
Gabriella Kazai, Bhaskar Mitra, Anlei Dong +2
Traditional information retrieval (IR) ranking models process the full text of documents. Newer models based on Transformers, however, would incur a high computational cost when pr…
Neural Approaches to Conversational Information Retrieval
Jianfeng Gao, Chenyan Xiong, Paul Bennett +1
A conversational information retrieval (CIR) system is an information retrieval (IR) system with a conversational interface which allows users to interact with the system to seek i…
Intra-Document Cascading: Learning to Select Passages for Neural Document Ranking
Sebastian Hofstätter, Bhaskar Mitra, Hamed Zamani +2
An emerging recipe for achieving state-of-the-art effectiveness in neural document re-ranking involves utilizing large pre-trained language models - e.g., BERT - to evaluate all in…
MS MARCO: Benchmarking Ranking Models in the Large-Data Regime
Nick Craswell, Bhaskar Mitra, Emine Yilmaz +2
Evaluation efforts such as TREC, CLEF, NTCIR and FIRE, alongside public leaderboard such as MS MARCO, are intended to encourage research and track our progress, addressing big ques…
TREC Deep Learning Track: Reusable Test Collections in the Large Data Regime
Nick Craswell, Bhaskar Mitra, Emine Yilmaz +3
The TREC Deep Learning (DL) Track studies ad hoc search in the large data regime, meaning that a large set of human-labeled training data is available. Results so far indicate that…
Improving Transformer-Kernel Ranking Model Using Conformer and Query Term Independence
Bhaskar Mitra, Sebastian Hofstatter, Hamed Zamani +1
The Transformer-Kernel (TK) model has demonstrated strong reranking performance on the TREC Deep Learning benchmark -- and can be considered to be an efficient (but slightly less e…
Significant Improvements over the State of the Art? A Case Study of the MS MARCO Document Ranking Leaderboard
Jimmy Lin, Daniel Campos, Nick Craswell +2
Leaderboards are a ubiquitous part of modern research in applied machine learning. By design, they sort entries into some linear order, where the top-scoring entry is recognized as…
Overview of the TREC 2020 deep learning track
Nick Craswell, Bhaskar Mitra, Emine Yilmaz +1
This is the second year of the TREC Deep Learning Track, with the goal of studying ad hoc ranking in the large training data regime. We again have a document retrieval task and a p…