Papers by Nandan Thakur
Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks (2021.naacl-main)
Copied to clipboard
| Challenge: | Cross-encoders perform full-attention over the input pair, while bi-encoding requires substantial training data and fine-tuning over the target task to achieve competitive performance. |
| Approach: | They propose a data augmentation strategy that uses cross-encoders to label larger set of input pairs to augment training data for bi-encoding. |
| Outcome: | The proposed approach improves on multiple tasks and domain adaptation tasks by up to 37 points compared to the original bi-encoder performance. |
“Knowing When You Don’t Know”: A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generation (2024.findings-emnlp)
Copied to clipboard
Nandan Thakur, Luiz Bonifacio, Crystina Zhang, Odunayo Ogundepo, Ehsan Kamalloo, David Alfonso-Hermelo, Xiaoguang Li, Qun Liu, Boxing Chen, Mehdi Rezagholizadeh, Jimmy Lin
| Challenge: | Prior work on RAG grounds Large Language Models to reduce factual hallucinations lacks a comprehensive evaluation of different language families. |
| Approach: | They propose a human-annotated dataset for evaluating LLM robustness in RAG . they find that most models struggle to balance the two capacities . |
| Outcome: | The proposed dataset includes both a non-relevant and a relevant subset. |
Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval (2024.naacl-long)
Copied to clipboard
| Challenge: | et al., 2020: performance of dense retrieval models in multilingual retrieval is limited due to uneven and scarce training data available across multiple languages. |
| Approach: | They propose a synthetic retrieval training dataset containing 33 languages for fine-tuning multilingual retrievers without human supervision. |
| Outcome: | The proposed model outperforms human-supervised retrieval models on three retrieval benchmarks. |
MIRACL: A Multilingual Retrieval Dataset Covering 18 Diverse Languages (2023.tacl-1)
Copied to clipboard
Xinyu Zhang, Nandan Thakur, Odunayo Ogundepo, Ehsan Kamalloo, David Alfonso-Hermelo, Xiaoguang Li, Qun Liu, Mehdi Rezagholizadeh, Jimmy Lin
| Challenge: | MIRACL is a multilingual dataset for ad hoc retrieval across 18 languages that collectively encompass over three billion native speakers around the world. |
| Approach: | They have gathered over 726k high-quality relevance judgments for 78k queries over Wikipedia in these languages, where all annotations have been performed by native speakers hired by their team. |
| Outcome: | MIRACL covers languages that are typologically close as well as distant from 10 language families and 13 sub-families, associated with varying amounts of publicly available resources. |
GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval (2022.naacl-main)
Copied to clipboard
| Challenge: | Dense retrieval approaches suffer from the lexical gap and require large amounts of training data. |
| Approach: | They propose an unsupervised method for domain adaptation that uses query generator and pseudo labeling from a cross-encoder to improve retrieval performance. |
| Outcome: | The proposed method outperforms state-of-the-art retrieval methods on domain-specialized datasets by 9.3 points nDCG@10 on six tasks. |
Evaluating Embedding APIs for Information Retrieval (2023.acl-industry)
Copied to clipboard
Ehsan Kamalloo, Xinyu Zhang, Odunayo Ogundepo, Nandan Thakur, David Alfonso-hermelo, Mehdi Rezagholizadeh, Jimmy Lin
| Challenge: | a growing number of language models are limiting their access to the community . we evaluate existing APIs for domain generalization and multilingual retrieval . |
| Approach: | They evaluate semantic embedding APIs in retrieval scenarios to assess their capabilities . they use BEIR and MIRACL to re-rank BM25 results using the APIs . |
| Outcome: | The proposed model is based on semantic embedding APIs that build vector representations of a given text. |
BrowseComp-Plus: A Fair and Disentangled Evaluation Benchmark for Deep Search Agents (2026.acl-long)
Copied to clipboard
Zijian Chen, Xueguang Ma, Shengyao Zhuang, Ping Nie, Kai Zou, Sahel Sharifymoghaddam, Andrew Liu, Joshua Green, Kshama Patel, Ruoxi Meng, Mingyi Su, Yanxi Li, Haoran Hong, Xinyu Shi, Xuye Liu, Hosna Oyarhoseini, Nandan Thakur, Crystina Zhang, Luyu Gao, Wenhu Chen, Jimmy Lin
| Challenge: | Existing benchmarks for deep search agents rely on blackbox web search APIs . dynamic and opaque web APIs hinder reproducibility and fair comparisons - authors . |
| Approach: | They propose a benchmark that employs a fixed corpus for controlled retrieval for deep search agents. |
| Outcome: | The new benchmark shows that agents that combine large language models with retrieval tools excel at complex, reasoning-intensive queries. |
Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Using LLMs to identify false negatives improves retrieval and reranker models by 0.7-1.4 points on BEIR and by 1.7-1.8 points on AIR-Bench evaluation. |
| Approach: | They use a simple, cost-effective approach to identify and relabel false negatives in training datasets. |
| Outcome: | The proposed approach improves retrieval models by 0.7-1.4 points on BEIR and by 1.7-1.8 points on AIR-Bench evaluation. |
MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems (2025.naacl-long)
Copied to clipboard
| Challenge: | Traditional retrieval-augmented generation benchmarks use heuristics as the ground truth for evaluation, but require an expensive large language model (LLM) as a judge for a reliable evaluation. |
| Approach: | They propose to use large language models as a judge for retrieval-augmented generation benchmarks . they use heuristic metrics as input and a large language model as heuriistic input . |
| Outcome: | The proposed method couples heuristic features with large language models as judge for evaluation. |