Nandan Thakur's picture

Nandan Thakur

nthakur

·

https://thakur-nandan.github.io

AI & ML interests

NLP, IR, QA

Recent Activity

liked a model 1 day ago

Alibaba-NLP/gte-large-en-v1.5

liked a model 1 day ago

Qwen/Qwen3-Embedding-0.6B

upvoted a collection 1 day ago

Qwen3-Embedding

View all activity

Organizations

nthakur's activity

upvoted a collection 1 day ago

Qwen3-Embedding

6 items • Updated 1 day ago • 58

upvoted a paper 15 days ago

Fixing Data That Hurts Performance: Cascading LLMs to Relabel Hard Negatives for Robust Information Retrieval

Paper • 2505.16967 • Published 16 days ago • 22

upvoted 2 collections 15 days ago

RLHN Datasets

RLHN: Cleaned Training Datasets with False Negatives Identified & Relabeled as ground truth. • 5 items • Updated 15 days ago • 4

Multilingual SFT & DPO Datasets

These SFT or DPO datasets were translated from English using the Mistral-7B-Instruct-v0.2 or taken from other sources. • 8 items • Updated Mar 31 • 3

upvoted a paper about 2 months ago

FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents

Paper • 2504.13128 • Published Apr 17 • 5

upvoted a collection about 2 months ago

Multimodal DSE Retrievers

A collection of DSE models for multimodal retrieval • 5 items • Updated Apr 15 • 14

upvoted 2 collections 2 months ago

🌐 NoMIRACL Dataset [EMNLP'24]

A collection of multilingual relevance assessment datasets. We also have SFT fine-tuned models (Mistral-7B & Llama-3 8B) • 7 items • Updated Mar 31 • 1

🏜️MIRAGE-Bench [NAACL'25]

Dataset Collection from the MIRAGE-Bench paper • 13 items • Updated Mar 31 • 2

upvoted a collection 3 months ago

DRAMA

A collection of small (sub-1B) multilingual dense retrievers that generalize well across a number of tasks and languages. • 3 items • Updated Feb 26 • 7

upvoted a paper 4 months ago

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Paper • 2501.12948 • Published Jan 22 • 400

upvoted a paper 7 months ago

NoMIRACL: Knowing When You Don't Know for Robust Multilingual Retrieval-Augmented Generation

Paper • 2312.11361 • Published Dec 18, 2023 • 1

upvoted an article 7 months ago

Article

Visually Multilingual: Introducing mcdse-2b

By

•

Oct 27, 2024

• 41

upvoted a paper about 1 year ago

MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Paper • 2406.01574 • Published Jun 3, 2024 • 47

upvoted an article about 1 year ago

Article

Training and Finetuning Embedding Models with Sentence Transformers v3

By

•

May 28, 2024

• 223

upvoted a collection about 1 year ago

🦢SWIM-IR Dataset [NAACL'24]

29 million Synthetic Wikipedia-based Multilingual Retrieval Training Pairs. • 4 items • Updated Mar 31 • 7

upvoted a paper about 1 year ago

Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval

Paper • 2311.05800 • Published Nov 10, 2023 • 4

upvoted a paper over 1 year ago

BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models

Paper • 2104.08663 • Published Apr 17, 2021 • 3