1 citations · 3 across the 16 of their papers we have counts for
16 papers
STAIR (STructure Aware Information Retriever): A novel dataset and LLM based retriever for document structure augmentation
Vineet Kumar, Meghanadh Pulivarthi, vishwajeet kumar +3
Retrieval Augmented Generation (RAG) is a key component for generating accurate and hallucination free answers using Large Language Models (LLMs). LLMs are improving at handling lo…
DKL: Decoupled Knowledge Learning for Instruction-Tuned Language Models
Kushagra Bhushan, Meghanadh Pulivarthi, Sai Krishna Reddy Sathi +7
RAG has become the de facto method for incorporating new, corpus-specific knowledge into an instruction following LLM (Instruct LLM). Although RAG-based prompting improves factual…
KItCAT: Knowledge Injection via Input Corruption for Auto-regressive Training
Meghanadh Pulivarthi, Kushagra Bhushan, Vineet Kumar +5
LLMs acquire vast amounts of knowledge during pre-training, but often lack the specialized knowledge needed to answer questions from niche sources such as manuals or technical docu…
SearchWiki: Learning to Build and Navigate Knowledge Wikis for Active Information Seeking
Guransh Singh, Vishwajeet Kumar, Arkadeep Acharya +3
Flat retrieval-augmented generation treats a corpus as a bag of chunks, discarding document hierarchy and cross document structure. We introduce SearchWiki, a harness framework tha…
Spatial Matryoshka Training for Multi-Granularity Visual Document Retrieval
Trishan Singha Roy, Arkadeep Acharya, Vishwajeet Kumar +2
Multi-modal late-interaction retrievers achieve strong retrieval on visually rich documents by representing each page as per patch embeddings and matching at the token level. Howev…
CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval
Adnan Qidwai, Anand Eswaran, Sonam Mishra +2
RAG ingestion pipelines frequently augment search corpus index with semantic enrichment indices (e.g., synthetic queries or summaries generated from corpus chunks) that are subsequ…
Granite Embedding Multilingual R2 Models
Parul Awasthy, Aashka Trivedi, Yushu Yang +14
We introduce the multilingual Granite Embedding R2 models, a family of encoder-based embedding models for enterprise-scale dense retrieval across 200+ languages. Extending our Engl…
Influence Guided Sampling for Domain Adaptation of Text Retrievers
Meet Doshi, Vishwajeet Kumar, Yulong Li +1
General-purpose open-domain dense retrieval systems are usually trained with a large, eclectic mix of corpora and search tasks. How should these diverse corpora and tasks be sample…
LMK > CLS: Landmark Pooling for Dense Embeddings
Meet Doshi, Aashka Trivedi, Vishwajeet Kumar +5
Representation learning is central to many downstream tasks such as search, clustering, classification, and reranking. State-of-the-art sequence encoders typically collapse a varia…
Granite Embedding R2 Models
Parul Awasthy, Aashka Trivedi, Yulong Li +17
We introduce the Granite Embedding R2 models, a comprehensive family of high-performance English encoder-based embedding models engineered for enterprise-scale dense retrieval appl…
Granite Embedding Models
Parul Awasthy, Aashka Trivedi, Yulong Li +19
We introduce the Granite Embedding models, a family of encoder-based embedding models designed for retrieval tasks, spanning dense-retrieval and sparse retrieval architectures, wit…
MILU: A Multi-task Indic Language Understanding Benchmark
Sshubam Verma, Mohammed Safi Ur Rahman Khan, Vishwajeet Kumar +2
Evaluating Large Language Models (LLMs) in low-resource and linguistically diverse languages remains a significant challenge in NLP, particularly for languages using non-Latin scri…
Benchmarking and Building Zero-Shot Hindi Retrieval Model with Hindi-BEIR and NLLB-E5
Arkadeep Acharya, Rudra Murthy, Vishwajeet Kumar +1
Given the large number of Hindi speakers worldwide, there is a pressing need for robust and efficient information retrieval systems for Hindi. Despite ongoing research, comprehensi…
Mistral-SPLADE: LLMs for better Learned Sparse Retrieval
Meet Doshi, Vishwajeet Kumar, Rudra Murthy +2
Learned Sparse Retrievers (LSR) have evolved into an effective retrieval strategy that can bridge the gap between traditional keyword-based sparse retrievers and embedding-based de…
Hindi-BEIR : A Large Scale Retrieval Benchmark in Hindi
Arkadeep Acharya, Rudra Murthy, Vishwajeet Kumar +1
Given the large number of Hindi speakers worldwide, there is a pressing need for robust and efficient information retrieval systems for Hindi. Despite ongoing research, there is a…
INDIC QA BENCHMARK: A Multilingual Benchmark to Evaluate Question Answering capability of LLMs for Indic Languages
Abhishek Kumar Singh, Vishwajeet kumar, Rudra Murthy +3
Large Language Models (LLMs) perform well on unseen tasks in English, but their abilities in non English languages are less explored due to limited benchmarks and training data. To…