← Search

Siva Sankalp Patel

5 accepted papers

2025

InspectorRAGet: An Introspection Platform for RAG Evaluation

NAACL 2025system demonstrations

Large Language Models (LLM) have become a popular approach for implementing Retrieval Augmented Generation (RAG) systems, and a significant amount of effort has been spent on building good models and metrics. In spite of increased recognition of the need for rigorous evaluation of RAG systems, few t…

2023

Semi-Structured Object Sequence Encoders

EMNLP 2023long findings

In this paper we explore the task of modeling semi-structured object sequences; in particular, we focus our attention on the problem of developing a structure-aware input representation for such sequences. Examples of such data include user activity on websites, machine logs, and many others. This t…

Cited by 0SourceScholar
2022

Fast and Light-Weight Answer Text Retrieval in Dialogue Systems

NAACL 2022industry

Dialogue systems can benefit from being able to search through a corpus of text to find information relevant to user requests, especially when encountering a request for which no manually curated response is available. The state-of-the-art technology for neural dense retrieval or re-ranking involves…

2021

Does Structure Matter? Encoding Documents for Machine Reading Comprehension

NAACL 2021long

Machine reading comprehension is a challenging task especially for querying documents with deep and interconnected contexts. Transformer-based methods have shown advanced performances on this task; however, most of them still treat documents as a flat sequence of tokens. This work proposes a new Tra…

Cited by 8SourcePDFScholar
2021

MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents

EMNLP 2021main

We propose MultiDoc2Dial, a new task and dataset on modeling goal-oriented dialogues grounded in multiple documents. Most previous works treat document-grounded dialogue modeling as machine reading comprehension task based on a single given document or passage. In this work, we aim to address more r…