79 citations · 447 across the 119 of their papers we have counts for
62 papers · 1 filter
DirectSpeech2LLM: A Simple End-to-End Framework to Mitigate Prompt Overfitting in Speech-LLMs
Hemant Yadav, Sunayana Sitaram, Roger Zimmermann +1
Speech-LLMs often exhibit prompt overfitting, where models solely trained on automatic speech recognition (ASR) instruction fail to generalize to new instructions such as speech tr…
Exploring Collaboration between a language and a non-language agent
Harini S, Somesh Singh, Yaman K Singla +3
LLMs are increasingly deployed as orchestrators that coordinate specialized subagents to solve complex tasks through natural language. However, in many important domains like game…
TextNCA: Neural Cellular Automata for Language Modeling via Hierarchical Local Attention
Avni Mittal, Avinash Anand, Ashutosh Kumar +7
Can a strictly local, iterated, weight-shared computation primitive support language modelling, and which of those three properties actually drives the model's behaviour? We define…
StocksTalk: A Voice-Enabled Conversational Agent for Structured Query Generation over Web Data
Akshat Parmar, Vikranth Udandarao, Abhay Shakya +4
StocksTalk is a voice-enabled conversational system for transforming spoken financial screening requests into executable and validated structured queries over real-world market dat…
The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes
Avinash Anand, Mahisha Ramesh, Avni Mittal +8
Reasoning has become central to how Large Language Models (LLMs) are evaluated and interpreted, spanning Chain-of-Thought (CoT), mathematical problem-solving, multi-hop question an…
IRIS: Interleaved Reinforcement with Incremental Staged Curriculum for Cross-Lingual Mathematical Reasoning
Navya Gupta, Rishitej Reddy Vyalla, Avinash Anand +8
Curriculum learning helps language models tackle complex reasoning by gradually increasing task difficulty. However, it often fails to generate consistent step-by-step reasoning, e…
LittiChoQA: Literary Texts in Indic Languages Chosen for Question Answering
Aarya Khandelwal, Ritwik Mishra, Rajiv Ratn Shah
Long-context question answering (QA) over literary texts poses significant challenges for modern large language models, particularly in low-resource languages. We address the scarc…
Structured Definitions and Segmentations for Legal Reasoning in LLMs: A Study on Indian Legal Data
Mann Khatri, Mirza Yusuf, Rajiv Ratn Shah +1
Large Language Models (LLMs), trained on extensive datasets from the web, exhibit remarkable general reasoning skills. Despite this, they often struggle in specialized areas like l…
Long-context Non-factoid Question Answering in Indic Languages
Ritwik Mishra, Rajiv Ratn Shah, Ponnurangam Kumaraguru
Question Answering (QA) tasks, which involve extracting answers from a given context, are relatively straightforward for modern Large Language Models (LLMs) when the context is sho…
Multilingual Mathematical Reasoning: Advancing Open-Source LLMs in Hindi and English
Avinash Anand, Kritarth Prasad, Chhavi Kirtani +4
Large Language Models (LLMs) excel in linguistic tasks but struggle with mathematical reasoning, particularly in non English languages like Hindi. This research aims to enhance the…
Knowledge Graphs are all you need: Leveraging KGs in Physics Question Answering
Krishnasai Addala, Kabir Dev Paul Baghel, Dhruv Jain +5
This study explores the effectiveness of using knowledge graphs generated by large language models to decompose high school-level physics questions into sub-questions. We introduce…
Steps are all you need: Rethinking STEM Education with Prompt Engineering
Krishnasai Addala, Kabir Dev Paul Baghel, Navya Gupta +4
Few shot and Chain-of-Thought prompting have shown promise when applied to Physics Question Answering Tasks, but are limited by the lack of mathematical ability inherent to LLMs, a…
JOOCI: a Framework for Learning Comprehensive Speech Representations
Hemant Yadav, Rajiv Ratn Shah, Sunayana Sitaram
Information in speech can be categorized into two groups: Content (what is being said, such as linguistics) and Other (how it is expressed such as information about speaker and par…
Multilingual Non-Factoid Question Answering with Answer Paragraph Selection
Ritwik Mishra, Sreeram Vennam, Rajiv Ratn Shah +1
Most existing Question Answering Datasets (QuADs) primarily focus on factoid-based short-context Question Answering (QA) in high-resource languages. However, the scope of such data…
Speech Representation Learning Revisited: The Necessity of Separate Learnable Parameters and Robust Data Augmentation
Hemant Yadav, Sunayana Sitaram, Rajiv Ratn Shah
Speech modeling methods learn one embedding for a fixed segment of speech, typically in between 10-25 ms. The information present in speech can be divided into two categories: "wha…
MS-HuBERT: Mitigating Pre-training and Inference Mismatch in Masked Language Modelling methods for learning Speech Representations
Hemant Yadav, Sunayana Sitaram, Rajiv Ratn Shah
In recent years, self-supervised pre-training methods have gained significant traction in learning high-level information from raw speech. Among these methods, HuBERT has demonstra…
Context-Enhanced Language Models for Generating Multi-Paper Citations
Avinash Anand, Kritarth Prasad, Ujjwal Goel +4
Citation text plays a pivotal role in elucidating the connection between scientific documents, demanding an in-depth comprehension of the cited paper. Constructing citations is oft…
Mathify: Evaluating Large Language Models on Mathematical Problem Solving Tasks
Avinash Anand, Mohit Gupta, Kritarth Prasad +5
The rapid progress in the field of natural language processing (NLP) systems and the expansion of large language models (LLMs) have opened up numerous opportunities in the field of…
KG-CTG: Citation Generation through Knowledge Graph-guided Large Language Models
Avinash Anand, Mohit Gupta, Kritarth Prasad +4
Citation Text Generation (CTG) is a task in natural language processing (NLP) that aims to produce text that accurately cites or references a cited document within a source documen…
MM-PhyQA: Multimodal Physics Question-Answering With Multi-Image CoT Prompting
Avinash Anand, Janak Kapuriya, Apoorv Singh +5
While Large Language Models (LLMs) can achieve human-level performance in various tasks, they continue to face challenges when it comes to effectively tackling multi-step physics r…
Multilingual Coreference Resolution in Low-resource South Asian Languages
Ritwik Mishra, Pooja Desur, Rajiv Ratn Shah +1
Coreference resolution involves the task of identifying text spans within a discourse that pertain to the same real-world entity. While this task has been extensively explored in t…
Isometric Neural Machine Translation using Phoneme Count Ratio Reward-based Reinforcement Learning
Shivam Ratnakant Mhaskar, Nirmesh J. Shah, Mohammadi Zaki +3
Traditional Automatic Video Dubbing (AVD) pipeline consists of three key modules, namely, Automatic Speech Recognition (ASR), Neural Machine Translation (NMT), and Text-to-Speech (…
Long-Term Ad Memorability: Understanding & Generating Memorable Ads
Harini SI, Somesh Singh, Yaman K Singla +5
Despite the importance of long-term memory in marketing and brand building, until now, there has been no large-scale study on the memorability of ads. All previous memorability stu…
Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior
Ashmit Khandelwal, Aditya Agrawal, Aanisha Bhattacharyya +8
Shannon and Weaver's seminal information theory divides communication into three levels: technical, semantic, and effectiveness. While the technical level deals with the accurate r…