77 citations · 135 across the 21 of their papers we have counts for
25 papers
Correct Answers, Invalid Traces: What Verifiable Grade-School Math Reveals About Chain-of-Thought Traces
Ratish Puduppully, Pranabendu Misra, Paarth Iyer +3
Chain-of-thought traces are widely read as records of how models reach their answers, informing debugging, agent auditing, and claims about reasoning. Testing this interpretation i…
IndicIFEval: A Benchmark for Verifiable Instruction-Following Evaluation in 14 Indic Languages
Thanmay Jayakumar, Mohammed Safi Ur Rahman Khan, Raj Dabre +2
Instruction-following benchmarks remain predominantly English-centric, leaving a critical evaluation gap for the hundreds of millions of Indic language speakers. We introduce Indic…
The Illusion of Generalization in Tabular Language Models
Aditya Gorla, Ratish Puduppully
Tabular Language Models (TLMs) have been claimed to achieve strong generalization for tabular prediction. We conduct a systematic re-evaluation of Tabula-8B as a representative TLM…
RiddleBench: A New Generative Reasoning Benchmark for LLMs
Deepon Halder, Alan Saji, Thanmay Jayakumar +3
Large Language Models have demonstrated strong performance on many established reasoning benchmarks. However, these benchmarks primarily evaluate structured skills like quantitativ…
Chimera: State Space Models Beyond Sequences
Aakash Lahoti, Tanya Marwah, Ratish Puduppully +1
Transformer-based deep learning methods have become the standard approach for modeling diverse data such as sequences, images, and graphs. These methods rely on self-attention, whi…
The Reasoning Lingua Franca: A Double-Edged Sword for Multilingual AI
Alan Saji, Raj Dabre, Anoop Kunchukuttan +1
Large Reasoning Models (LRMs) achieve strong performance on mathematical, scientific, and other question-answering tasks, but their multilingual reasoning abilities remain underexp…
Improving Genomic Models via Task-Specific Self-Pretraining
Sohan Mupparapu, Parameswari Krishnamurthy, Ratish Puduppully
Pretraining DNA language models (DNALMs) on the full human genome is resource-intensive, yet often considered necessary for strong downstream performance. Inspired by recent findin…
An Empirical Comparison of Vocabulary Expansion and Initialization Approaches for Language Models
Nandini Mundra, Aditya Nanda Kishore, Raj Dabre +3
Language Models (LMs) excel in natural language processing tasks for English but show reduced performance in most other languages. This problem is commonly tackled by continually p…
How Good is Zero-Shot MT Evaluation for Low Resource Indian Languages?
Anushka Singh, Ananya B. Sai, Raj Dabre +3
While machine translation evaluation has been studied primarily for high-resource languages, there has been a recent interest in evaluation for low-resource languages due to the in…
Airavata: Introducing Hindi Instruction-tuned LLM
Jay Gala, Thanmay Jayakumar, Jaavid Aktar Husain +8
We announce the initial release of "Airavata," an instruction-tuned LLM for Hindi. Airavata was created by fine-tuning OpenHathi with diverse, instruction-tuning Hindi datasets to…
RomanSetu: Efficiently unlocking multilingual capabilities of Large Language Models via Romanization
Jaavid Aktar Husain, Raj Dabre, Aswanth Kumar +4
This study addresses the challenge of extending Large Language Models (LLMs) to non-English languages that use non-Roman scripts. We propose an approach that utilizes the romanized…
VerityMath: Advancing Mathematical Reasoning by Self-Verification Through Unit Consistency
Vernon Toh Yan Han, Ratish Puduppully, Nancy F. Chen
Large Language Models (LLMs), combined with program-based solving techniques, are increasingly demonstrating proficiency in mathematical reasoning. For example, closed-source model…
A Comprehensive Analysis of Adapter Efficiency
Nandini Mundra, Sumanth Doddapaneni, Raj Dabre +3
Adapters have been positioned as a parameter-efficient fine-tuning (PEFT) approach, whereby a minimal number of parameters are added to the model and fine-tuned. However, adapters…
IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages
Jay Gala, Pranjal A. Chitale, Raghavan AK +11
India has a rich linguistic landscape with languages from 4 major language families spoken by over a billion people. 22 of these languages are listed in the Constitution of India (…
CTQScorer: Combining Multiple Features for In-context Example Selection for Machine Translation
Aswanth Kumar, Ratish Puduppully, Raj Dabre +1
Large language models have demonstrated the capability to perform on machine translation when the input is prompted with a few examples (in-context learning). Translation quality d…
Decomposed Prompting for Machine Translation Between Related Languages using Large Language Models
Ratish Puduppully, Anoop Kunchukuttan, Raj Dabre +2
This study investigates machine translation between related languages i.e., languages within the same family that share linguistic characteristics such as word order and lexical si…
Multi-Document Summarization with Centroid-Based Pretraining
Ratish Puduppully, Parag Jain, Nancy F. Chen +1
In Multi-Document Summarization (MDS), the input can be modeled as a set of documents, and the output is its summary. In this paper, we focus on pretraining objectives for MDS. Spe…
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran +74
Evaluation in machine learning is usually informed by past choices, for example which datasets or metrics to use. This standardization enables the comparison on equal footing using…
IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages
Aman Kumar, Himani Shrotriya, Prachi Sahu +6
Natural Language Generation (NLG) for non-English languages is hampered by the scarcity of datasets in these languages. In this paper, we present the IndicNLG Benchmark, a collecti…
Data-to-text Generation with Variational Sequential Planning
Ratish Puduppully, Yao Fu, Mirella Lapata
We consider the task of data-to-text generation, which aims to create textual output from non-linguistic input. We focus on generating long-form text, i.e., documents with multiple…
IndicBART: A Pre-trained Model for Indic Natural Language Generation
Raj Dabre, Himani Shrotriya, Anoop Kunchukuttan +3
In this paper, we study pre-trained sequence-to-sequence models for a group of related languages, with a focus on Indic languages. We present IndicBART, a multilingual, sequence-to…
Data-to-text Generation with Macro Planning
Ratish Puduppully, Mirella Lapata
Recent approaches to data-to-text generation have adopted the very successful encoder-decoder architecture or variants thereof. These models generate text which is fluent (but ofte…
Transition-Based Deep Input Linearization
Ratish Puduppully, Yue Zhang, Manish Shrivastava
Traditional methods for deep NLG adopt pipeline approaches comprising stages such as constructing syntactic input, predicting function words, linearizing the syntactic input and ge…
Data-to-text Generation with Entity Modeling
Ratish Puduppully, Li Dong, Mirella Lapata
Recent approaches to data-to-text generation have shown great promise thanks to the use of large-scale datasets and the application of neural network architectures which are traine…