3 citations · 5 across the 17 of their papers we have counts for
19 papers
COILD: An Indic-Centric Parallel Corpus and Benchmark for Machine Translation Across Indian Languages
Kshetrimayum Boynao Singh, Nitin Kumar Mishra, Palash Pratim Dutta +22
Machine translation (MT) for Indian languages remains constrained by the limited availability of high-quality, Indic-centric parallel corpora and evaluation benchmarks. Existing mu…
AUDITPLAN: Commit, Then Answer for Auditable Safety Alignment
Sai Sri Pushpa Jampani, Kshitij Mishra, Asif Ekbal
Safety tuning pipelines judge only the final answer, which makes it difficult to distinguish robust refusal from two undesirable shortcuts: blanket refusal on benign requests and p…
Source-Free MT Evaluation Is Not MT Evaluation
Baban Gain, Ramakrishna Appicharla, Asif Ekbal
Reference-based metrics remain the standard choice in machine translation evaluation, partly because quality estimation methods often correlate less well with human judgments. As a…
GPUAlert: A Zero-Instrumentation Process-Boundary Monitor for Diagnosing GPU Training-Job Failures
Parv Agarwal, Asif Ekbal
GPU training jobs fail often, roughly two in five on large production clusters, yet the operator typically learns of a failure only by reconnecting hours later. Experiment trackers…
Which Tokens Need Context? A Reference-Based Analysis of Translation Responsibility Using Fertility and Entropy
Ramakrishna Appicharla, Baban Gain, Santanu Pal +1
When humans translate, not every word depends equally on the surrounding context. Some tokens, particularly function words like pronouns and auxiliaries, rely heavily on preceding…
When Can We Trust the Sparse Lens? A Certification Framework for SAE Faithfulness
Dibyanayan Bandyopadhyay, Asif Ekbal
Sparse autoencoders (SAEs) are increasingly used to study internal representations in language models (LMs), but it remains unclear when an SAE-based representation reliably preser…
One Model to Translate Them All? A Journey to Mount Doom for Multilingual Model Merging
Baban Gain, Trilok Nath Singh, Asif Ekbal
Weight-space model merging combines independently fine-tuned checkpoints without access to the original training data. While merging has shown promise in multitask settings, its be…
Sparse Semantic Dimension as a Generalization Certificate for LLMs
Dibyanayan Bandyopadhyay, Asif Ekbal
Standard statistical learning theory predicts that Large Language Models (LLMs) should overfit because their parameter counts vastly exceed the number of training tokens. Yet, in p…
CAuSE: Decoding Multimodal Classifiers using Faithful Natural Language Explanation
Dibyanayan Bandyopadhyay, Soham Bhattacharjee, Mohammed Hasanuzzaman +1
Multimodal classifiers function as opaque black box models. While several techniques exist to interpret their predictions, very few of them are as intuitive and accessible as natur…
CorIL: Towards Enriching Indian Language to Indian Language Parallel Corpora and Machine Translation Systems
Soham Bhattacharjee, Mukund K Roy, Yathish Poojary +19
India's linguistic landscape is one of the most diverse in the world, comprising over 120 major languages and approximately 1,600 additional languages, with 22 officially recognize…
Beyond the Sentence: A Survey on Context-Aware Machine Translation with Large Language Models
Ramakrishna Appicharla, Baban Gain, Santanu Pal +1
Despite the popularity of the large language models (LLMs), their application to machine translation is relatively underexplored, especially in context-aware settings. This work pr…
Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation
Baban Gain, Dibyanayan Bandyopadhyay, Asif Ekbal +1
Large Language Models (LLMs) are rapidly reshaping machine translation (MT), particularly by introducing instruction-following, in-context learning, and preference-based alignment…
Thinking Machines: A Survey of LLM based Reasoning Strategies
Dibyanayan Bandyopadhyay, Soham Bhattacharjee, Asif Ekbal
Large Language Models (LLMs) are highly proficient in language-based tasks. Their language capabilities have positioned them at the forefront of the future AGI (Artificial General…
Balancing Global Quality and Pronoun-Specific Feedback for Context-Aware Machine Translation
Harshit Dhankhar, Baban Gain, Asif Ekbal +1
Context-aware machine translation can expose the evidence needed for pronoun choice, but standard fine-tuning does not explicitly prioritize these sparse discourse-sensitive decisi…
From Hallucinations to Facts: Enhancing Language Models with Curated Knowledge Graphs
Ratnesh Kumar Joshi, Sagnik Sengupta, Asif Ekbal
Hallucination, a persistent challenge plaguing language models, undermines their efficacy and trustworthiness in various natural language processing endeavors by generating respons…
Seeing Through VisualBERT: A Causal Adventure on Memetic Landscapes
Dibyanayan Bandyopadhyay, Mohammed Hasanuzzaman, Asif Ekbal
Detecting offensive memes is crucial, yet standard deep neural network systems often remain opaque. Various input attribution-based methods attempt to interpret their behavior, but…
A Case Study on Context-Aware Neural Machine Translation with Multi-Task Learning
Ramakrishna Appicharla, Baban Gain, Santanu Pal +2
In document-level neural machine translation (DocNMT), multi-encoder approaches are common in encoding context and source sentences. Recent studies \cite{li-etal-2020-multi-encoder…
Universal Adversarial Framework to Improve Adversarial Robustness for Diabetic Retinopathy Detection
Samrat Mukherjee, Dibyanayan Bandyopadhyay, Baban Gain +1
Diabetic Retinopathy (DR) is a prevalent illness associated with Diabetes which, if left untreated, can result in irreversible blindness. Deep Learning based systems are gradually…
Reference Free Domain Adaptation for Translation of Noisy Questions with Question Specific Rewards
Baban Gain, Ramakrishna Appicharla, Soumya Chennabasavaraj +3
Community Question-Answering (CQA) portals serve as a valuable tool for helping users within an organization. However, making them accessible to non-English-speaking users continue…