Papers by Rudra Murthy

19 papers
Prompting with Pseudo-Code Instructions (2023.emnlp-main)

Copied to clipboard

Challenge: ambiguity in natural language can hinder performance of large language models.
Approach: They manually create a dataset of pseudo-code prompts for 132 different classification, QA, and generative language tasks, sourced from the Super-NaturalInstructions dataset.
Outcome: The pseudo-code prompts improve the performance of two LLM families, BLOOM and CodeGen.
Benchmarking and Building Zero-Shot Hindi Retrieval Model with Hindi-BEIR and NLLB-E5 (2025.naacl-long)

Copied to clipboard

Challenge: Existing benchmarks for evaluating retrieval models in Hindi are lacking . despite efforts to build multilingual retrieval systems, this is still a work in progress .
Approach: They evaluate Hindi retrieval models on the Hindi-BEIR benchmark and introduce a multilingual model that leverages a zero-shot approach to support Hindi without the need for Hindi training data.
Outcome: The proposed model leverages a zero-shot approach to support Hindi without the need for Hindi training data.
Role of Language Relatedness in Multilingual Fine-tuning of Language Models: A Case Study in Indo-Aryan Languages (2021.emnlp-main)

Copied to clipboard

Challenge: A study of multilingual fine-tuning yields better performance on downstream NLP applications . low resource languages such as Oriya and Punjabi are found to be the largest beneficiaries of multi-lingual fine tuning.
Approach: They propose to leverage the relatedness of languages that belong to the same family in NLP models by multilingual fine-tuning.
Outcome: The proposed approach improves performance on downstream NLP tasks by 15% compared to monolingual fine-tuning.
MILU: A Multi-task Indic Language Understanding Benchmark (2025.naacl-long)

Copied to clipboard

Challenge: Existing benchmarks focus on English, leaving substantial gaps in assessing LLM capabilities in low-resource and linguistically diverse languages.
Approach: They propose a multi-task indic language understanding benchmark to assess LLMs in low-resource languages.
Outcome: The new benchmark spans 8 domains and 41 subjects across 11 Indic languages, reflecting general and culturally specific knowledge.
On Utilizing Constituent Language Resources to Improve Downstream Tasks in Hinglish (2022.findings-emnlp)

Copied to clipboard

Challenge: Intuitively, Hindi and English corpora should aid improve task performance on code-switched Hindi-English.
Approach: They propose a meta-learning framework that utilizes the labelled resources of the downstream tasks in the constituent languages to improve task performance.
Outcome: The proposed framework improves the performance on downstream tasks on code-switched Hindi-English.
Naamapadam: A Large-Scale Named Entity Annotated Data for Indic Languages (2023.acl-long)

Copied to clipboard

Challenge: Named Entity Recognition (NER) is a fundamental task in natural language processing (NLP).
Approach: They present the largest publicly available Named Entity Recognition dataset for the 11 major Indian languages from two language families.
Outcome: The proposed dataset is the largest publicly available Named Entity Recognition (NER) dataset for the 11 major Indian languages from two language families.
Data and Model Centric Approaches for Expansion of Large Language Models to New languages (2025.emnlp-tutorials)

Copied to clipboard

Challenge: Existing LLMs mainly support English alongside a handful of high resource languages . this leaves a major gap for most low-resource languages despite increasing pace of research .
Approach: This tutorial examines approaches to expand the language coverage of LLMs . they look at tokenizer training, pre-training, instruction tuning, alignment, evaluation, etc.
Outcome: This tutorial examines approaches to expand the language coverage of LLMs . it provides an efficient and viable path to bring LLM technologies to low-resource languages .
Addressing word-order Divergence in Multilingual Neural Machine Translation for extremely Low Resource Languages (N19-1)

Copied to clipboard

Challenge: Existing studies show that transfer learning works best when the languages are related.
Approach: They propose to pre-order assisting language sentences to match the word order of the source language and train the parent model.
Outcome: The proposed model can improve translation quality in low-resource scenarios by pre-ordering the assisting language sentences to match the word order of the source language and training the parent model.
Looking inside Noun Compounds: Unsupervised Prepositional and Free Paraphrasing (2020.findings-emnlp)

Copied to clipboard

Challenge: Noun compound interpretation is the task of uncovering the semantic relation between the components of a noun compound.
Approach: They propose an unsupervised method for identifying such relations between the components of a noun compound using pre-trained contextualized language models.
Outcome: The proposed method outperforms supervised approaches for free paraphrasing and prepositional paraphrases using pre-trained language models to uncover ‘missing’ words.
Power doesn’t reside in size: A Low Parameter Hybrid Language Model (HLM) for Sentiment Analysis in Code-mixed data (2025.emnlp-main)

Copied to clipboard

Challenge: Code-mixed text presents significant challenges for machine learning due to interplay of distinct grammatical structures, effectively forming a hybrid language.
Approach: They propose a Hybrid Language Model that combines a multilingual encoder and a lightweight decoder to achieve sentiment classification performance comparable to those of fine-tuned Large Language Models.
Outcome: The proposed model outperforms models trained individually in sentiment detection tasks.
UR2N: Unified Retriever and ReraNker (2025.coling-industry)

Copied to clipboard

Challenge: XTR-style retrieval on top of trained Mono-T5 reranker is suboptimal for two-stage retrieval, arguing that it is sub-optimal.
Approach: They propose a unified encoder-decoder architecture with a novel training regimen which enables the encoder representation to be used for retrieval and the decoder for re-ranking within a single unified model.
Outcome: The proposed architecture outperforms ColBERT, XTR, and even serves as a superior reranker compared to the Mono-T5 re-ranker.
HiNER: A large Hindi Named Entity Recognition Dataset (2022.lrec-1)

Copied to clipboard

Challenge: Named Entity Recognition (NER) is a lowerlevel task that aims to provide class labels like Person, Location, Organisation, Time, and Number to words in free text.
Approach: They propose to use a standard-abiding Hindi NER dataset to analyze the annotations of a class of naming entities in free text.
Outcome: The proposed dataset achieves a weighted F1 score of 88.78 with all the tags and 92.22 when we collapse the tag-set.
Happy Are Those Who Grade without Seeing: A Multi-Task Learning Approach to Grade Essays Using Gaze Behaviour (2020.aacl-main)

Copied to clipboard

Challenge: Using gaze behaviour to solve automatic essay grading tasks is costly in terms of time and money.
Approach: They propose to collect gaze behaviour from 48 essays and learn gaze behaviour for the rest of the essays using a multi-task learning framework.
Outcome: The proposed approach achieves a statistically significant improvement over the state-of-the-art system for the essay sets where gaze data is available.
“You are Beautiful, Body Image Stereotypes are Ugly!” BIStereo: A Benchmark to Measure Body Image Stereotypes in Language Models (2025.findings-acl)

Copied to clipboard

Challenge: BIStereo is a suite of language models that uncover body image stereotypes in language models.
Approach: They propose a metric, TriSentBias, that captures the biased preferences of LMs towards a certain body type over others.
Outcome: The proposed metric captures biased preferences of LMs towards a certain body type over others.
PUB: A Pragmatics Understanding Benchmark for Assessing LLMs’ Pragmatics Capabilities (2024.findings-acl)

Copied to clipboard

Challenge: Pragmatics understanding is not well studied in LLMs, but their understanding of pragmatics is lacking.
Approach: They propose to use a dataset to measure LLMs' understanding of pragmatics to evaluate their models.
Outcome: The proposed dataset includes 14 tasks in four pragmatics phenomena, namely; Implicature, Presupposition, Reference, and Deixis.
Judicious Selection of Training Data in Assisting Language for Multilingual Neural NER (P18-2)

Copied to clipboard

Challenge: Existing approaches to improve NER performance add training data from one or more assisting languages to the primary language.
Approach: They propose a metric based on symmetric KL divergence to filter out highly divergent training instances in the assisting language.
Outcome: The proposed method improves NER performance in many languages, including those with limited training data.
Semi-Structured Object Sequence Encoders (2023.findings-emnlp)

Copied to clipboard

Challenge: Semi-structured object sequences are often represented as a sequence of key-value pairs over time . authors propose a two-part approach that takes each key independently and encodes a representation of its values over time.
Approach: They propose a two-part approach that first considers each key independently and encodes a representation of its values over time.
Outcome: The proposed approach outperforms existing methods on multiple prediction tasks using real-world data.
INDIC QA BENCHMARK: A Multilingual Benchmark to Evaluate Question Answering capability of LLMs for Indic Languages (2025.findings-naacl)

Copied to clipboard

Challenge: Large Language Models perform well on unseen tasks in English, but their abilities in non-English languages are less explored due to limited benchmarks and training data.
Approach: They propose to release a large dataset for context-grounded question answering in 11 major Indian languages.
Outcome: The Indic-QA Benchmark compared large datasets of large LLMs on extractive and abstractive tasks in 11 major Indian languages.
Stereotype Detection as a Catalyst for Enhanced Bias Detection: A Multi-Task Learning Approach (2025.findings-acl)

Copied to clipboard

Challenge: a new study addresses bias and stereotypes in language models by exploring how learning them together improves performance.
Approach: They propose a dataset for bias and stereotype detection that integrates religion, gender, socio-economic status, race, profession, and others.
Outcome: The proposed dataset compares encoder-only models and fine-tuned decoder- only models . the results show that learning stereotypes together improves bias detection .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations