Papers by Niloy Ganguly

27 papers
Learning Faster with Better Tokens: Parameter-Efficient Vocabulary Adaptation for Specialized Text Summarization (2026.acl-long)

Copied to clipboard

Challenge: a new approach to adapt generalist models to expert domains is needed to overcome this problem.
Approach: They propose a parameter-efficient domain adaptation approach that combines vocabulary adaptation with pretraining for LLM-based text summarization.
Outcome: The proposed approach reduces training time by 35-55% over continual pretraining and reduces parameter counts up to 37% w.r.t expansion-only methods.
CLMSM: A Multi-Task Learning Framework for Pre-training on Procedural Text (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to solve procedural reasoning tasks are limited by the prior art.
Approach: They propose a domain-specific, continual pre-training framework that learns from a large set of procedural recipes.
Outcome: The proposed framework outperforms baselines on recipes (in-domain) but is able to generalize to open-domain procedural NLP tasks.
Parameter-Efficient Instruction Tuning of Large Language Models For Extreme Financial Numeral Labelling (2024.naacl-long)

Copied to clipboard

Challenge: Existing methods to automatically annotate relevant numerals (GAAP metrics) occurring in financial documents are not cost-effective nor scalable.
Approach: They propose a generative paradigm for annotating GAAP metrics with XBRL tags using metric metadata and a parameter efficient model using LoRA.
Outcome: The proposed model outperforms baseline models on two financial numeric labeling datasets and outperformed several strong baseline models.
TIGQA: An Expert-Annotated Question-Answering Dataset in Tigrinya (2024.lrec-main)

Copied to clipboard

Challenge: Existing annotated datasets for NLP tasks in languages with limited resources are limited.
Approach: They propose to use machine translation to convert existing Tigrinya dataset into a Tigrina dataset in SQuAD format.
Outcome: The proposed dataset is an expert-annotated Tigrinya dataset with 2,685 question-answer pairs covering 122 diverse topics.
Financial Numeric Extreme Labelling: A dataset and benchmarking (2023.findings-acl)

Copied to clipboard

Challenge: In 2019, the SEC mandates that all public companies file periodic financial statements that should contain numerals annotated with a particular label.
Approach: They propose to use a dataset to automate the assignment of a label to a particular numeral span in a sentence from an extremely large label set.
Outcome: The proposed solution outperforms the previous approaches but is less frequent than the pipeline solution.
Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs (2024.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) exhibit impressive zero/few-shot inference and generation quality for high-resource languages (HRLs).
Approach: They propose to reduce the cost of processing LRLs by code-mixing, translation, and transliteration of LRL to HRLs to ensure that predictive and generative qualities are not compromised.
Outcome: The proposed model reduces the cost of processing LRLs while ensuring that predictive and generative qualities are not compromised.
How Robust Are the QA Models for Hybrid Scientific Tabular Data? A Study Using Customized Dataset (2024.lrec-main)

Copied to clipboard

Challenge: Existing tabular QA models are lacking in understanding their robustness on scientific information.
Approach: They propose a dataset to assess the robustness of tabular QA models on scientific hybrid tabular data.
Outcome: The proposed model performs well on scientific tables and text, while the best score is 0.462.
A Framework to Generate High-Quality Datapoints for Multiple Novel Intent Detection (2022.findings-naacl)

Copied to clipboard

Challenge: Existing approaches to detect novel intents have been tested in the last decade.
Approach: They propose a framework to detect multiple novel intents with budgeted human annotation cost.
Outcome: The proposed framework outperforms baseline methods in terms of accuracy and F1-score on a set of benchmark datasets.
Adaptive BPE Tokenization for Enhanced Vocabulary Adaptation in Finetuning Pretrained Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Current vocabulary adaptation approaches append the target domainspecific vocabulary (V DOMAIN) at the end of the PLM vocabulary.
Approach: They propose a vocabulary adaptation scheme that appends a target domain-specific vocabulary (V DOMAIN) at the end of the PLM vocabulary.
Outcome: The proposed approach improves by 3.57% (in terms of accuracy) and 1.87% (royal-L) over various classification and summarization tasks.
Order-Based Pre-training Strategies for Procedural Text Understanding (2024.naacl-short)

Copied to clipboard

Challenge: Procedural text is difficult to understand due to the changing attributes of entities in the context.
Approach: They propose sequence-based pre-training methods to enhance procedural understanding in natural language processing by using ordered instructions to guide individuals through a task.
Outcome: The proposed methods improve on two datasets in the datasets NPN-Cooking and ProPara domains respectively.
Entropy-guided Vocabulary Augmentation of Multilingual Language Models for Low-resource Tasks (2023.findings-acl)

Copied to clipboard

Challenge: Multilingual language models (MLLMs) support low-resource languages (LRLs) but LRL words are under-represented in wordpiece/subword vocabularies, leading to low task accuracy .
Approach: They propose an entropy-based vocabulary augmented language model to detect LRL words with undesirable wordpiece segmentations.
Outcome: The proposed model improves performance and limits on wordpiece augmentation strategies for multiple diverse LRLs.
Evaluation of LLMs in Medical Text Summarization: The Role of Vocabulary Adaptation in High OOV Settings (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have been successful in medical text summarization . however, they do not perform fine-grained evaluations under difficult settings .
Approach: They show that large language models show a significant performance drop for data points with high concentration of out-of-vocabulary words or with high novelty.
Outcome: The proposed model shows a significant performance drop for data points with high concentration of out-of-vocabulary words or with high novelty.
Label-semantics Aware Generative Approach for Domain-Agnostic Multilabel Classification (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches to multi-label text classification are limited by textual data.
Approach: They propose a domain-agnostic generative model framework for multi-label text classification that generates predefined label descriptions and matches them to predefined labels.
Outcome: The proposed model achieves 13.94% and 24.85% performance over all datasets.
Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language Models (2025.naacl-long)

Copied to clipboard

Challenge: Large language models (LLMs) are recognized for their exceptional generative capabilities and versatility across various tasks.
Approach: They conduct a comprehensive benchmarking of LLM inference energy across a wide range of NLP tasks to determine the impact of different models, tasks, prompts, and system-related factors on inference.
Outcome: The proposed model energy benchmarks show that quantization and optimal batch sizes can significantly reduce energy usage.
Brevity is the soul of sustainability: Characterizing LLM response lengths (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) consume significant energy and carbon emissions due to their inference processes.
Approach: They first benchmark 12 decoder-only LLMs across 5 datasets and then analyze LLM responses to determine their quality.
Outcome: The proposed methods can reduce the length of responses while preserving the quality of the LLMs.
Introducing Spotlight: A Novel Approach for Generating Captivating Key Information from Documents (2025.emnlp-main)

Copied to clipboard

Challenge: Unlike highlights (fragmented key points) and traditional summaries, spotlights selectively emphasize intriguing content to foster deeper reader engagement with the source material.
Approach: They propose a novel paradigm for information extraction that selectively emphasizes intriguing content to foster deeper reader engagement with the source material.
Outcome: The proposed model improves readability and boosts engagement value of the original document.
***YesBut***: A High-Quality Annotated Multimodal Dataset for evaluating Satire Comprehension capability of Vision-Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing Vision-Language models perform poorly on satirical image detecting tasks . satire and humor are powerful tools to highlight issues, provoke thought, and encourage critical perspective .
Approach: They propose to use a dataset to evaluate satirical images and satire images to detect satiric images . they also propose to generate the reason behind the image being satiral by generating one half of the image to be satisfying .
Outcome: The proposed dataset contains 2547 images, 1084 satirical and 1463 non-satirically, with different artistic styles.
ECTSum: A New Benchmark Dataset For Bullet Point Summarization of Long Earnings Call Transcripts (2022.emnlp-main)

Copied to clipboard

Challenge: ECTSum is a dataset for bullet-point summarization of earnings calls hosted by publicly traded companies.
Approach: They propose a dataset with transcripts of earnings calls and bullet point summaries derived from Reuters articles.
Outcome: The proposed dataset compares transcripts of earnings calls hosted by publicly traded companies with experts-written bullet point summaries derived from Reuters articles .
tWT–WT: A Dataset to Assert the Role of Target Entities for Detecting Stance of Tweets (2021.naacl-main)

Copied to clipboard

Challenge: Existing stance detection datasets are complex deep neural networks, making them difficult to interpret.
Approach: They propose a new large dataset free of such biases and demonstrate its aptness on existing stance detection systems.
Outcome: The proposed model achieves human-level performance on the WT–WT dataset and more than two-third accuracy on other datasets.
On The Persona-based Summarization of Domain-Specific Documents (2024.findings-acl)

Copied to clipboard

Challenge: In an ever-expanding world of domain-specific knowledge, summarization of information is a complex task . persona-based summarizing of domain specific information by humans is deemed not preferred .
Approach: They propose a framework for efficient training of a small foundation LLM on a healthcare corpus.
Outcome: The proposed framework fine-tunes a domain-specific small foundation LLM using a healthcare corpus and evaluates its quality using AI-based critiquing.
AttentiveChecker: A Bi-Directional Attention Flow Mechanism for Fact Verification (N19-1)

Copied to clipboard

Challenge: Existing fact-checking datasets do not provide manual annotations for sentence-level evidence.
Approach: They propose a task-agnostic pipelined system that extracts textual evidence that supports or refutes a factual claim from Wikipedia pages.
Outcome: The proposed system achieves state-of-the-art results on the FEVER dataset.
Improved Sentiment Detection via Label Transfer from Monolingual to Synthetic Code-Switched Text (P19-1)

Copied to clipboard

Challenge: Existing sentiment detection methods are trained on sentiment-labeled monolingual text.
Approach: They propose a method for synthesizing labeled code-switched text from monolingual text.
Outcome: The proposed method improves sentiment labeling accuracy for three languages.
Benchmarking the Energy Savings with Speculative Decoding Strategies (2026.findings-eacl)

Copied to clipboard

Challenge: Existing studies on speculative decoding have focused on the energy requirements of these models, despite their utility and utility.
Approach: They propose to analyze the energy requirements of speculative decoding strategies and analyze how various factors influence the energy optimizations.
Outcome: The proposed approach reduces decoding time while offloading a substantial portion of the sequential generation to a smaller, more efficient model.
Incorporating Domain Knowledge into Medical NLI using Knowledge Graphs (D19-1)

Copied to clipboard

Challenge: Recent studies have shown that structured domain knowledge can be used for textual inference tasks in the medical domain.
Approach: They propose to integrate structured domain knowledge into a knowledge graph for the Medical NLI task.
Outcome: The proposed approach improves the baseline BioELMo architecture for the Medical NLI task.
MutantPrompt: Prompt Optimization via Mutation Under a Budget on Modest-sized LMs (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have revolutionized the way we learn and process information, but identifying optimal prompts remains a challenge for low-resource languages.
Approach: They propose a framework that leverages multi-armed bandit algorithms to efficiently identify optimal prompts tailored to low-resource languages.
Outcome: The proposed framework is able to find optimal prompts for low-resource languages and significantly improves performance across multiple low-level tasks.
Program of Thoughts for Financial Reasoning: Leveraging Dynamic In-Context Examples and Generative Retrieval (2025.emnlp-main)

Copied to clipboard

Challenge: Numerical reasoning remains a challenging area for large language models (LLMs).
Approach: They propose a two-step framework to enhance LLM's capabilities in financial numerical reasoning by using a generative retriever and context-aware program of thought prompting.
Outcome: The proposed model surpasses previous benchmarks with execution accuracy improvements of 5.98% and 4.05%, respectively.
Efficient Continual Pre-training of LLMs for Low-resource Languages (2025.naacl-industry)

Copied to clipboard

Challenge: Open-source large language models (LLMs) are a promising tool for low-resource languages . however, there is still a substantial performance gap between high-resourced languages and LRLs .
Approach: They develop an algorithm to select a subset of texts from a larger corpus and use it to select tokens for LLMs.
Outcome: The proposed algorithm reduces the cost of continual pre-training (CPT) with large amounts of language-specific data.

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