Papers by Purav Aggarwal

8 papers
SMART: Scalable Multilingual Approach for a Robust TOD System (2025.emnlp-industry)

Copied to clipboard

Challenge: Existing TOD frameworks face significant challenges in handling unstructured information, providing multilingual support, and engaging proactively.
Approach: They propose a novel TOD framework that combines traditional pipeline elements with modern agent-based approaches and features a simplified dialogue state, intelligent clarification mechanisms, and a unified natural language generation component that eliminates response redundancy.
Outcome: The proposed framework outperforms baseline systems across key metrics and integrates in an e-commerce store.
AutoEval-ToD: Automated Evaluation of Task-oriented Dialog Systems (2025.naacl-long)

Copied to clipboard

Challenge: Current evaluation methodologies heavily depend on human annotators, which can be inefficient, subjective, and expensive to scale.
Approach: They propose an automated end-to-end evaluation framework that interacts with the ToD system and then assesses its performance across key dimensions.
Outcome: The proposed framework first interacts with the ToD system and assesses its performance across key dimensions by analyzing both its responses and internal states.
ASK: Aspects and Retrieval based Hybrid Clarification in Task Oriented Dialogue Systems (2025.acl-industry)

Copied to clipboard

Challenge: Ambiguous user queries pose a challenge in task-oriented dialogue systems . Large Language Models (LLMs) rely on the top-k retrieved documents for clarification . traditional approaches lack principled mechanisms to determine when to use broad domain knowledge vs specific retrieved document context for clarification.
Approach: They propose a hybrid approach that dynamically chooses between document-based or aspect-based clarification based on query ambiguity.
Outcome: The proposed approach shows significant improvements over baselines on product troubleshooting and product search datasets.
VADE: Visual Attention Guided Hallucination Detection and Elimination (2025.findings-acl)

Copied to clipboard

Challenge: Vision Language Models (VLMs) are prone to hallucinations, generating outputs that lack grounding in the actual visual data.
Approach: They propose a sequence modelling approach to learn complex sequential patterns from transformer attention maps.
Outcome: The proposed approach achieves an average PR-AUC of 80% in hallucination detection on M-HalDetect and an 5% improvement in hallucinosis mitigation on MSCOCO.
AutoChunker: Structured Text Chunking and its Evaluation (2025.acl-industry)

Copied to clipboard

Challenge: Existing methods for text chunking struggle with document structure and noise . Existing approaches struggle with maintaining semantic coherence while handling complex documents.
Approach: They propose a bottom-up approach to chunking that combines document structure awareness with noise elimination.
Outcome: The proposed method outperforms existing methods in noise reduction, completeness, context coherence, task relevance, and retrieval performance.
AutoKB: Automated Creation of Structured Knowledge Bases for Domain-Specific Support (2025.naacl-industry)

Copied to clipboard

Challenge: Effective customer support requires domain-specific solutions tailored to users’ issues.
Approach: They propose an automated pipeline for building a domain-specific KB with a hierarchical tree structure that maps user issues to precise and domain-compliant solutions.
Outcome: Experiments in troubleshooting and medical domains show that the proposed pipeline outperforms LLMs and unstructured knowledge bases and is 75 times more cost-effective than manual methods.
MTIVE: Multi-Task Image Verification Engine Using Vision-Language Models for E-commerce (2026.acl-industry)

Copied to clipboard

Challenge: Vision-language models struggle with noisy real-world images and multi-task requirements.
Approach: They propose a curriculum learning framework that adapts vision-language models through three stages . MTIVE uses frozen base weights with stacked LoRA adapters for shared domain knowledge .
Outcome: MTIVE outperforms open-source and proprietary baselines in standard and continual learning settings.
VIT-Pro: Visual Instruction Tuning for Product Images (2025.naacl-industry)

Copied to clipboard

Challenge: general-purpose vision-language models struggle to understand and converse about real-world e-commerce product images.
Approach: a new approach is proposed to use large-scale image-text pairs to train a generative VLM for e-commerce product images.
Outcome: The proposed model outperforms general-purpose VLMs on multiple vision tasks in the e-commerce domain.

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