Papers by Aditya Gupta
Can Sequence-to-Sequence Transformers Naturally Understand Sequential Instructions? (2023.starsem-1)
Copied to clipboard
| Challenge: | Using a limited annotation budget, we can greatly improve the performance on intermediate steps with a drop in final-step performance. |
| Approach: | They propose to use a pre-supervised sequence-to-sequence transformer to provide training signals on intermediate steps with zero gold supervision instead of only final-step supervision to improve performance. |
| Outcome: | The proposed model significantly improves on intermediate steps with a drop in final-step performance on one subtask, but also shows decreased performance on another subtask. |
Efficient Encoders for Streaming Sequence Tagging (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing bidirectional encoders require a restart when a new token is received. |
| Approach: | They propose a Hybrid Encoder with Adaptive Restart that enables asynchronous encoding of a new token in an incremental streaming input. |
| Outcome: | The proposed encoder offers FLOP savings in streaming settings up to 71.1% and outperforms bidirectional encoders for streaming predictions by up to +0% streaming exact match. |
TwiRGCN: Temporally Weighted Graph Convolution for Question Answering over Temporal Knowledge Graphs (2023.eacl-main)
Copied to clipboard
| Challenge: | Recent years have witnessed interest in Temporal Question Answering over Knowledge Graphs (TKGQA) but these methods are highly engineered and do not automatically discover relevant parts of the KG during multi-hop reasoning. |
| Approach: | They propose a scheme to modulate the messages passed through a KG edge during convolution based on the relevance of its associated period to the question. |
| Outcome: | The proposed system outperforms state-of-the-art models on a recent challenging dataset for multi-hop complex temporal QA called TimeQuestions. |
MORPHOGEN: A Multilingual Benchmark for Evaluating Gender-Aware Morphological Generation (2026.acl-long)
Copied to clipboard
| Challenge: | In morphologically rich languages, gender influences verb conjugation, pronouns, and even first-person constructions with explicit and implicit mentions of gender. |
| Approach: | They propose a morphologically grounded large-scale benchmark dataset for evaluating gender-aware generation in three typologically diverse grammatically gendered languages: French, Arabic, and Hindi. |
| Outcome: | The proposed dataset compares 15 popular multilingual large language models on their ability to handle morphological gender and morphology agreement. |
TableFormer: Robust Transformer Modeling for Table-Text Encoding (2022.acl-long)
Copied to clipboard
| Challenge: | Existing tables models require linearization of the table structure, where row or column order is encoded as an unwanted bias. |
| Approach: | They propose a robust and structurally aware table-text encoding architecture TableFormer where tabular structural biases are incorporated completely through learnable attention biase. |
| Outcome: | The proposed architecture outperforms strong baselines on SQA, WTQ and TabFact table reasoning datasets and achieves state-of-the-art performance on SQ. |
Effective Use of Transformer Networks for Entity Tracking (D19-1)
Copied to clipboard
| Challenge: | Existing pre-trained language models for entity-related tasks are not able to handle the nuances of procedural text. |
| Approach: | They propose to use pre-trained transformer networks to track entities in procedural text by restructuring input to focus on a particular entity. |
| Outcome: | The proposed models outperform baseline models on ingredient detection in recipes and QA over scientific processes on two different tasks. |
Improving Top-K Decoding for Non-Autoregressive Semantic Parsing via Intent Conditioning (2022.coling-1)
Copied to clipboard
| Challenge: | Semantic parsing (SP) is a core component of modern virtual assistants like Google Assistant and Amazon Alexa. |
| Approach: | They propose a non-autoregressive (NAR) semantic parser that introduces intent conditioning on the decoder. |
| Outcome: | The proposed model reduces inference latency while maintaining competitive parsing quality. |
Training Data Augmentation for Code-Mixed Translation (2021.naacl-main)
Copied to clipboard
| Challenge: | We show a 5.8 point increase in BLEU on heavily code-mixed sentences . code-mixing is becoming more commonplace in several bilingual communities . |
| Approach: | They propose a method to convert existing parallel data sources into code-mixed parallel data. |
| Outcome: | The proposed method shows a 5.8 point increase in BLEU on heavily code-mixed sentences on a Hindi-English code-mixed translation task. |
Multimodal Persona Based Generation of Comic Dialogs (2023.acl-long)
Copied to clipboard
| Challenge: | Existing models for persona based dialogue generation for comic strips encode two-party dialogues and do not account for visual information. |
| Approach: | They propose a multimodal persona-based architecture to generate dialogues for the next panel in comic strips. |
| Outcome: | The proposed paradigm reduces the perplexity score by 10 points over existing models . the novel dataset, ComSet, contains 54K comic strips . |
PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs (2023.emnlp-main)
Copied to clipboard
Rahul Goel, Waleed Ammar, Aditya Gupta, Siddharth Vashishtha, Motoki Sano, Faiz Surani, Max Chang, HyunJeong Choe, David Greene, Chuan He, Rattima Nitisaroj, Anna Trukhina, Shachi Paul, Pararth Shah, Rushin Shah, Zhou Yu
| Challenge: | PRESTO dataset contains 550K contextual multilingual conversations between humans and virtual assistants. |
| Approach: | They propose to use a dataset of 550K contextual multilingual conversations between humans and virtual assistants to study some of the more challenging aspects of parsing realistic conversations. |
| Outcome: | The dataset contains 550K contextual conversations between humans and virtual assistants. |
PROPER Agents: Proactivity Driven Personalized Agents for Advancing Knowledge Gap Navigation (2026.findings-acl)
Copied to clipboard
| Challenge: | Current approaches to proactive assistance are anchored in what users express or can read, leading to unnecessary or mistimed interventions. |
| Approach: | They propose a framework that explicitly models user-specific knowledge gaps in a controlled manner. |
| Outcome: | The proposed framework improves on quality scores and win rates across multiple domains, achieving up to 84% gains in single-turn evaluation and consistent dominance in multiturn interactions. |
Adapting Multilingual Models for Code-Mixed Translation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work has addressed the lack of gold standard code-mixed to pure language parallel data with data augmentation techniques. |
| Approach: | They propose a back-translation-based training scheme for code-mixed translation which eliminates dependence on external resources. |
| Outcome: | The proposed model beats previous work by up to +3.8 BLEU on code-mixed tasks. |
XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants (2026.acl-long)
Copied to clipboard
| Challenge: | Cross-Origin Context Poisoning (XOXO) exploits this automatic context inclusion by subtly manipulating code without changing its semantics. |
| Approach: | They propose a novel attack that exploits automatic context inclusion by subtly manipulating code without changing its semantics. |
| Outcome: | The proposed attack achieves 73.20% success rates against eight state-of-the-art models including GPT 4.1 and Claude 3.5 Sonnet v2 and vulnerability injection rates up to 66.67%. |
TIMEDIAL: Temporal Commonsense Reasoning in Dialog (2021.acl-long)
Copied to clipboard
| Challenge: | Existing studies on pre-trained language models for dialog reasoning fail to understand context correctly. |
| Approach: | They propose to use a crowd-sourced English task and a time-based task to test models' temporal reasoning abilities in dialogs. |
| Outcome: | The proposed task and crowd-sourced English challenge set show that even the best performing models struggle on this task compared to humans. |
ERVQA: A Dataset to Benchmark the Readiness of Large Vision Language Models in Hospital Environments (2024.emnlp-main)
Copied to clipboard
| Challenge: | a global shortage of healthcare workers has demanded the development of smart healthcare assistants. |
| Approach: | They analyze the healthcare knowledge of existing Large Vision Language Models (LVLMs) using an annotated open-ended task. |
| Outcome: | The study analyzes the knowledge of large vision language models using open-ended questions . the results highlight the need for specialized, domain-specific solutions . |
Disfl-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answering (2021.findings-acl)
Copied to clipboard
| Challenge: | Disfluencies are an under-studied topic in NLP, even though it is ubiquitous in human conversation. |
| Approach: | They propose a challenge question answering dataset where humans introduce contextual disfluencies in previously fluent questions. |
| Outcome: | The proposed dataset shows that existing models degrade significantly when tested on DISFL-QA in a zero-shot setting. |
How to Fine-Tune Safely on a Budget: Model Adaptation Using Minimal Resources (2025.emnlp-industry)
Copied to clipboard
Anh C. Pham, Mihir Thalanki, Michael Sun, Aditya Chaloo, Ankita Gupta, Tian Xia, Aditya Mate, Ehi Nosakhare, Soundararajan Srinivasan
| Challenge: | Existing methods for fine-tuning safety examples are underdeveloped. |
| Approach: | They hypothesize that the effectiveness of a safety example is governed by its instruction-response behavior and its semantic diversity across harm categories. |
| Outcome: | The proposed method reduces harmfulness by up to 41% while adding only 0.05% more data to the fine-tuning set. |