Papers by Vaibhav Vaibhav
ARISE: Iterative Rule Induction and Synthetic Data Generation for Text Classification (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing frameworks for large language models (LLMs) generate high-quality synthetic data that can be used to supplement training data or surpass crowd-sourced annotations. |
| Approach: | They propose a framework that iteratively induces rules and generates synthetic data for text classification. |
| Outcome: | The proposed framework outperforms existing models on in-context learning and fine-tuning settings by using augmented data. |
Democratizing LLMs: An Exploration of Cost-Performance Trade-offs in Self-Refined Open-Source Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have been experiencing seismic growth in size and capabilities, radically transforming the field of NLP. |
| Approach: | They propose a generalized variant of iterative self-critique and self-refinement devoid of external influence and a ranking metric to find the optimal model for a given task considering refined performance and cost. |
| Outcome: | The proposed model improves 8.2% from baseline and even with extremely small memory footprints, outperforms ChatGPT post-refinement. |
Do Sentence Interactions Matter? Leveraging Sentence Level Representations for Fake News Classification (D19-53)
Copied to clipboard
| Challenge: | Existing methods to distinguish between trusted and fake news articles lack feature engineering . et al. (2009) define fake news as the one which deliberately exposes real-world individuals, organisations and events to ridicule. |
| Approach: | They propose a graph neural network-based model which captures sentence interactions within a document. |
| Outcome: | The proposed model beats baselines and achieves state-of-the-art accuracy on existing datasets. |
Colorism in Multimodal AI: An Empirical Exploration of Socioeconomic Linguistic Bias in Text-to-Image Generation (2026.eacl-srw)
Copied to clipboard
| Challenge: | Socioeconomic inequalities worldwide are deeply linked to ethnoracial hierarchies and stereotypes, argues a new study. |
| Approach: | They use a Monk Skin Tone scale to benchmark VLMs and annotators . they then use linguistic cues to vary skin-tone representations in text-to-image generation . |
| Outcome: | The study compares 3 small VLMs and 60 human annotators on the monk skin tone scale with 210 occupations and produces over 2,500 portraits across 3 large VLM models. |
Extractive Summarization with SWAP-NET: Sentences and Words from Alternating Pointer Networks (P18-1)
Copied to clipboard
| Challenge: | Abstractive summarization methods use factual and grammatical errors to generate summaries. |
| Approach: | They propose a neural sequence-to-sequence model for extractive summarization called SWAP-NET . it identifies salient sentences and key words in an input document and combines them to form an extractive summary. |
| Outcome: | The proposed model outperforms state-of-the-art extractive summarization methods on large scale corpora. |
Don’t Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination (2026.acl-industry)
Copied to clipboard
Prafulla Kumar Choubey, Kung-Hsiang Huang, Pranav Narayanan Venkit, Jiaxin Zhang, Vaibhav Vats, Yu Li, Xiangyu Peng, Chien-Sheng Wu
| Challenge: | Enterprise deep research systems fail to produce decision-ready reports due to uneven information coverage, context explosion, and premature stopping. |
| Approach: | They propose a scalable Enterprise Deep Research (EDR) architecture that decomposes requests into coverage-driven objectives via outline generation with reflection and localizes context with dependency-guided execution and explicit information sharing. |
| Outcome: | The proposed system achieves the strongest overall performance compared with competitive deep-research baselines on internal sales enablement tasks and the public DeepResearch Bench benchmark. |
Intent Detection and Discovery from User Logs via Deep Semi-Supervised Contrastive Clustering (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing approaches to intent detection rely on epoch wise clustering and classification based on labeled and unlabeled data. |
| Approach: | They propose an end-to-end deep contrastive clustering algorithm that jointly updates model parameters and cluster centers via supervised and self-supervised learning. |
| Outcome: | The proposed approach outperforms baselines on five public datasets and human-in-the-loop variant for practical deployment. |
Prompt Augmented Generative Replay via Supervised Contrastive Learning for Lifelong Intent Detection (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to identify all possible user intents at design time are expensive and require storage of past data. |
| Approach: | They propose to continually train an intent detector on new intents while maintaining performance on prior intents. |
| Outcome: | The proposed method outperforms exemplar replay-based approaches on lifelong intent detection tasks and achieves state-of-the-art on four public datasets. |
De-Mixing Sentiment from Code-Mixed Text (P19-2)
Copied to clipboard
| Challenge: | Code-mixing is the phenomenon of mixing the vocabulary and syntax of multiple languages in the same sentence. |
| Approach: | They propose a hybrid architecture for the task of Sentiment Analysis of English-Hindi code-mixed data using CNNs to generate subword representations for the sentences. |
| Outcome: | The proposed architecture achieves 83.54% accuracy and 0.827 F1 score on a benchmark dataset. |
Unsupervised Human Preference Learning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for in-context learning and parameter-efficient fine-tuning fail to capture the complexity of human preferences, especially given the small, personal datasets individuals possess. |
| Approach: | They propose a method that uses small parameter models as preference agents to generate natural language rules that guide a larger, pre-trained model, enabling efficient personalization. |
| Outcome: | The proposed method outperforms baseline personalization methods on email and article datasets and significantly outperformed existing methods. |
Pixie: Preference in Implicit and Explicit Comparisons (2022.acl-short)
Copied to clipboard
| Challenge: | Existing studies on preference classification focus on explicit comparisons, but recent work has focused on indirect comparisons which lack comparative quantifiers and adjectives. |
| Approach: | They propose a manual annotated dataset for preference classification that includes 8,890 app reviews. |
| Outcome: | The proposed model outperforms the state-of-the-art model and achieves a weighted average F1 score of 83.34%. |
Think Like You Execute: Verifiable Chain of Thought from Program Traces (2026.acl-industry)
Copied to clipboard
Shailja Thakur, Vaibhav Saxena, Rohan Kulkarni, Shivdeep Singh, Parameswaran Selvam, Hiroshi Kanayama, Hima Patel
| Challenge: | Current synthetic Chain-of-Thought (CoT) training data often consists of plausible-sounding explanations generated by teacher models, not verifiable accounts of actual program behavior. |
| Approach: | They propose to ground CoT generation directly in program execution traces to improve reasoning capabilities. |
| Outcome: | The proposed pipeline improves performance on live code benchmarks and on cruxEval-output and cruxeval-input. |
Improving Tool Retrieval by Leveraging Large Language Models for Query Generation (2025.coling-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown great promise in common sense language understanding, conversational fluency, and reasoning. |
| Approach: | They propose to use Large Language Models to generate a retrieval query and embed it into the prompt to find relevant tools via a nearest-neighbor search. |
| Outcome: | The proposed method improves retrieval for in-domain (seen tools) and out-of-domain settings. |
DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to developing LLM-powered coding agents struggle with sub-optimal decision-making. |
| Approach: | They propose a novel inference time compute scaling approach that recovers from sub-optimal decisions by branching out a trajectory at certain key decision points by taking an alternative action given the history of the trajectory and execution feedback of the previous attempt. |
| Outcome: | The proposed approach achieves a pass@1 rate of 47% on the SWE-Bench Lite benchmark, outperforming state-of-the-art (SOTA) open-source frameworks. |
Towards Robust Knowledge Representations in Multilingual LLMs for Equivalence and Inheritance based Consistent Reasoning (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models have led to impressive linguistic capabilities and emergent reasoning behaviors. |
| Approach: | They propose to use "equivalence" and "inheritance" to evaluate LLMs' representations . they propose to combine "equal" and 'inheritory' to improve consistency across languages . |
| Outcome: | The proposed representations show that they produce conflicting answers across languages . the proposed representation improves performance across languages and improves learning and knowledge sharing. |
Making Information Seeking Easier: An Improved Pipeline for Conversational Search (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing tools for conversational information seeking (CIS) do not support conversational contexts. |
| Approach: | They propose a highly effective pipeline for passage retrieval in a conversational search setting using a BERT-based classifier and a multi-view reranking component. |
| Outcome: | The proposed pipeline achieves 14.8% performance improvement over the current state-of-the-art pipeline and surpasses the Oracle. |
ClarQ: A large-scale and diverse dataset for Clarification Question Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing datasets hinder development of large-scale models capable of generating and utilising clarification questions. |
| Approach: | They propose a bootstrapping framework that utilises a neural network architecture to classify clarification questions based on post-comment tuples extracted from stackexchange. |
| Outcome: | The proposed framework aims to increase the accuracy of the classifier and increase recall of clarification questions by applying it to question-answering tasks. |
Leveraging the Cross-Domain & Cross-Linguistic Corpus for Low Resource NMT: A Case Study On Bhili-Hindi-English Parallel Corpus (2025.findings-emnlp)
Copied to clipboard
| Challenge: | linguistic diversity of India poses significant machine translation challenges, authors say . underrepresented tribal languages like Bhili lack high-quality linguistic resources . |
| Approach: | They introduce a Bhili-Hindi-English Parallel Corpus, the first and largest parallel corpus worldwide . they evaluated a wide range of proprietary and open-source MLLMs on bidirectional translation tasks . |
| Outcome: | The proposed corpus spans critical domains such as education, administration, and news. |
Controlled Text Generation with Hidden Representation Transformations (2023.findings-acl)
Copied to clipboard
| Challenge: | Using a con-trolled language model, we gain attribute control by modifying the hidden representation of thebase model through learning transformations. |
| Approach: | They propose a con-trolled language generation framework that gains attribute control bymodifying the hidden representation of thebase model through learned transformations. |
| Outcome: | The proposed framework outperforms all thebaselines in detoxification, positivesentiment steering, and text simplification while minimizing the loss in linguistic qualities. |
When Meaning Travels: A Granular Lens on Hybrid-MoE’s Role in Idiomatic Understanding for Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | idioms provide a fascinating gateway to creativity, cultural values, historical context, and diverse perspectives inherent to diverse linguistic traditions. |
| Approach: | They propose a multimodal idiom corpus enriched with seven idiomatic tones . they propose idiomic hybridization framework that embeds multiple idiomatic expert opinions . |
| Outcome: | The proposed framework achieves 5–6% performance gains across advanced vision language models. |
Index-Time Prefix Injection for Multi-Tenant Retrieval: Improving Search Relevance Without Model Fine-Tuning (2026.acl-industry)
Copied to clipboard
| Challenge: | a single multilingual biencoder handles all retrieval, but these are task-generic and domain-agnostic. |
| Approach: | They propose a training-free method that prepending domain-descriptive prefixes to documents during indexing. |
| Outcome: | The proposed method improves retrieval relevance by prepending natural-language prefixes to documents during indexing. |
Understanding the Influence of Synthetic Data for Text Embedders (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in general purpose text embedders have been driven by training on synthetic training data. |
| Approach: | They propose to use GPT-4 to produce high quality synthetic data that expands existing training datasets for embeddings to new tasks. |
| Outcome: | The proposed dataset is high quality and leads to consistent improvements in performance. |
TopiOCQA: Open-domain Conversational Question Answering with Topic Switching (2022.tacl-1)
Copied to clipboard
| Challenge: | Current datasets for conversational question answering do not contain topic switches . people often engage in information-seeking conversations to discover new knowledge . |
| Approach: | They propose an open-domain conversational dataset with topic switches based on Wikipedia. |
| Outcome: | The proposed dataset achieves an F1 of 55.8, falling short of human performance by 14.2 points, indicating the difficulty of the dataset. |
X-Eval: Generalizable Multi-aspect Text Evaluation via Augmented Instruction Tuning with Auxiliary Evaluation Aspects (2024.naacl-long)
Copied to clipboard
| Challenge: | X-Eval is a two-stage instruction tuning framework to evaluate text in both seen and unseen aspects customized by end users. |
| Approach: | They introduce a two-stage instruction tuning framework to evaluate text in both seen and unseen aspects customized by end users. |
| Outcome: | The proposed framework improves the model’s ability to follow evaluation instructions and enhances the learning stage to better assess text quality. |
Bridging the Language Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs (2025.coling-main)
Copied to clipboard
Somnath Kumar, Vaibhav Balloli, Mercy Ranjit, Kabir Ahuja, Sunayana Sitaram, Kalika Bali, Tanuja Ganu, Akshay Nambi
| Challenge: | Large language models (LLMs) excel in diverse applications but still struggle with non-Latin scripts and low-resource languages. |
| Approach: | They propose a dynamic learning approach that optimizes prompt strategy, embedding model, and LLM per query at runtime. |
| Outcome: | The proposed approach achieves 10-15% improvements in multilingual performance over pre-trained models and 4x gains compared to fine-tuned, language-specific models. |
Planning and Editing What You Retrieve for Enhanced Tool Learning (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for integrating external tools with Large Language Models fall short on effectively shortlisting relevant tools. |
| Approach: | They propose a plan-and-retrieve and edit-and ground paradigms for LLMs that decompose complex queries into actionable tasks. |
| Outcome: | The proposed paradigms significantly improve recall and NDCG in tool retrieval tasks, surpassing current state-of-the-art models. |
CheckersGPT: Learning World Models through Language Modeling (2024.acl-srw)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown impressive performance on various tasks, but the underlying process behind predicting the desired next token remains a black box. |
| Approach: | They train a GPT-style autoregressive language model using only the next character prediction objective and then train corresponding model with different layer sizes. |
| Outcome: | The proposed model shows a hint of learning a world model representation of the board positions on a simulated game of checkers and human gameplay dataset. |
PoseStitch-SLT: Linguistically Inspired Pose-Stitching for End-to-End Sign Language Translation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Sign language translation remains a challenging task due to the scarcity of large-scale, sentence-aligned datasets. |
| Approach: | They propose a pose-based pre-training scheme that is inspired by a linguistic-templates-based sentence generation technique. |
| Outcome: | The proposed pre-training scheme outperforms state-of-the-art methods for pose-based gloss-free translation on two sign language datasets. |
Empowering the Fact-checkers! Automatic Identification of Claim Spans on Twitter (2022.emnlp-main)
Copied to clipboard
| Challenge: | Current vogue is to employ manual fact-checkers to efficiently classify and verify such data to combat this avalanche of misinformation and fake news. |
| Approach: | They propose a large-scale Twitter corpus with token-level claim spans on more than 7.5k tweets and a model that automatically detects and extracts the snippets of misinformation. |
| Outcome: | The proposed model outperforms baseline systems on several evaluation metrics, improving by 1.5 points. |
Nurse is Closer to Woman than Surgeon? Mitigating Gender-Biased Proximities in Word Embeddings (2020.tacl-1)
Copied to clipboard
| Challenge: | Existing methods for debiasing word embeddings lack gender-based debiases . Existing approaches only reduce gender-related proximity biases by at least 42.02% . |
| Approach: | They propose a gender debiasing methodology that eliminates bias in word vectors and alters spatial distribution of neighboring vectors, achieving a bias-free setting while maintaining minimal semantic offset. |
| Outcome: | The proposed method outperforms the state-of-the-art in reducing proximity bias by at least 42.02% and reduces direct bias, adding minimal semantic disturbance, and achieves the best performance in a downstream application task. |
Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining (2022.findings-emnlp)
Copied to clipboard
| Challenge: | To explain NLP models, importance measures are often used to inform input tokens are important for making a prediction. |
| Approach: | They propose a faithfulness metric that masks allegedly important tokens and retrains the model. |
| Outcome: | The proposed metric is based on LSTM-attention models and RoBERTa models. |
Embarrassingly Simple Performance Prediction for Abductive Natural Language Inference (2022.naacl-main)
Copied to clipboard
| Challenge: | a method for learning an NLI model is time-consuming and resource-intensive, but it can save time and resources. |
| Approach: | They propose a method for predicting model performance without fine-tuning it . they compare sentence embeddings with cosine similarity to classifiers . |
| Outcome: | The proposed method can save time and resources by comparing pre-trained models to real-world datasets. |
OpenIE6: Iterative Grid Labeling and Coordination Analysis for Open Information Extraction (2020.emnlp-main)
Copied to clipboard
| Challenge: | OpenIE generates extractions iteratively, requiring repeated encoding of partial outputs. |
| Approach: | They propose an iterative open information extraction system that generates extractions iterativly, requiring repeated encoding of partial outputs. |
| Outcome: | The proposed system beats the previous systems by as much as 4 pts in F1 while being much faster. |
FIND: Toward Multimodal Financial Reasoning and Question Answering for Indic Languages (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks for numerical reasoning in multilingual Indic languages are inadequate . e.g., FinVQA is a framework for evaluating financial numerical reasoning . |
| Approach: | They propose a framework that combines supervised fine-tuning with constraint-aware decoding to promote faithful numerical reasoning. |
| Outcome: | The proposed framework spans English, Hindi, Bengali, Marathi, Gujarati, and Tamil . it combines supervised fine-tuning with constraint-aware decoding to promote faithful numerical reasoning . |
RELIC: Enhancing Reward Model Generalization for Low-Resource Indic Languages with Few-Shot Examples (2025.findings-emnlp)
Copied to clipboard
Soumya Suvra Ghosal, Vaibhav Singh, Akash Ghosh, Soumyabrata Pal, Subhadip Baidya, Sriparna Saha, Dinesh Manocha
| Challenge: | a new reward model for low-resource Indic languages is proposed . a preference-based training approach is prohibitively expensive, authors say . |
| Approach: | a new in-context learning framework is proposed to train a retriever to select in-constext examples from low-resource Indic languages. |
| Outcome: | a new in-context learning framework for reward modeling in low-resource Indic languages is developed . the proposed framework outperforms existing examples on three preference datasets . |
Image Retrieval from Contextual Descriptions (2022.acl-long)
Copied to clipboard
| Challenge: | a new multimodal challenge challenges vision-and-language models to integrate context into their representations. |
| Approach: | They propose a multimodal challenge to integrate context into vision-and-language models . they benchmark several state-of-the-art models using cross-encoders and bi-encodings . |
| Outcome: | The proposed model lags behind human models on imageCoDe, compared with human models. |
Improving Robustness of Machine Translation with Synthetic Noise (N19-1)
Copied to clipboard
| Challenge: | Recent work on MT robustness has demonstrated the need to build or adapt systems that are resilient to such noise. |
| Approach: | They propose to synthesize natural noise in social media data to enhance robustness of MT systems by leveraging natural noise. |
| Outcome: | The proposed method can make a vanilla MT system more resilient to noise, partially mitigating loss in accuracy resulting therefrom. |
LADDER: Language-Driven Slice Discovery and Error Rectification in Vision Classifiers (2025.findings-acl)
Copied to clipboard
Shantanu Ghosh, Rayan Syed, Chenyu Wang, Vaibhav Choudhary, Binxu Li, Clare B Poynton, Shyam Visweswaran, Kayhan Batmanghelich
| Challenge: | Current slice discovery methods in computer vision rely on converting input images into sets of attributes and testing hypotheses about configurations of pre-computed attributes associated with elevated error patterns. |
| Approach: | They propose a method to identify systematic biases in the mistakes of pre-trained vision models by converting input images into sets of attributes and testing hypotheses about configurations of these attributes. |
| Outcome: | The proposed method outperforms existing methods on 3 natural and 3 medical imaging datasets and generates pseudo-labels for each identified bias. |