PPaperPicks

Pushpak Bhattacharyya

Indian Institute of Technology, Bombay, India

49 papers at tracked venues · 21 at CORE A* · active 20242026

Venues

Frequent coauthors

Settaluri Lakshmi Sravanthi
×4
Kaustubh Shivshankar Shejole
×2
Sourabh Dattatray Deoghare
×2
Sameer Pimparkhede
×2
Tejpalsingh Siledar
×2

Papers

  1. CaRVE: Critiquing and Refining Visual Elaborations for Figurative Language Illustrations
  2. How effective are VLMs in assisting humans in inferring the quality of mental models from Multimodal short answers?
  3. Looking at Radiology Report Generation through a Causal Lens: A Survey
  4. Rad-Flamingo: A Multimodal Prompt driven Radiology Report Generation Framework with Patient-Centric Explanations
  5. Rethinking Research on Stereotypes: An Analysis through Social Psychological and Computational Perspectives
    ACL 2026 ·
    Kaustubh Shivshankar Shejole
  6. Savior: Sample-Efficient Adaptation of Vision-Language Models for OCR Representation
  7. SrcMix: Mixing of Related Source Languages Benefits Extremely Low-resource Machine Translation
  8. "My life is miserable, have to sign 500 autographs everyday": Exposing Humblebragging, the Brags in Disguise
  9. "You are Beautiful, Body Image Stereotypes are Ugly!" BIStereo: A Benchmark to Measure Body Image Stereotypes in Language Models
  10. Are Language Models Agnostic to Linguistically Grounded Perturbations? A Case Study of Indic Languages
  11. ConCodeEval: Evaluating Large Language Models for Code Constraints in Domain-Specific Languages
  12. Divide, Link, and Conquer: Recall-oriented Schema Linking for NL-to-SQL via Question Decomposition
  13. ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries
  14. From Perception to Reasoning: Enhancing Vision-Language Models for Mobile UI Understanding
    ACL 2025 ·
    Settaluri Lakshmi Sravanthi
  15. From Recall to Creation: Generating Follow-Up Questions Using Bloom's Taxonomy and Grice's Maxims
  16. GRAFT: A Graph-based Flow-aware Agentic Framework for Document-level Machine Translation
  17. Giving the Old a Fresh Spin: Quality Estimation-Assisted Constrained Decoding for Automatic Post-Editing
    NAACL 2025 ·
    Sourabh Dattatray Deoghare
  18. HalluDetect: Detecting, Mitigating, and Benchmarking Hallucinations in Conversational Systems in the Legal Domain
  19. Improving Text Style Transfer Using Masked Diffusion Language Models with Inference-Time Scaling
  20. IndiGEC: Multilingual Grammar Error Correction for Low-Resource Indian Languages
  21. Looking Beyond the Pixels: Evaluating Visual Metaphor Understanding in VLMs
  22. Main Predicate and Their Arguments as Explanation Signals For Intent Classification
  23. RG-VQA: Leveraging Retriever-Generator Pipelines for Knowledge Intensive Visual Question Answering
    EMNLP 2025 ·
    Settaluri Lakshmi Sravanthi
  24. ReDepress: A Cognitive Framework for Detecting Depression Relapse from Social Media
  25. Recon, Answer, Verify: Agents in Search of Truth
  26. StereoDetect: Detecting Stereotypes and Anti-stereotypes the Correct Way Using Social Psychological Underpinnings
    EMNLP 2025 ·
    Kaustubh Shivshankar Shejole
  27. Stereotype Detection as a Catalyst for Enhanced Bias Detection: A Multi-Task Learning Approach
  28. Understand the Implication: Learning to Think for Pragmatic Understanding
    ACL 2025 ·
    Settaluri Lakshmi Sravanthi
  29. Why We Feel What We Feel: Joint Detection of Emotions and Their Opinion Triggers in E-commerce
  30. A Morphology-Based Investigation of Positional Encodings
  31. Beyond Aesthetics: Cultural Competence in Text-to-Image Models
  32. DocCGen: Document-based Controlled Code Generation
  33. Emotion Arithmetic: Emotional Speech Synthesis via Weight Space Interpolation
  34. Hi Model, generating "nice" instead of "good" is not as bad as generating "rice"! Towards Context and Semantic Infused Dialogue Generation Loss Function
  35. In-context Mixing (ICM): Code-mixed Prompts for Multilingual LLMs
  36. IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Context
  37. IndicCONAN: A Multilingual Dataset for Combating Hate Speech in Indian Context
  38. IndicIRSuite: Multilingual Dataset and Neural Information Models for Indian Languages
  39. MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention
  40. Mental Disorder Classification via Temporal Representation of Text
  41. One Prompt To Rule Them All: LLMs for Opinion Summary Evaluation
  42. PUB: A Pragmatics Understanding Benchmark for Assessing LLMs' Pragmatics Capabilities
    ACL 2024 ·
    Settaluri Lakshmi Sravanthi
  43. Part-of-speech Tagging for Extremely Low-resource Indian Languages
  44. Pretraining Language Models Using Translationese
  45. Product Description and QA Assisted Self-Supervised Opinion Summarization
  46. Together We Can: Multilingual Automatic Post-Editing for Low-Resource Languages
    EMNLP 2024 ·
    Sourabh Dattatray Deoghare
  47. ToxVidLM: A Multimodal Framework for Toxicity Detection in Code-Mixed Videos
  48. Unveiling the Invisible: Captioning Videos with Metaphors
    EMNLP 2024 ·
    Abisek Rajakumar Kalarani
  49. Well, Now We Know! Unveiling Sarcasm: Initiating and Exploring Multimodal Conversations with Reasoning