SRW Program#

Program at a Glance#

• Note: Time is in India Standard Time (UTC+5:30)

Oral Session 1 (SRW-OP1-Session)#

• Time: 11:00 – 12:30
• Format: Hybrid
• Location: 2nd Floor Room 23
• Slides (opening remarks, panel discussion, and closing remarks)

SRW Opeing Remarks#

• Time: 11:00 - 11:05

Panel Discussion#

• Panel:

  Time	Topic	Panelists
  11:05 – 11:55	Navigating Research in the Era of LLMs	Fajri Koto (in-person), Raj Dabre (in-person), Sriparna Saha (virtual)

Oral Presentations#

• Time: 11:55 – 12:25

• Presentations:

  • Note: Presentation time is 10 minutes each, including Q&A.

  Time	Title	Presenter
  11:55 – 12:05	On Multilingual Encoder Language Model Compression for Low-Resource Languages	Daniil Gurgurov (in-person)
  12:05 – 12:15	Do We Need Large VLMs for Spotting Soccer Actions?	Ritabrata Chakraborty (virtual)
  12:15 – 12:25	Testing Simulation Theory in LLMs’ Theory of Mind	Koshiro Aoki (in-person)

SRW Closing Remarks#

• Time: 12:25 - 12:30

Oral Session 2 (SRW-OP2-Session)#

• Time: 14:00 – 15:30
• Format: Hybrid
• Location: 2nd Floor Room 23

Oral Presentations#

• Presentations:

  • Note: Presentation time is 15 minutes each, including Q&A.

  Time	Title	Presenter
  14:00 – 14:15	Two Step Automatic Post Editing of Patent Machine Translation based on Pre-trained Encoder Models and LLMs	Kosei Buma (in-person)
  14:15 – 14:30	To What Extent Can In-Context Learning Solve Unseen Tasks?	Ryoma Shinto (in-person)
  14:30 – 14:45	Learning Dynamics of Meta-Learning in Small Model Pretraining	David Africa (virtual)
  14:45 – 15:00	NumPert: Numerical Perturbations to Probe Language Models for Veracity Prediction	Peter Røysland Aarnes (virtual)
  15:00 – 15:15	Turn-by-Turn Behavior Monitoring in LM-Guided Psychotherapy	Anish Chedalla (virtual)
  15:15 – 15:30	WOLF: Werewolf-based Observations for LLM Deception and Falsehoods	Mrinal Agarwal (virtual)

In-person Poster Session (SRW-PP-Poster Session)#

• Time: 16:00 – 17:30
• Format: In-person
• Location: Poster Hall

Poster Presentations#

• Presentations:

  Title	Presenter
  BookAsSumQA: An Evaluation Framework for Aspect-Based Book Summarization via Question Answering	Ryuhei Miyazato
  Thesis Proposal: Interpretable Reasoning Enhancement in Large Language Models through Puzzle and Ontological Task Analysis	Mihir Panchal
  AI Through the Human Lens: Investigating Cognitive Theories in Machine Psychology	Rishika Goswami
  Thesis Proposal: A NeuroSymbolic Approach to Control Task-Oriented Dialog Systems	Anuja Tayal
  Enriching the Low-Resource Neural Machine Translation with Large Language Model	Sachin Giri
  Investigating Training and Generalization in Faithful Self-Explanations of Large Language Models	Tomoki Doi
  Thesis Proposal: Efficient Methods for Natural Language Generation/Understanding Systems	Nalin Kumar
  Rethinking Tokenization for Rich Morphology: The Dominance of Unigram over BPE and Morphological Alignment	Saketh Reddy Vemula
  Are LLMs Good for Semantic Role Labeling via Question Answering?: A Preliminary Analysis	Ritwik Raghav
  Could you BE more sarcastic? A Cognitive Approach to Bidirectional Sarcasm Understanding in Language Models	Veer Chheda
  The ‘aftermath’ of compounds: Investigating Compounds and their Semantic Representations	Swarang Joshi
  Demystifying Representation Spaces of Multilingual and Multimodal Aspects in Large Audio Language Models	Antonio Natthan Krishna

Virtual Poster Session (SRW-PV-Poster Session)#

• Time: 16:00 – 17:30
• Format: Virtual
• Location: Gather

Poster Presentations#

• Presentations:

  Title	Presenter
  Stacked LoRA: Isolated Low-Rank Adaptation for Lifelong Knowledge Management	Heramb Patil
  CORAL: A Synergistic Approach to Deception Detection with Socially-Aware Representations and Positive-Unlabeled Learning	Bhavinkumar Vinodbhai Kuwar
  Efficient Environmental Claim Detection with Hyperbolic Graph Neural Networks	Darpan Aswal
  Pruning for Performance: Efficient Idiom and Metaphor Classification in Low-Resource Konkani Using mBERT	Timothy Do, Pranav Saran
  Interpretable Sparse Features for Probing Self-Supervised Speech Models	Iñigo Parra
  Adaptive Coopetition: Leveraging Coarse Verifier Signals for Resilient Multi-Agent LLM Reasoning	Wendy Yaqiao Liu
  Visualizing and Benchmarking LLM Factual Hallucination Tendencies via Internal State Analysis and Clustering	Nathan Mao, Varun Kaushik
  The Role of Emotional Stimuli and Intensity in Shaping Large Language Model Behavior	Ameen Patel
  Mitigating Forgetting in Continual Learning with Selective Gradient Projection	Anika Singh
  VariantBench: A Framework for Evaluating LLMs on Justifications for Genetic Variant Interpretation	Humair Basharat
  LRMGS: A Language-Robust Metric for Evaluating Question Answering in Very Low-Resource Indic Languages	Anuj Kumar