Papers by Shrikanth Narayanan

Aggregation Artifacts in Subjective Tasks Collapse Large Language Models’ Posteriors (2025.naacl-long)

Copied to clipboard

Georgios Chochlakis, Alexandros Potamianos, Kristina Lerman, Shrikanth Narayanan

Challenge:	In-context Learning (ICL) is the primary method for performing natural language tasks with Large Language Models.
Approach:	They examine whether aggregation is a confounding factor in the modeling of subjective tasks . they find it is possible for minority annotators to better align with LLMs .
Outcome:	The proposed method is based on aggregation of annotations in a dataset with appropriate priors.

Towards end-2-end learning for predicting behavior codes from spoken utterances in psychotherapy conversations (2020.acl-main)

Copied to clipboard

Karan Singla, Zhuohao Chen, David Atkins, Shrikanth Narayanan

Multimodality

Challenge:	Xu and Sarikaya, 2014) proposes a framework for predicting utterance level labels directly from speech features.
Approach:	They propose a framework for predicting utterance level labels directly from speech features using a pretrained Speech-2-Vector encoder as bottleneck.
Outcome:	The proposed model outperforms state-of-the-art approaches which use transcribed text for the task of predicting psychotherapy-relevant behavior codes.

Humans Hallucinate Too: Language Models Identify and Correct Subjective Annotation Errors With Label-in-a-Haystack Prompts (2025.emnlp-main)

Copied to clipboard

Georgios Chochlakis, Peter Wu, Tikka Arjun Singh Bedi, Marcus Ma, Kristina Lerman, Shrikanth Narayanan

Semantic Text Processing

Challenge:	Existing approaches to model complex subjective tasks in natural language are limited by significant variation in annotations.
Approach:	They propose a simple in-context learning binary filtering baseline that estimates the reasonableness of a document-label pair.
Outcome:	The proposed approach can be integrated into annotation pipelines to enhance signal-to-noise ratios.

The Subjectivity of Respect in Police Traffic Stops: Modeling Community Perspectives in Body-Worn Camera Footage (2026.acl-long)

Copied to clipboard

Preni Golazizian, Elnaz Rahmati, Jackson Trager, Zhivar Sourati, Nona Ghazizadeh, Georgios Chochlakis, Jose J. Alcocer, Kerby Bennett, Aarya Vijay Devnani, Parsa Hejabi, Harry G. Muttram, Akshay Kiran Padte, Mehrshad Saadatinia, Chenhao Wu, Alireza Salkhordeh Ziabari, Michael Sierra-Arévalo, Nicholas Weller, Shrikanth Narayanan, Benjamin A.t. Graham, Morteza Dehghani

Challenge:	a new study examines the perception of police-civilian traffic stops using respect ratings and free-text rationales from multiple perspectives.
Approach:	They propose a traffic-stop dataset annotated with respect ratings and rationales from multiple perspectives . they use a criterion-driven preference data construction framework to predict personalized respect ratings .
Outcome:	The proposed framework improves rating prediction performance and rationale alignment across all three annotators.

RespiraMFM: A Multimodal Foundation Model with Contrastive Audio-Language Alignment for Respiratory Disease Identification (2026.acl-long)

Copied to clipboard

Shakhrul Iman Siam, Tiantian Feng, Jiankun Zhang, Shrikanth Narayanan, Mi Zhang

Multimodality

Challenge:	Existing models for respiratory diseases rely on audio inputs, but they lack generalizability and diagnostic precision.
Approach:	They propose a multimodal foundation model that integrates respiratory sounds with medical history and symptoms to enhance diagnostic accuracy and disease detection capabilities.
Outcome:	The proposed model improves AUROC and zero-shot tasks across five respiratory diseases using real-world datasets.

Leveraging Open Data and Task Augmentation to Automated Behavioral Coding of Psychotherapy Conversations in Low-Resource Scenarios (2022.findings-emnlp)

Copied to clipboard

Zhuohao Chen, Nikolaos Flemotomos, Zac Imel, David Atkins, Shrikanth Narayanan

Responsible & Trustworthy NLP

Challenge:	Behavioral coding is a procedure that requires human intervention to be performed manually.
Approach:	They propose to use a publicly available conversation-based dataset to transfer knowledge to a low-resource behavioral coding task by meta-learning.
Outcome:	The proposed framework predicts target behaviors more accurately than baseline models.

Large Language Models Do Multi-Label Classification Differently (2025.emnlp-main)

Copied to clipboard

Marcus Ma, Georgios Chochlakis, Niyantha Maruthu Pandiyan, Jesse Thomason, Shrikanth Narayanan

Information Retrieval

Challenge:	Multi-label classification is prevalent in real-world settings, but the behavior of Large Language Models (LLMs) in this setting is understudied.
Approach:	They propose to use initial probability distributions to analyze output distributions of LLMs at each label generation step to find out how LLM models perform multi-label classification.
Outcome:	The proposed methods improve alignment and predictive performance over existing methods.

Creating a Lens of Chinese Culture: A Multimodal Dataset for Chinese Pun Rebus Art Understanding (2025.findings-acl)

Copied to clipboard

Tuo Zhang, Tiantian Feng, Yibin Ni, Mengqin Cao, Ruying Liu, Kiana Avestimehr, Katharine Butler, Yanjun Weng, Mi Zhang, Shrikanth Narayanan, Salman Avestimehr

Multimodality

Challenge:	a new study examines the performance of large vision-language models in understanding art . the Pun Rebus Art Dataset is a multimodal dataset for art understanding rooted in traditional Chinese culture .
Approach:	They propose a multimodal dataset for art understanding deeply rooted in traditional Chinese culture . they aim to facilitate the development of VLMs that can better understand culturally specific content .
Outcome:	The proposed dataset shows that state-of-the-art VLMs struggle with these tasks . the data will facilitate the development of VLM models that can better understand culturally specific content .

Domain Adaptation for Sentiment Analysis Using Robust Internal Representations (2023.findings-emnlp)

Copied to clipboard

Mohammad Rostami, Digbalay Bose, Shrikanth Narayanan, Aram Galstyan

Semantic Text Processing

Challenge:	Cross-domain sentiment analysis methods reduce the domain gap by training generalizable classifiers for each domain . large interclass margins in source domain help to reduce the effect of "domain shift" in the target domain.
Approach:	They propose a domain adaptation method which induces large margins between data representations that belong to different classes in an embedding space.
Outcome:	The proposed method reduces the domain gap by training cross-domain generalizable classifiers . large interclass margins in the source domain help reduce the effect of "domain shift" the proposed method is available in the u.s.

A Multi-task Approach to Learning Multilingual Representations (P18-2)

Copied to clipboard

Karan Singla, Dogan Can, Shrikanth Narayanan

Semantic Text Processing

Challenge:	Using a multi-task model, we learn word and sentence embeddings in a single task.
Approach:	They propose a multi-task modeling approach that trains a skip-gram model and a cross-lingual sentence similarity model to learn word and sentence embeddings together.
Outcome:	The proposed model can learn word and sentence embeddings in a multilingual distributed representations of text using a cross-lingual sentence similarity model.

Character Coreference Resolution in Movie Screenplays (2023.findings-acl)

Copied to clipboard

Sabyasachee Baruah, Shrikanth Narayanan

Robustness in NLP

Challenge:	Movie screenplays have a distinct narrative structure.
Approach:	They develop a method to extract structural information and character coreference clusters from movie screenplays by leveraging a movie parser and a character coreferser.
Outcome:	The proposed methods scale to long movie screenplays without dramatically increasing their memory footprints.

Annotation and Evaluation of Coreference Resolution in Screenplays (2021.findings-acl)

Copied to clipboard

Sabyasachee Baruah, Sandeep Nallan Chakravarthula, Shrikanth Narayanan

Information Extraction & Text Mining

Challenge:	Screenplays refer to characters using different names, pronouns, and nominal expressions.
Approach:	They develop an automatic screenplay parser to extract structural information and design coreference rules based upon the structure of screenplays.
Outcome:	The proposed model outperforms a benchmark model on the screenplay coreference resolution task.

Joint Estimation and Analysis of Risk Behavior Ratings in Movie Scripts (2020.emnlp-main)

Copied to clipboard

Victor Martinez, Krishna Somandepalli, Yalda Tehranian-Uhls, Shrikanth Narayanan

Challenge:	Existing methods to identify portrayals of risk behaviors from audio-visual cues are limited in their applicability to films in post-production, where modifications might be prohibitively expensive.
Approach:	They propose a model that estimates content ratings based on the language use in movie scripts and leverages the co-occurrence of risk behaviors following a multi-task approach.
Outcome:	The proposed model improves state-of-the-art by adapting novel techniques to learn better movie representations from the semantic and sentiment aspects of a character’s language use and by leveraging the co-occurrence of risk behaviors, following a multi-task approach.