activity
20172022
most citedAnalyzing Modality Robustness in Multimodal Sentiment Analysis

3 citations · 7 across the 6 of their papers we have counts for

collaborators

21 papers

cs.CL20232 cited

Data-Efficient Alignment of Large Language Models with Human Feedback Through Natural Language

Di Jin, Shikib Mehri, Devamanyu Hazarika +4

Learning from human feedback is a prominent technique to align the output of large language models (LLMs) with human expectations. Reinforcement learning from human feedback (RLHF)…

cs.CL2022

Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning

Yifan Chen, Devamanyu Hazarika, Mahdi Namazifar +3

Prefix-tuning, or more generally continuous prompt tuning, has become an essential paradigm of parameter-efficient transfer learning. Using a large pre-trained language model (PLM)…

cs.CL20223 cited

Analyzing Modality Robustness in Multimodal Sentiment Analysis

Devamanyu Hazarika, Yingting Li, Bo Cheng +3

Building robust multimodal models are crucial for achieving reliable deployment in the wild. Despite its importance, less attention has been paid to identifying and improving the r…

cs.CL20221 cited

So Different Yet So Alike! Constrained Unsupervised Text Style Transfer

Abhinav Ramesh Kashyap, Devamanyu Hazarika, Min-Yen Kan +2

Automatic transfer of text between domains has become popular in recent times. One of its aims is to preserve the semantic content of text being translated from source to target do…

cs.CL20211 cited

Exemplars-guided Empathetic Response Generation Controlled by the Elements of Human Communication

Navonil Majumder, Deepanway Ghosal, Devamanyu Hazarika +3

The majority of existing methods for empathetic response generation rely on the emotion of the context to generate empathetic responses. However, empathy is much more than generati…

cs.CL2020

Recognizing Emotion Cause in Conversations

Soujanya Poria, Navonil Majumder, Devamanyu Hazarika +9

We address the problem of recognizing emotion cause in conversations, define two novel sub-tasks of this problem, and provide a corresponding dialogue-level dataset, along with str…