1.2k citations · 1.7k across the 29 of their papers we have counts for
36 papers
Discretizing Reward Models
Vijay Viswanathan, Shiqi Wang, Devamanyu Hazarika +4
Despite their widespread use, the role of reward models in shaping reinforcement learning is poorly understood. Reward models offer a tempting promise: they automatically estimate…
The Llama 4 Herd: Architecture, Training, Evaluation, and Deployment Notes
Redacted by arXiv
This document consolidates publicly reported technical details about Metas Llama 4 model family. It summarizes (i) released variants (Scout and Maverick) and the broader herd conte…
The Amazon Nova Family of Models: Technical Report and Model Card
Amazon AGI, Aaron Langford, Aayush Shah +783
We present Amazon Nova, a new generation of state-of-the-art foundation models that deliver frontier intelligence and industry-leading price performance. Amazon Nova Pro is a highl…
Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs
Siyan Zhao, Mingyi Hong, Yang Liu +2
Large Language Models (LLMs) are increasingly used as chatbots, yet their ability to personalize responses to user preferences remains limited. We introduce PrefEval, a benchmark f…
From Pixels to Personas: Investigating and Modeling Self-Anthropomorphism in Human-Robot Dialogues
Yu Li, Devamanyu Hazarika, Di Jin +2
Self-anthropomorphism in robots manifests itself through their display of human-like characteristics in dialogue, such as expressing preferences and emotions. Our study systematica…
CESAR: Automatic Induction of Compositional Instructions for Multi-turn Dialogs
Taha Aksu, Devamanyu Hazarika, Shikib Mehri +4
Instruction-based multitasking has played a critical role in the success of large language models (LLMs) in multi-turn dialog applications. While publicly available LLMs have shown…
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)…
"What do others think?": Task-Oriented Conversational Modeling with Subjective Knowledge
Chao Zhao, Spandana Gella, Seokhwan Kim +7
Task-oriented Dialogue (TOD) Systems aim to build dialogue systems that assist users in accomplishing specific goals, such as booking a hotel or a restaurant. Traditional TODs rely…
KILM: Knowledge Injection into Encoder-Decoder Language Models
Yan Xu, Mahdi Namazifar, Devamanyu Hazarika +3
Large pre-trained language models (PLMs) have been shown to retain implicit knowledge within their parameters. To enhance this implicit knowledge, we propose Knowledge Injection in…
Role of Bias Terms in Dot-Product Attention
Mahdi Namazifar, Devamanyu Hazarika, Dilek Hakkani-Tur
Dot-product attention is a core module in the present generation of neural network models, particularly transformers, and is being leveraged across numerous areas such as natural l…
Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information
Yen-Ting Lin, Alexandros Papangelis, Seokhwan Kim +6
This work focuses on in-context data augmentation for intent detection. Having found that augmentation via in-context prompting of large pre-trained language models (PLMs) alone do…
Using In-Context Learning to Improve Dialogue Safety
Nicholas Meade, Spandana Gella, Devamanyu Hazarika +5
While large neural-based conversational models have become increasingly proficient dialogue agents, recent work has highlighted safety issues with these systems. For example, these…
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)…
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…
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…
Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention
Yifan Chen, Devamanyu Hazarika, Mahdi Namazifar +3
The massive amount of trainable parameters in the pre-trained language models (PLMs) makes them hard to be deployed to multiple downstream tasks. To address this issue, parameter-e…
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…
Zero-Shot Controlled Generation with Encoder-Decoder Transformers
Devamanyu Hazarika, Mahdi Namazifar, Dilek Hakkani-Tür
Controlling neural network-based models for natural language generation (NLG) has broad applications in numerous areas such as machine translation, document summarization, and dial…
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…
Domain Divergences: a Survey and Empirical Analysis
Abhinav Ramesh Kashyap, Devamanyu Hazarika, Min-Yen Kan +1
Domain divergence plays a significant role in estimating the performance of a model in new domains. While there is a significant literature on divergence measures, researchers find…
Multimodal Research in Vision and Language: A Review of Current and Emerging Trends
Shagun Uppal, Sarthak Bhagat, Devamanyu Hazarika +4
Deep Learning and its applications have cascaded impactful research and development with a diverse range of modalities present in the real-world data. More recently, this has enhan…
KinGDOM: Knowledge-Guided DOMain adaptation for sentiment analysis
Deepanway Ghosal, Devamanyu Hazarika, Abhinaba Roy +3
Cross-domain sentiment analysis has received significant attention in recent years, prompted by the need to combat the domain gap between different applications that make use of se…
MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis
Devamanyu Hazarika, Roger Zimmermann, Soujanya Poria
Multimodal Sentiment Analysis is an active area of research that leverages multimodal signals for affective understanding of user-generated videos. The predominant approach, addres…
Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research
Soujanya Poria, Devamanyu Hazarika, Navonil Majumder +1
Sentiment analysis as a field has come a long way since it was first introduced as a task nearly 20 years ago. It has widespread commercial applications in various domains like mar…