Search Results for author:
Found 96 papers, 33 papers with code
LoRACode: LoRA Adapters for Code Embeddings
Code embeddings are essential for semantic code search; however, current approaches often struggle to capture the precise syntactic and contextual nuances inherent in code.
From Fog to Failure: How Dehazing Can Harm Clear Image Object Detection
This study explores the challenges of integrating human visual cue-based dehazing into object detection, given the selective nature of human perception.
Multilingual State Space Models for Structured Question Answering in Indic Languages
The diversity and complexity of Indic languages present unique challenges for natural language processing (NLP) tasks, particularly in the domain of question answering (QA). To address these challenges, this paper explores the application of State Space Models (SSMs), to build efficient and contextually aware QA systems tailored for Indic languages.
IndicMMLU-Pro: Benchmarking Indic Large Language Models on Multi-Task Language Understanding
Known by more than 1. 5 billion people in the Indian subcontinent, Indic languages present unique challenges and opportunities for natural language processing (NLP) research due to their rich cultural heritage, linguistic diversity, and complex structures.
Potential and Perils of Large Language Models as Judges of Unstructured Textual Data
Our findings reveal that while LLM-as-judge offer a scalable solution comparable to human raters, humans may still excel at detecting subtle, context-specific nuances.
DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization
The rapid rise of large language models (LLMs) has unlocked many applications but also underscores the challenge of aligning them with diverse values and preferences.
On the Feasibility of Vision-Language Models for Time-Series Classification
We develop a novel approach that incorporates graphical data representations as images in conjunction with numerical data.
LLMsAgainstHate @ NLU of Devanagari Script Languages 2025: Hate Speech Detection and Target Identification in Devanagari Languages via Parameter Efficient Fine-Tuning of LLMs
The detection of hate speech has become increasingly important in combating online hostility and its real-world consequences.
SKETCH: Structured Knowledge Enhanced Text Comprehension for Holistic Retrieval
Notably, on the Italian Cuisine dataset, SKETCH achieved an answer relevancy of 0. 94 and a context precision of 0. 99, representing the highest performance across all evaluated metrics.
KnowledgePrompts: Exploring the Abilities of Large Language Models to Solve Proportional Analogies via Knowledge-Enhanced Prompting
Making analogies is fundamental to cognition.
Improving speaker verification robustness with synthetic emotional utterances
A speaker verification (SV) system offers an authentication service designed to confirm whether a given speech sample originates from a specific speaker.
All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages
In pursuit of culturally diverse global multimodal models, our proposed All Languages Matter Benchmark (ALM-bench) represents the largest and most comprehensive effort to date for evaluating LMMs across 100 languages.
Visual Counter Turing Test (VCT^2): Discovering the Challenges for AI-Generated Image Detection and Introducing Visual AI Index (V_AI)
The proliferation of AI techniques for image generation, coupled with their increasing accessibility, has raised significant concerns about the potential misuse of these images to spread misinformation.
ViBe: A Text-to-Video Benchmark for Evaluating Hallucination in Large Multimodal Models
We introduce ViBe: a large-scale Text-to-Video Benchmark of hallucinated videos from T2V models.
DM-Codec: Distilling Multimodal Representations for Speech Tokenization
Recent advancements in speech-language models have yielded significant improvements in speech tokenization and synthesis.
Overview of Factify5WQA: Fact Verification through 5W Question-Answering
Researchers have found that fake news spreads much times faster than real news.
MedVisionLlama: Leveraging Pre-Trained Large Language Model Layers to Enhance Medical Image Segmentation
Large Language Models (LLMs), known for their versatility in textual data, are increasingly being explored for their potential to enhance medical image segmentation, a crucial task for accurate diagnostic imaging.
Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types
Visual Question-Answering (VQA) has become key to user experience, particularly after improved generalization capabilities of Vision-Language Models (VLMs).
Density Adaptive Attention-based Speech Network: Enhancing Feature Understanding for Mental Health Disorders
Speech-based depression detection poses significant challenges for automated detection due to its unique manifestation across individuals and data scarcity.
Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMs
Given the widespread dissemination of misinformation on social media, implementing fact-checking mechanisms for online claims is essential.
RoundTable: Leveraging Dynamic Schema and Contextual Autocomplete for Enhanced Query Precision in Tabular Question Answering
With advancements in Large Language Models (LLMs), a major use case that has emerged is querying databases in plain English, translating user questions into executable database queries, which has improved significantly.
Unboxing Occupational Bias: Grounded Debiasing of LLMs with U.S. Labor Data
Large Language Models (LLMs) are prone to inheriting and amplifying societal biases embedded within their training data, potentially reinforcing harmful stereotypes related to gender, occupation, and other sensitive categories.
Out-of-Distribution Detection with Attention Head Masking for Multimodal Document Classification
To address the scarcity of high-quality publicly available document datasets and encourage further research on OOD detection for documents, we introduce FinanceDocs, a new document AI dataset.
The Brittleness of AI-Generated Image Watermarking Techniques: Examining Their Robustness Against Visual Paraphrasing Attacks
However, in this paper, we argue that current image watermarking methods are fragile and susceptible to being circumvented through visual paraphrase attacks.
How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions
We prompt different LLMs with a series of advice requests based on 5 Hofstede Cultural Dimensions -- a quantifiable way of representing the values of a country.
Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles
It assesses the complexity of tasks with the Hierarchical Prompting Index (HPI), which demonstrates the cognitive competencies of LLMs across diverse datasets and offers insights into the cognitive demands that datasets place on different LLMs.
Ranked #1 on
Machine Translation
on IWSLT 2017
Are Small Language Models Ready to Compete with Large Language Models for Practical Applications?
The rapid rise of Language Models (LMs) has expanded their use in several applications.
Investigating Annotator Bias in Large Language Models for Hate Speech Detection
This paper serves as a crucial resource, guiding researchers and practitioners in harnessing the potential of LLMs for data annotation, thereby fostering advancements in this critical field.
Decoding the Diversity: A Review of the Indic AI Research Landscape
This work aims to serve as a valuable resource for researchers and practitioners working in the field of NLP, particularly those focused on Indic languages, and contributes to the development of more accurate and efficient LLM applications for these languages.
Cognitively Inspired Energy-Based World Models
One of the predominant methods for training world models is autoregressive prediction in the output space of the next element of a sequence.
MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention
In the digital world, memes present a unique challenge for content moderation due to their potential to spread harmful content.
The Evolution of Multimodal Model Architectures
This work uniquely identifies and characterizes four prevalent multimodal model architectural patterns in the contemporary multimodal landscape.
Enhancing Adverse Drug Event Detection with Multimodal Dataset: Corpus Creation and Model Development
Additionally, we introduce a framework that leverages the capabilities of LLMs and VLMs for ADE detection by generating detailed descriptions of medical images depicting ADEs, aiding healthcare professionals in visually identifying adverse events.
How Culturally Aware are Vision-Language Models?
Our research compares the performance of four popular vision-language models (GPT-4V, Gemini Pro Vision, LLaVA, and OpenFlamingo) in identifying culturally specific information in such images and creating accurate and culturally sensitive image captions.
A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models
The rapid advancement of foundation models (FMs) across language, image, audio, and video domains has shown remarkable capabilities in diverse tasks.
A Comprehensive Survey of Accelerated Generation Techniques in Large Language Models
Despite the crucial importance of accelerating text generation in large language models (LLMs) for efficiently producing content, the sequential nature of this process often leads to high inference latency, posing challenges for real-time applications.
Parameter Efficient Fine Tuning: A Comprehensive Analysis Across Applications
The rise of deep learning has marked significant progress in fields such as computer vision, natural language processing, and medical imaging, primarily through the adaptation of pre-trained models for specific tasks.
Cross-Platform Hate Speech Detection with Weakly Supervised Causal Disentanglement
Content moderation faces a challenging task as social media's ability to spread hate speech contrasts with its role in promoting global connectivity.
FACTOID: FACtual enTailment fOr hallucInation Detection
We present FACTOID (FACTual enTAILment for hallucInation Detection), a benchmark dataset for FE.
"Sorry, Come Again?" Prompting -- Enhancing Comprehension and Diminishing Hallucination with [PAUSE]-injected Optimal Paraphrasing
We have fine-tuned an LLM with injected [PAUSE] tokens, allowing the LLM to pause while reading lengthier prompts.
Refining Text-to-Image Generation: Towards Accurate Training-Free Glyph-Enhanced Image Generation
We introduce a benchmark, LenCom-Eval, specifically designed for testing models' capability in generating images with Lengthy and Complex visual text.
Optical Character Recognition (OCR)
Text-to-Image Generation
ClaimVer: Explainable Claim-Level Verification and Evidence Attribution of Text Through Knowledge Graphs
In the midst of widespread misinformation and disinformation through social media and the proliferation of AI-generated texts, it has become increasingly difficult for people to validate and trust information they encounter.
OffensiveLang: A Community Based Implicit Offensive Language Dataset
Firstly, the existing datasets primarily rely on the collection of texts containing explicit offensive keywords, making it challenging to capture implicitly offensive contents that are devoid of these keywords.
PHAnToM: Persona-based Prompting Has An Effect on Theory-of-Mind Reasoning in Large Language Models
These differences have been attributed to many factors, such as variations in prompting and the specific LLMs used.
Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models
Large Language Models (LLMs) have become a cornerstone in the field of Natural Language Processing (NLP), offering transformative capabilities in understanding and generating human-like text.
A Survey of AI-generated Text Forensic Systems: Detection, Attribution, and Characterization
We have witnessed lately a rapid proliferation of advanced Large Language Models (LLMs) capable of generating high-quality text.
Cause and Effect: Can Large Language Models Truly Understand Causality?
The knowledge from ConceptNet enhances the performance of multiple causal reasoning tasks such as causal discovery, causal identification and counterfactual reasoning.
COBIAS: Contextual Reliability in Bias Assessment
We develop the Context-Oriented Bias Indicator and Assessment Score (COBIAS) to measure a biased statement's reliability in detecting bias based on the variance in model behavior across different contexts.
Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions
The advent of Large Language Models (LLMs) has significantly reshaped the trajectory of the AI revolution.
From Prejudice to Parity: A New Approach to Debiasing Large Language Model Word Embeddings
Embeddings play a pivotal role in the efficacy of Large Language Models.
Born With a Silver Spoon? Investigating Socioeconomic Bias in Large Language Models
Socioeconomic bias in society exacerbates disparities, influencing access to opportunities and resources based on individuals' economic and social backgrounds.
LLMAuditor: A Framework for Auditing Large Language Models Using Human-in-the-Loop
A case study using questions from the TruthfulQA dataset demonstrates that we can generate a reliable set of probes from one LLM that can be used to audit inconsistencies in a different LLM.
AuditLLM: A Tool for Auditing Large Language Models Using Multiprobe Approach
AuditLLM's primary function is to audit a given LLM by deploying multiple probes derived from a single question, thus detecting any inconsistencies in the model's comprehension or performance.
Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Review
The paper underscores the significance of Large Language Models (LLMs) in reshaping recommender systems, attributing their value to unique reasoning abilities absent in traditional recommenders.
Source-Free Domain Adaptation with Diffusion-Guided Source Data Generation
This paper introduces a novel approach to leverage the generalizability of Diffusion Models for Source-Free Domain Adaptation (DM-SFDA).
Source-Free Domain Adaptation
Unsupervised Domain Adaptation
A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications
This approach leverages task-specific instructions, known as prompts, to enhance model efficacy without modifying the core model parameters.
Post-Training Embedding Alignment for Decoupling Enrollment and Runtime Speaker Recognition Models
Automated speaker identification (SID) is a crucial step for the personalization of a wide range of speech-enabled services.
Density Adaptive Attention is All You Need: Robust Parameter-Efficient Fine-Tuning Across Multiple Modalities
We propose the Multi-Head Density Adaptive Attention Mechanism (DAAM), a novel probabilistic attention framework that can be used for Parameter-Efficient Fine-tuning (PEFT), and the Density Adaptive Transformer (DAT), designed to enhance information aggregation across multiple modalities, including Speech, Text, and Vision.
The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey
The advent of Large Language Models (LLMs) represents a notable breakthrough in Natural Language Processing (NLP), contributing to substantial progress in both text comprehension and generation.
MedSumm: A Multimodal Approach to Summarizing Code-Mixed Hindi-English Clinical Queries
This work introduces the task of multimodal medical question summarization for codemixed input in a low-resource setting.
A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models
As Large Language Models (LLMs) continue to advance in their ability to write human-like text, a key challenge remains around their tendency to hallucinate generating content that appears factual but is ungrounded.
CLIPSyntel: CLIP and LLM Synergy for Multimodal Question Summarization in Healthcare
This multimodal approach not only enhances the decision-making process in healthcare but also fosters a more nuanced understanding of patient queries, laying the groundwork for future research in personalized and responsive medical care
Dynamic Corrective Self-Distillation for Better Fine-Tuning of Pretrained Models
We tackle the challenging issue of aggressive fine-tuning encountered during the process of transfer learning of pre-trained language models (PLMs) with limited labeled downstream data.
SEPSIS: I Can Catch Your Lies -- A New Paradigm for Deception Detection
This research explores the problem of deception through the lens of psychology, employing a framework that categorizes deception into three forms: lies of omission, lies of commission, and lies of influence.
Improved Contextual Recognition In Automatic Speech Recognition Systems By Semantic Lattice Rescoring
Automatic Speech Recognition (ASR) has witnessed a profound research interest.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
On the Relationship between Sentence Analogy Identification and Sentence Structure Encoding in Large Language Models
Through our analysis, we find that LLMs' ability to identify sentence analogies is positively correlated with their ability to encode syntactic and semantic structures of sentences.
Counter Turing Test CT^2: AI-Generated Text Detection is Not as Easy as You May Think -- Introducing AI Detectability Index
Given this cynosural spotlight on generative AI, AI-generated text detection (AGTD) has emerged as a topic that has already received immediate attention in research, with some initial methods having been proposed, soon followed by emergence of techniques to bypass detection.
The Troubling Emergence of Hallucination in Large Language Models -- An Extensive Definition, Quantification, and Prescriptive Remediations
Finally, to establish a method for quantifying and to offer a comparative spectrum that allows us to evaluate and rank LLMs based on their vulnerability to producing hallucinations, we propose Hallucination Vulnerability Index (HVI).
Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems
Recent advancements in Large Language Models empower them to follow freeform instructions, including imitating generic or specific demographic personas in conversations.
Transcending Domains through Text-to-Image Diffusion: A Source-Free Approach to Domain Adaptation
Domain Adaptation (DA) is a method for enhancing a model's performance on a target domain with inadequate annotated data by applying the information the model has acquired from a related source domain with sufficient labeled data.
Can LLMs Augment Low-Resource Reading Comprehension Datasets? Opportunities and Challenges
Large Language Models (LLMs) have demonstrated impressive zero shot performance on a wide range of NLP tasks, demonstrating the ability to reason and apply commonsense.
Overview of Memotion 3: Sentiment and Emotion Analysis of Codemixed Hinglish Memes
In this paper, we present the overview of the Memotion 3 shared task, as part of the DeFactify 2 workshop at AAAI-23.
CONFLATOR: Incorporating Switching Point based Rotatory Positional Encodings for Code-Mixed Language Modeling
Therefore, to enrich word information and incorporate positional information, positional encoding is defined.
Generative Data Augmentation using LLMs improves Distributional Robustness in Question Answering
Robustness in Natural Language Processing continues to be a pertinent issue, where state of the art models under-perform under naturally shifted distributions.
RESTORE: Graph Embedding Assessment Through Reconstruction
We analyze their effectiveness in preserving the (a) topological structure of node-level graph reconstruction with an increasing number of hops and (b) semantic information on various word semantic and analogy tests.
Artificial Intelligence in Career Counseling: A Test Case with ResumAI
It is difficult to find good resources or schedule an appointment with a career counselor to help with editing a resume for a specific role.
Breaking Language Barriers: A Question Answering Dataset for Hindi and Marathi
The recent advances in deep-learning have led to the development of highly sophisticated systems with an unquenchable appetite for data.
Causality Guided Disentanglement for Cross-Platform Hate Speech Detection
By disentangling input into platform-dependent features (useful for predicting hate targets) and platform-independent features (used to predict the presence of hate), we learn invariant representations resistant to distribution shifts.
Findings of Factify 2: Multimodal Fake News Detection
With social media usage growing exponentially in the past few years, fake news has also become extremely prevalent.
PEACE: Cross-Platform Hate Speech Detection- A Causality-guided Framework
Hate speech detection refers to the task of detecting hateful content that aims at denigrating an individual or a group based on their religion, gender, sexual orientation, or other characteristics.
Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers
Both PAAT and PAAB surpass their respective backbone Transformers by up to 9. 8% in real-world action recognition and 21. 8% in multi-view robotic video alignment.
FACTIFY3M: A Benchmark for Multimodal Fact Verification with Explainability through 5W Question-Answering
To address this gap, we introduce FACTIFY 3M, a dataset of 3 million samples that pushes the boundaries of the domain of fact verification via a multimodal fake news dataset, in addition to offering explainability through the concept of 5W question-answering.
IMAGINATOR: Pre-Trained Image+Text Joint Embeddings using Word-Level Grounding of Images
We also evaluate pre-trained IMAGINATOR JEs on three downstream tasks: (i) image captioning, (ii) Image2Tweet, and (iii) text-based image retrieval.
ANALOGICAL -- A Novel Benchmark for Long Text Analogy Evaluation in Large Language Models
Over the past decade, analogies, in the form of word-level analogies, have played a significant role as an intrinsic measure of evaluating the quality of word embedding methods such as word2vec.
FACTIFY-5WQA: 5W Aspect-based Fact Verification through Question Answering
Finally, we report a baseline QA system to automatically locate those answers from evidence documents, which can serve as a baseline for future research in the field.
Factify 2: A Multimodal Fake News and Satire News Dataset
In this paper, we provide a multi-modal fact-checking dataset called FACTIFY 2, improving Factify 1 by using new data sources and adding satire articles.
Memotion 3: Dataset on Sentiment and Emotion Analysis of Codemixed Hindi-English Memes
Memes are the new-age conveyance mechanism for humor on social media sites.
Few-shot Multimodal Multitask Multilingual Learning
While few-shot learning as a transfer learning paradigm has gained significant traction for scenarios with limited data, it has primarily been explored in the context of building unimodal and unilingual models.
Facial Expression Recognition using Squeeze and Excitation-powered Swin Transformers
The ability to recognize and interpret facial emotions is a critical component of human communication, as it allows individuals to understand and respond to emotions conveyed through facial expressions and vocal tones.
I see what you hear: a vision-inspired method to localize words
This paper explores the possibility of using visual object detection techniques for word localization in speech data.
iReason: Multimodal Commonsense Reasoning using Videos and Natural Language with Interpretability
We demonstrate the effectiveness of iReason using a two-pronged comparative analysis with language representation learning models (BERT, GPT-2) as well as current state-of-the-art multimodal causality models.
iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering
Most prior art in visual understanding relies solely on analyzing the "what" (e. g., event recognition) and "where" (e. g., event localization), which in some cases, fails to describe correct contextual relationships between events or leads to incorrect underlying visual attention.
Ranked #4 on
Video Question Answering
on TVQA
iSeeBetter: Spatio-Temporal Video Super Resolution using Recurrent-Generative Back-Projection Networks
However, generative adversarial networks (GANs) offer a competitive advantage by being able to mitigate the issue of a lack of finer texture details, usually seen with CNNs when super-resolving at large upscaling factors.
Ranked #1 on
Video Super-Resolution
on Vimeo90K
iSeeBetter: Spatio-temporal video super-resolution using recurrent generative back-projection networks
However, generative adversarial networks (GANs) offer a competitive advantage by being able to mitigate the issue of a lack of finer texture details, usually seen with CNNs when super-resolving at large upscaling factors.
Comparative Study and Optimization of Feature-Extraction Techniques for Content based Image Retrieval
The aim of a Content-Based Image Retrieval (CBIR) system, also known as Query by Image Content (QBIC), is to help users to retrieve relevant images based on their contents.
A robust, low-cost approach to Face Detection and Face Recognition
The proposed Face Detection and Recognition system using Discrete Wavelet Transform (DWT) accepts face frames as input from a database containing images from low cost devices such as VGA cameras, webcams or even CCTV's, where image quality is inferior.
