48 citations · 92 across the 19 of their papers we have counts for
22 papers
Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs
Sameep Vani, Shreyas Jena, Maitreya Patel +3
While Video Large Language Models (Video-LLMs) have demonstrated remarkable performance across general video understanding benchmarks-particularly in video captioning and descripti…
NLKI: A lightweight Natural Language Knowledge Integration Framework for Improving Small VLMs in Commonsense VQA Tasks
Aritra Dutta, Swapnanil Mukherjee, Deepanway Ghosal +1
Commonsense visual-question answering often hinges on knowledge that is missing from the image or the question. Small vision-language models (sVLMs) such as ViLT, VisualBERT and FL…
LOGICPO: Efficient Translation of NL-based Logical Problems to FOL using LLMs and Preference Optimization
Koushik Viswanadha, Deepanway Ghosal, Somak Aditya
Logical reasoning is a key task for artificial intelligence due to it's role in major downstream tasks such as Question Answering, Summarization. Recent methods in improving the re…
SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation
Saurabh Kumar Pandey, Sachin Vashistha, Debrup Das +2
To understand the complexity of sequence classification tasks, Hahn et al. (2021) proposed sensitivity as the number of disjoint subsets of the input sequence that can each be indi…
[WIP] Jailbreak Paradox: The Achilles' Heel of LLMs
Abhinav Rao, Monojit Choudhury, Somak Aditya
We introduce two paradoxes concerning jailbreak of foundation models: First, it is impossible to construct a perfect jailbreak classifier, and second, a weaker model cannot consist…
Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided Interventions
Pengfei Hong, Navonil Majumder, Deepanway Ghosal +3
Recent advancements in Large Language Models (LLMs) have showcased striking results on existing logical reasoning benchmarks, with some models even surpassing human performance. Ho…
Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models
Man Luo, Shrinidhi Kumbhar, Ming shen +5
Logical reasoning is fundamental for humans yet presents a substantial challenge in the domain of Artificial Intelligence. Initially, researchers used Knowledge Representation and…
ReMask: A Robust Information-Masking Approach for Domain Counterfactual Generation
Pengfei Hong, Rishabh Bhardwaj, Navonil Majumdar +2
Domain shift is a big challenge in NLP, thus, many approaches resort to learning domain-invariant features to mitigate the inference phase domain shift. Such methods, however, fail…
Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks
Abhinav Rao, Sachin Vashistha, Atharva Naik +2
Recent explorations with commercial Large Language Models (LLMs) have shown that non-expert users can jailbreak LLMs by simply manipulating their prompts; resulting in degenerate o…
Generating Intermediate Steps for NLI with Next-Step Supervision
Deepanway Ghosal, Somak Aditya, Monojit Choudhury
The Natural Language Inference (NLI) task often requires reasoning over multiple steps to reach the conclusion. While the necessity of generating such intermediate steps (instead o…
Multilingual CheckList: Generation and Evaluation
Karthikeyan K, Shaily Bhatt, Pankaj Singh +4
Multilingual evaluation benchmarks usually contain limited high-resource languages and do not test models for specific linguistic capabilities. CheckList is a template-based evalua…
LoNLI: An Extensible Framework for Testing Diverse Logical Reasoning Capabilities for NLI
Ishan Tarunesh, Somak Aditya, Monojit Choudhury
Natural Language Inference (NLI) is considered a representative task to test natural language understanding (NLU). In this work, we propose an extensible framework to collectively…
Analyzing the Effects of Reasoning Types on Cross-Lingual Transfer Performance
Karthikeyan K, Aalok Sathe, Somak Aditya +1
Multilingual language models achieve impressive zero-shot accuracies in many languages in complex tasks such as Natural Language Inference (NLI). Examples in NLI (and equivalent co…
Trusting RoBERTa over BERT: Insights from CheckListing the Natural Language Inference Task
Ishan Tarunesh, Somak Aditya, Monojit Choudhury
The recent state-of-the-art natural language understanding (NLU) systems often behave unpredictably, failing on simpler reasoning examples. Despite this, there has been limited foc…
Analyzing the Nuances of Transformers' Polynomial Simplification Abilities
Vishesh Agarwal, Somak Aditya, Navin Goyal
Symbolic Mathematical tasks such as integration often require multiple well-defined steps and understanding of sub-tasks to reach a solution. To understand Transformers' abilities…
TaxiNLI: Taking a Ride up the NLU Hill
Pratik Joshi, Somak Aditya, Aalok Sathe +1
Pre-trained Transformer-based neural architectures have consistently achieved state-of-the-art performance in the Natural Language Inference (NLI) task. Since NLI examples encompas…
Uncovering Relations for Marketing Knowledge Representation
Somak Aditya, Atanu Sinha
Online behaviors of consumers and marketers generate massive marketing data, which ever more sophisticated models attempt to turn into insights and aid decisions by marketers. Yet,…
Integrating Knowledge and Reasoning in Image Understanding
Somak Aditya, Yezhou Yang, Chitta Baral
Deep learning based data-driven approaches have been successfully applied in various image understanding applications ranging from object recognition, semantic segmentation to visu…
Spatial Knowledge Distillation to aid Visual Reasoning
Somak Aditya, Rudra Saha, Yezhou Yang +1
For tasks involving language and vision, the current state-of-the-art methods tend not to leverage any additional information that might be present to gather relevant (commonsense)…
Explicit Reasoning over End-to-End Neural Architectures for Visual Question Answering
Somak Aditya, Yezhou Yang, Chitta Baral
Many vision and language tasks require commonsense reasoning beyond data-driven image and natural language processing. Here we adopt Visual Question Answering (VQA) as an example t…
Answering Image Riddles using Vision and Reasoning through Probabilistic Soft Logic
Somak Aditya, Yezhou Yang, Chitta Baral +1
In this work, we explore a genre of puzzles ("image riddles") which involves a set of images and a question. Answering these puzzles require both capabilities involving visual dete…
From Images to Sentences through Scene Description Graphs using Commonsense Reasoning and Knowledge
Somak Aditya, Yezhou Yang, Chitta Baral +2
In this paper we propose the construction of linguistic descriptions of images. This is achieved through the extraction of scene description graphs (SDGs) from visual scenes using…