Neeraj Varshney
YOU?
Author Swipe
View article: Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness
Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness Open
As Large Language Models (LLMs) are increasingly adopted as automated judges in benchmarking and reward modeling, ensuring their reliability, efficiency, and robustness has become critical. In this work, we present a systematic comparison …
View article: ENHANCING STUDENTS MOTIVATION BY ONLINE LEARNING ADVANCED TOOLS THROUGH COOPERATIVE LEARNING IN THE EFL CLASSROOM
ENHANCING STUDENTS MOTIVATION BY ONLINE LEARNING ADVANCED TOOLS THROUGH COOPERATIVE LEARNING IN THE EFL CLASSROOM Open
This study investigates how integrating online advanced learning tools within cooperative learning designs can enhance students’ motivation in English as a Foreign Language (EFL) classroom. Building on socio-constructivist and self-determi…
View article: Deep Learning-based Human Gesture Channel Modeling for Integrated Sensing and Communication Scenarios
Deep Learning-based Human Gesture Channel Modeling for Integrated Sensing and Communication Scenarios Open
With the development of Integrated Sensing and Communication (ISAC) for Sixth-Generation (6G) wireless systems, contactless human recognition has emerged as one of the key application scenarios. Since human gesture motion induces subtle an…
View article: Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models
Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models Open
As Large Language Models (LLMs) continue to exhibit remarkable performance in natural language understanding tasks, there is a crucial need to measure their ability for human-like multi-step logical reasoning. Existing logical reasoning ev…
View article: Efficient Transmission Scheme for LEO Satellite-Based NB-IoT: A Data-Driven Perspective
Efficient Transmission Scheme for LEO Satellite-Based NB-IoT: A Data-Driven Perspective Open
This study analyses the medium access control (MAC) layer aspects of a low-Earth-orbit (LEO) satellite-based Internet of Things (IoT) network. A transmission scheme based on change detection is proposed to accommodate more users within the…
View article: Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation
Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation Open
Large Language Models (LLMs) have achieved remarkable performance across a wide variety of natural language tasks. However, they have been shown to suffer from a critical limitation pertinent to 'hallucination' in their output. Recent rese…
View article: Chaos with Keywords: Exposing Large Language Models Sycophantic Hallucination to Misleading Keywords and Evaluating Defense Strategies
Chaos with Keywords: Exposing Large Language Models Sycophantic Hallucination to Misleading Keywords and Evaluating Defense Strategies Open
This study explores the sycophantic tendencies of Large Language Models (LLMs), where these models tend to provide answers that match what users want to hear, even if they are not entirely correct. The motivation behind this exploration st…
View article: LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models
LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models Open
Recently developed large language models (LLMs) have been shown to perform remarkably well on a wide range of language understanding tasks. But, can they really "reason" over the natural language? This question has been receiving significa…
View article: Quasi-Deterministic Channel Propagation Model for Human Sensing: Gesture Recognition Use Case
Quasi-Deterministic Channel Propagation Model for Human Sensing: Gesture Recognition Use Case Open
We describe a quasi-deterministic channel propagation model for human gesture recognition reduced from real-time measurements with our context-aware channel sounder, considering four human subjects and 20 distinct body motions, for a total…
View article: The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness
The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness Open
As Large Language Models (LLMs) play an increasingly pivotal role in natural language processing applications, their safety concerns become critical areas of NLP research. This paper presents Safety and Over-Defensiveness Evaluation (SODE)…
View article: INGR Roadmap Satellite Chapter
INGR Roadmap Satellite Chapter Open
The fifth generation (5G) wireless communication systems development has brought about a paradigm shift using advanced technologies; including softwarization, virtualization, massive MIMO, and ultradensification, in addition to introducing…
View article: Accelerating LLaMA Inference by Enabling Intermediate Layer Decoding via Instruction Tuning with LITE
Accelerating LLaMA Inference by Enabling Intermediate Layer Decoding via Instruction Tuning with LITE Open
Large Language Models (LLMs) have achieved remarkable performance across a wide variety of natural language tasks; however, their large size makes their inference slow and computationally expensive. Focusing on this problem, we propose to …
View article: Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models
Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models Open
Logical reasoning is fundamental for humans yet presents a substantial challenge in the domain of Artificial Intelligence. Initially, researchers used Knowledge Representation and Reasoning (KR) systems that did not scale and required non-…
View article: Can NLP Models 'Identify', 'Distinguish', and 'Justify' Questions that Don't have a Definitive Answer?
Can NLP Models 'Identify', 'Distinguish', and 'Justify' Questions that Don't have a Definitive Answer? Open
Though state-of-the-art (SOTA) NLP systems have achieved remarkable performance on a variety of language understanding tasks, they primarily focus on questions that have a correct and a definitive answer. However, in real-world application…
View article: Adaptive Channel-State-Information Feedback in Integrated Sensing and Communication Systems
Adaptive Channel-State-Information Feedback in Integrated Sensing and Communication Systems Open
Efficient design of integrated sensing and communication systems can minimize signaling overhead by reducing the size and/or rate of feedback in reporting channel state information (CSI). To minimize the signaling overhead when performing …
View article: A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation
A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation Open
Recently developed large language models have achieved remarkable success in generating fluent and coherent text. However, these models often tend to 'hallucinate' which critically hampers their reliability. In this work, we address this c…
View article: Can NLP Models Correctly Reason Over Contexts that Break the Common Assumptions?
Can NLP Models Correctly Reason Over Contexts that Break the Common Assumptions? Open
Pre-training on large corpora of text enables the language models to acquire a vast amount of factual and commonsense knowledge which allows them to achieve remarkable performance on a variety of language understanding tasks. They typicall…
View article: A Unified Evaluation Framework for Novelty Detection and Accommodation in NLP with an Instantiation in Authorship Attribution
A Unified Evaluation Framework for Novelty Detection and Accommodation in NLP with an Instantiation in Authorship Attribution Open
State-of-the-art natural language processing models have been shown to achieve remarkable performance in 'closed-world' settings where all the labels in the evaluation set are known at training time. However, in real-world settings, 'novel…
View article: Post-Abstention: Towards Reliably Re-Attempting the Abstained Instances in QA
Post-Abstention: Towards Reliably Re-Attempting the Abstained Instances in QA Open
Despite remarkable progress made in natural language processing, even the state-of-the-art models often make incorrect predictions. Such predictions hamper the reliability of systems and limit their widespread adoption in real-world applic…
View article: Matrix Quantization and LPC Vocoder Based Linear Predictive for Low-Resource Speech Recognition system
Matrix Quantization and LPC Vocoder Based Linear Predictive for Low-Resource Speech Recognition system Open
Over the last ten years, there has been significant progress in the use of low-rate speech coders in voice applications for computers, military communications, and civil communications. This advancement has been made possible by the develo…
View article: Post-Abstention: Towards Reliably Re-Attempting the Abstained Instances in QA
Post-Abstention: Towards Reliably Re-Attempting the Abstained Instances in QA Open
Despite remarkable progress made in natural language processing, even the state-of-the-art models often make incorrect predictions. Such predictions hamper the reliability of systems and limit their widespread adoption in real-world applic…
View article: “John is 50 years old, can his son be 65?” Evaluating NLP Models’ Understanding of Feasibility
“John is 50 years old, can his son be 65?” Evaluating NLP Models’ Understanding of Feasibility Open
Himanshu Gupta, Neeraj Varshney, Swaroop Mishra, Kuntal Kumar Pal, Saurabh Arjun Sawant, Kevin Scaria, Siddharth Goyal, Chitta Baral. Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguisti…
View article: A Unified Evaluation Framework for Novelty Detection and Accommodation in NLP with an Instantiation in Authorship Attribution
A Unified Evaluation Framework for Novelty Detection and Accommodation in NLP with an Instantiation in Authorship Attribution Open
State-of-the-art natural language processing models have been shown to achieve remarkable performance in ‘closed-world’ settings where all the labels in the evaluation set are known at training time. However, in real-world settings, ‘novel…