Picture for Neeraj Varshney

Neeraj Varshney

Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models

Add code
Jun 24, 2024
Viaarxiv icon

Efficient Transmission Scheme for LEO Satellite-Based NB-IoT: A Data-Driven Perspective

Add code
Jun 20, 2024
Viaarxiv icon

Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation

Add code
Jun 08, 2024
Viaarxiv icon

Chaos with Keywords: Exposing Large Language Models Sycophancy to Misleading Keywords and Evaluating Defense Strategies

Add code
Jun 06, 2024
Viaarxiv icon

Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models

Add code
Apr 23, 2024
Viaarxiv icon

The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness

Add code
Dec 30, 2023
Viaarxiv icon

Accelerating LLaMA Inference by Enabling Intermediate Layer Decoding via Instruction Tuning with LITE

Add code
Nov 07, 2023
Viaarxiv icon

Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models

Add code
Oct 02, 2023
Figure 1 for Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models
Figure 2 for Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models
Figure 3 for Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models
Figure 4 for Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models
Viaarxiv icon

Can NLP Models 'Identify', 'Distinguish', and 'Justify' Questions that Don't have a Definitive Answer?

Add code
Sep 08, 2023
Figure 1 for Can NLP Models 'Identify', 'Distinguish', and 'Justify' Questions that Don't have a Definitive Answer?
Figure 2 for Can NLP Models 'Identify', 'Distinguish', and 'Justify' Questions that Don't have a Definitive Answer?
Figure 3 for Can NLP Models 'Identify', 'Distinguish', and 'Justify' Questions that Don't have a Definitive Answer?
Figure 4 for Can NLP Models 'Identify', 'Distinguish', and 'Justify' Questions that Don't have a Definitive Answer?
Viaarxiv icon

A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation

Add code
Jul 08, 2023
Figure 1 for A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation
Figure 2 for A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation
Figure 3 for A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation
Figure 4 for A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation
Viaarxiv icon