Papers by Neeraj Varshney

15 papers
Post-Abstention: Towards Reliably Re-Attempting the Abstained Instances in QA (2023.acl-long)

Copied to clipboard

Challenge: Despite remarkable progress made in natural language processing, even the state-of-the-art systems often make incorrect predictions.
Approach: They propose to use selective prediction to enable models to abstain from answering when their predictions are likely to be incorrect.
Outcome: The proposed method improves performance on 11 QA datasets and in- and out-of-domain settings.
Chaos with Keywords: Exposing Large Language Models Sycophancy to Misleading Keywords and Evaluating Defense Strategies (2024.findings-acl)

Copied to clipboard

Challenge: sycophancy is a type of hallucination in Large Language Models, which can lead to false information being presented.
Approach: They explore the sycophantic tendencies of Large Language Models where models provide accurate answers even if they are not entirely correct.
Outcome: The proposed models generate factually correct statements even when they are not completely correct.
ILDAE: Instance-Level Difficulty Analysis of Evaluation Data (2022.acl-long)

Copied to clipboard

Challenge: Instance-level difficulty analysis of evaluation data is a new field of research that focuses on leveraging instance difficulty in natural language processing.
Approach: They conduct Instance-Level Difficulty Analysis of Evaluation data in a large-scale setup of 23 datasets and demonstrate its five novel applications.
Outcome: The proposed model improves efficiency and accuracy, improves quality and improves Out-of-Domain performance.
Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing logical reasoning evaluation benchmarks focus on simplistic single-step or multi-step reasoning with limited set of inference rules.
Approach: They propose to use a multi-step logical reasoning evaluation dataset to measure their ability for human-like multi- step logical thinking.
Outcome: The proposed dataset covers three logic types including propositional, first-order, and non-monotonic logic with various inference rules and depths.
Investigating Acceleration of LLaMA Inference by Enabling Intermediate Layer Decoding via Instruction Tuning with ‘LITE’ (2024.findings-naacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have remarkable performance across a wide variety of tasks, however, their large size makes their inference slow and computationally expensive.
Approach: They propose to perform 'dynamic confidence-based early exiting' at token level from the intermediate layers which improves the computational efficiency of text generation without sacrificing the quality of the generation.
Outcome: The proposed model achieves significant cost and quality improvements while maintaining the quality of the generation.
The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness (2024.findings-acl)

Copied to clipboard

Challenge: Recent work on Large Language Models (LLMs) has identified a number of approaches to protect against their vulnerabilities and safety.
Approach: They propose to use a large collection of safe and unsafe prompts to evaluate various LLM defense strategies over both ‘safety’ and ‘over-defensiveness’.
Outcome: The proposed defense strategies are compared on multiple state-of-the-art LLMs and show that they are effective against both ‘safety’ and ‘over-defensiveness’.
LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Existing work investigating the logical reasoning ability of large language models has focused only on a couple of inference rules of propositional and first-order logics.
Approach: They propose to use a natural language question-answering dataset to evaluate the logical reasoning ability of large language models.
Outcome: The proposed model performs poorly on a range of natural language questions using chain-of-thought prompting.
A Unified Evaluation Framework for Novelty Detection and Accommodation in NLP with an Instantiation in Authorship Attribution (2023.findings-acl)

Copied to clipboard

Challenge: 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.
Approach: They propose a multi-stage task to evaluate a system's performance on pipelined novelty ‘detection’ and ‘accommodation’ tasks.
Outcome: The proposed model performs poorly in ‘closed-world’ settings where all the labels in the evaluation set are known at training time.
Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks (2022.emnlp-main)

Copied to clipboard

Challenge: a benchmark of 1,616 diverse NLP tasks and their expert-written instructions is used to test generalization of models to unseen tasks . a recent study shows that instruction-following models outperform instruction-based models by over 9% .
Approach: They build a benchmark of 1,616 diverse NLP tasks and their expert-written instructions.
Outcome: The proposed model outperforms existing instruction-following models by over 9% on the benchmark despite being smaller.
“John is 50 years old, can his son be 65?” Evaluating NLP Models’ Understanding of Feasibility (2023.eacl-main)

Copied to clipboard

Challenge: Recent work has found that large-scale language models lack commonsense reasoning ability . a dataset evaluating large-level language models is needed to evaluate their understanding of feasibility .
Approach: They propose a question-answering dataset that tests understanding of feasibility . they propose to use commonsense reasoning to reason about when an action is feasible .
Outcome: The proposed dataset shows that state-of-the-art models struggle to answer feasibility questions correctly.
LogicAttack: Adversarial Attacks for Evaluating Logical Consistency of Natural Language Inference (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) have demonstrated impressive performance on Natural Language Inference (NLI) tasks.
Approach: They propose a method to attack NLI models using diverse logical forms of premise and hypothesis using propositional logic to generate effective adversarial attacks.
Outcome: The proposed method achieves an average 53% Attack Success Rate (ASR) across multiple logic-based attacks.
Model Cascading: Towards Jointly Improving Efficiency and Accuracy of NLP Systems (2022.emnlp-main)

Copied to clipboard

Challenge: Pre-trained language models such as RoBERTa, ELECTRA, and T5 have a large number of parameters which makes them slow and computationally expensive.
Approach: They propose a technique that utilizes a collection of models of varying capacities to accurately yet efficiently output predictions.
Outcome: The proposed technique saves up to 88.93% computation cost and consistently achieves superior prediction accuracy with an improvement of up to 2.18%.
NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks (2022.acl-long)

Copied to clipboard

Challenge: Existing AI systems fail to perform basic mathematical reasoning when presented in a slightly different manner.
Approach: They propose a multi-task benchmark that evaluates the performance of AI systems on eight different tasks that at their core require simple arithmetic understanding.
Outcome: The proposed benchmark compares the performance of AI systems on eight different tasks.
Unsupervised Natural Language Inference Using PHL Triplet Generation (2022.findings-acl)

Copied to clipboard

Challenge: In some cases, training samples may not be available or collecting them could be time-consuming and resource-intensive.
Approach: They propose a procedural approach that leverages sentence transformations to collect PHL triplets for training NLI models.
Outcome: The proposed model outperforms existing models on several NLI benchmarks with a set of sentence transformations.
Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settings (2022.findings-acl)

Copied to clipboard

Challenge: Existing approaches to selective prediction are not consistently outperform the simplest baseline MaxProb in all three settings.
Approach: They propose to use a large-scale setup of 17 datasets to study selective prediction in NLP tasks using in-domain, out-of-domain and adversarial settings.
Outcome: The proposed approaches outperform the simplest baseline MaxProb in in-domain, out-of-domain and adversarial settings, but none consistently outperformed in all three settings.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations