Challenge: Neural network models have significantly pushed forward performance on natural language processing benchmarks with the development of largescale language model pre-training.
Approach: They find that models on natural language inference and reading comprehension are unstable . they propose to use a model-selection routine to analyze the model's instability .
Outcome: The proposed models can perform poorly on two language-related tasks, the authors show . they also show that the model selection routine is unstable, and that it is not reliable .

Similar Papers

Measuring the Instability of Fine-Tuning (2023.acl-long)

Copied to clipboard

Challenge: Many previous studies have investigated fine-tuning pre-trained language models on downstream tasks with varying random seeds, but they only used the standard deviation of performance scores (SD) as their measure, which is a narrow characterization of instability.
Approach: They propose a systematic evaluation framework for the standard deviation of performance scores (SD) and six other measures quantifying instability of different granularity levels.
Outcome: The proposed framework will be used to evaluate the validity of these measures and to improve them.
Behavior Analysis of NLI Models: Uncovering the Influence of Three Factors on Robustness (N18-1)

Copied to clipboard

Challenge: Currently, state-of-the-art models achieve impressive test set performance in the form of accuracy scores.
Approach: They examine the models' robustness to semantically-valid alterations to the input data by identifying three factors and comparing their impact on three SNLI models.
Outcome: The proposed models show that they can generalise to new in-domain instances while also showing that they suffer from insensitivity to small but semantically significant alterations.
What Will it Take to Fix Benchmarking in Natural Language Understanding? (2021.naacl-main)

Copied to clipboard

Challenge: Evaluation for many natural language understanding (NLU) tasks is broken due to unreliable and biased systems scoring so high on standard benchmarks.
Approach: They argue that current benchmarks fail at four criteria for evaluation . they argue that adversarial data collection does not address the causes of failures .
Outcome: The proposed frameworks fail at four criteria, and adversarial data collection does not address the causes of these failures, the authors argue . restoring a healthy evaluation ecosystem will require significant progress in the design of benchmark datasets, reliability with which they are annotated, their size, and the ways they handle social bias.
A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have gained significant attention due to their capabilities in performing diverse tasks across domains.
Approach: They review the primary challenges and limitations causing inconsistencies in evaluations . early models could generate coherent text but limited to simple tasks .
Outcome: The proposed evaluations are reproducible, reliable, and robust.
SCORE: Systematic COnsistency and Robustness Evaluation for Large Language Models (2025.naacl-industry)

Copied to clipboard

Challenge: Typical evaluations of Large Language Models (LLMs) report a single accuracy metric per dataset, often derived from an optimized setup.
Approach: They propose a framework for non-adversarial evaluation of large language models that evaluates models by repeatedly testing them on the same benchmarks in various setups.
Outcome: The proposed framework evaluates models by repeatedly testing them on the same benchmarks in various setups to give a realistic estimate of their accuracy and consistency.
Morphological Inflection: A Reality Check (2023.acl-long)

Copied to clipboard

Challenge: Morphological inflection is a popular task in sub-word NLP with practical and cognitive applications.
Approach: They propose new methods to analyze data sets and evaluate their generalization abilities to better reflect likely use-cases.
Outcome: The proposed methods improve generalizability and reliability of results and improve generalization abilities.
Let’s Stop Incorrect Comparisons in End-to-end Relation Extraction! (2020.emnlp-main)

Copied to clipboard

Challenge: Existing literature on Relation Extraction (RE) uses multiple evaluation setups to compare performance.
Approach: They propose to quantify the most common comparison mistake and evaluate it leads to overestimating the final RE performance by around 5% on ACE05.
Outcome: The proposed meta-analysis overestimates the final RE performance by around 5% on ACE05.
Evaluating the Robustness of Neural Language Models to Input Perturbations (2021.emnlp-main)

Copied to clipboard

Challenge: High-performance neural language models have achieved state-of-the-art results on a wide range of NLP tasks, but results for common benchmark datasets often do not reflect model reliability and robustness when applied to noisy, real-world data.
Approach: They propose to implement character-level and word-level perturbation methods to simulate scenarios in which input texts may be slightly noisy or different from the data distribution on which NLP systems were trained.
Outcome: The proposed methods simulate scenarios in which input texts may be slightly noisy or different from the data distribution on which NLP systems were trained.
Robustness and Adversarial Examples in Natural Language Processing (2021.emnlp-tutorials)

Copied to clipboard

Challenge: This tutorial aims to raise awareness of practical concerns about NLP robustness . it aims at addressing the weaknesses of NLP systems when faced with adversarial inputs and data with a distribution shift .
Approach: This tutorial aims to bring awareness of practical concerns about NLP robustness . it reviews recent studies on analyzing the weakness of NLP systems when facing adversarial inputs .
Outcome: This tutorial aims to bring awareness of practical concerns about NLP robustness . it will examine the weaknesses of NLP systems when faced with adversarial inputs and data with a distribution shift .
Whispers of Doubt Amidst Echoes of Triumph in NLP Robustness (2024.naacl-long)

Copied to clipboard

Challenge: Existing approaches to measure robustness are problematic, and out-of-domain evaluations are no longer relevant.
Approach: They examine models of different sizes spanning different architectural choices and pretraining objectives.
Outcome: The results show that not all out-of-domain tests provide insight into robustness . merely scaling models does not make them adequately robust .

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