Challenge: Promotional language is a term used to undermine objective evaluation of evidence, impede research development, and erode trust in science.
Approach: They propose formalized guidelines for identifying hype language and apply them to annotate a portion of the National Institutes of Health grant application corpus.
Outcome: The proposed guidelines can help humans reliably annotate candidate hype adjectives and train machine learning models yield promising results.

Similar Papers

Can Large Language Models Discern Evidence for Scientific Hypotheses? Case Studies in the Social Sciences (2024.lrec-main)

Copied to clipboard

Challenge: scholarly databases fail to aggregate, compare, contrast, and contextualize existing studies in service to a targeted research question.
Approach: They propose to use large language models to discern evidence in support or refute of specific hypotheses based on abstracts.
Outcome: The proposed method outperforms state-of-the-art methods and highlights opportunities for future research.
A Computational Exploration of Exaggeration (D18-1)

Copied to clipboard

Challenge: a new computational approach to exaggeration detection is needed for non-literal phenomena . a corpus of overstatements (or hyperboles) is used to detect exaggrements .
Approach: They propose a computational approach to detect exaggerated sentences using crowdsourcing data . they build a corpus containing overstatements and then evaluate models trained on HYPO .
Outcome: The proposed approach can detect exaggerated sentences using a crowdsourced dataset.
Identifying Exaggerated Language (2020.emnlp-main)

Copied to clipboard

Challenge: Recent studies on metaphor and metonymy have focused on hyperbole, but it is a relatively understudied phenomenon in the figurative language processing community.
Approach: They propose to use hyperbole detection to determine whether a sentence is hyperbolic . they also perform statistical and manual analyses of the corpus and address the automatic hyperbola detection task.
Outcome: The proposed dataset consists of 709 hyperbolic sentences with a non-hyperbolic version created by paraphrasing its hyperbolical counterpart.
Annotation Artifacts in Natural Language Inference Data (N18-2)

Copied to clipboard

Challenge: Large-scale datasets for natural language inference are created by crowdsourcing annotations . authors show that success of natural language models to date has been overestimated .
Approach: They propose a method for crowdsourcing annotations to generate 3 new sentences based on a sentence (premise) they show that a simple text categorization model can correctly classify the hypothesis alone in about 67% of SNLI and 53% of MultiNLI .
Outcome: The proposed model can classify the hypothesis alone in 67% of SNLI and 53% of MultiNLI datasets.
HyPe: Better Pre-trained Language Model Fine-tuning with Hidden Representation Perturbation (2023.acl-long)

Copied to clipboard

Challenge: Existing techniques to fine-tune pre-trained language models on downstream tasks are inadequate.
Approach: They propose a technique to perturb hidden Transformers representations by enhancing generalization of hidden representations from different layers.
Outcome: The proposed technique outperforms vanilla fine-tuning and enhances generalization of hidden representations from different layers.
Towards a Gold Standard Corpus for Variable Detection and Linking in Social Science Publications (L18-1)

Copied to clipboard

Challenge: a new corpus for detecting and linking survey variables is being developed . the corpus is multilingual and includes manually curated word and phrase alignments .
Approach: They propose to create a corpus for the evaluation of detecting and linking survey variables in social science publications.
Outcome: The proposed corpus is the first gold standard for the variable detection and linking task.
HypoGen: Hyperbole Generation with Commonsense and Counterfactual Knowledge (2021.findings-emnlp)

Copied to clipboard

Challenge: despite its abundance, the computational explorations of hyperboles remain under-explored.
Approach: They propose a sentence-level hyperbole generation method that leverages commonsense and counterfactual inference to generate hyperbolic candidates based on the results.
Outcome: The proposed method generates hyperboles with high success rate, intensity, funniness, and creativity.
SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference (D18-1)

Copied to clipboard

Challenge: a new dataset presents a task of grounded commonsense inference, unifying natural language inference and commonsensical reasoning.
Approach: They propose a procedure that constructs a de-biased dataset by iteratively training stylistic classifiers and using them to filter the data.
Outcome: The proposed procedure oversamples a de-biased dataset using state-of-the-art language models . human models struggle on the proposed procedure, indicating significant opportunities for future research.
Exploring the Limitations of Detecting Machine-Generated Text (2025.coling-main)

Copied to clipboard

Challenge: Recent advances in the quality of the generation of text by large language models have spurred research into identifying machine-generated text.
Approach: They audit classification performance for detecting machine-generated text by evaluating on texts with varying writing styles.
Outcome: The proposed methods are highly sensitive to stylistic changes and complexity, and in some cases degrade entirely to random classifiers.
The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail (2022.acl-long)

Copied to clipboard

Challenge: Researchers in NLP often frame and discuss research results in ways that serve to deemphasize the field’s successes, often in response to the field's widespread hype.
Approach: They propose to use more rigorous evaluation techniques to avoid false claims about the limits of our best technology.
Outcome: This paper urges researchers to be careful about these claims and suggests research directions and communication strategies that will make it easier to avoid or rebut them.

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