Search Results for author:
Found 19 papers, 9 papers with code
Active Learning for BERT: An Empirical Study
Here, we present a large-scale empirical study on active learning techniques for BERT-based classification, addressing a diverse set of AL strategies and datasets.
WildIFEval: Instruction Following in the Wild
In this work, we introduce WildIFEval - a large-scale dataset of 12K real user instructions with diverse, multi-constraint conditions.
The Mighty ToRR: A Benchmark for Table Reasoning and Robustness
ToRR goes beyond model performance rankings, and is designed to reflect whether models can handle tabular data consistently and robustly, across a variety of common table representation formats.
JuStRank: Benchmarking LLM Judges for System Ranking
To address this gap, we conduct the first large-scale study of LLM judges as system rankers.
Do These LLM Benchmarks Agree? Fixing Benchmark Evaluation with BenchBench
Despite the crucial role of BAT for benchmark builders and consumers, there are no standardized procedures for such agreement testing.
Label-Efficient Model Selection for Text Generation
Model selection for a given target task can be costly, as it may entail extensive annotation of the quality of outputs of different models.
Unitxt: Flexible, Shareable and Reusable Data Preparation and Evaluation for Generative AI
In the dynamic landscape of generative NLP, traditional text processing pipelines limit research flexibility and reproducibility, as they are tailored to specific dataset, task, and model combinations.
Efficient Benchmarking of Language Models
The increasing versatility of language models (LMs) has given rise to a new class of benchmarks that comprehensively assess a broad range of capabilities.
Active Learning for Natural Language Generation
In this paper, we present a first systematic study of active learning for NLG, considering a diverse set of tasks and multiple leading selection strategies, and harnessing a strong instruction-tuned model.
The Benefits of Bad Advice: Autocontrastive Decoding across Model Layers
Applying language models to natural language processing tasks typically relies on the representations in the final model layer, as intermediate hidden layer representations are presumed to be less informative.
Zero-Shot Text Classification with Self-Training
Recent advances in large pretrained language models have increased attention to zero-shot text classification.
Label Sleuth: From Unlabeled Text to a Classifier in a Few Hours
Text classification can be useful in many real-world scenarios, saving a lot of time for end users.
Cluster & Tune: Boost Cold Start Performance in Text Classification
In real-world scenarios, a text classification task often begins with a cold start, when labeled data is scarce.
Cluster & Tune: Enhance BERT Performance in Low Resource Text Classification
In such low resources scenarios, we suggest performing an unsupervised classification task prior to fine-tuning on the target task.
Financial Event Extraction Using Wikipedia-Based Weak Supervision
Extraction of financial and economic events from text has previously been done mostly using rule-based methods, with more recent works employing machine learning techniques.
Corpus Wide Argument Mining -- a Working Solution
One of the main tasks in argument mining is the retrieval of argumentative content pertaining to a given topic.
A Dataset of General-Purpose Rebuttal
In Natural Language Understanding, the task of response generation is usually focused on responses to short texts, such as tweets or a turn in a dialog.
Argument Invention from First Principles
In this work we aim to explicitly define a taxonomy of such principled recurring arguments, and, given a controversial topic, to automatically identify which of these arguments are relevant to the topic.
Controversy in Context
With the growing interest in social applications of Natural Language Processing and Computational Argumentation, a natural question is how controversial a given concept is.
