Papers by Yoav Katz

16 papers
Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness (2026.acl-long)

Copied to clipboard

Challenge: Recent research suggests large language models encode meta-information about their own outputs.
Approach: They investigate whether large language models possess similar privileged knowledge about answer correctness . they train correctness classifiers on question representations from a model’s hidden states and external models .
Outcome: The proposed model outperforms peer-model models in factual knowledge tasks, but shows no advantage in math reasoning.
From Surrogacy to Adoption; From Bitcoin to Cryptocurrency: Debate Topic Expansion (P19-1)

Copied to clipboard

Challenge: Recent advances in argumentation mining have left much of the relevant argumentative content out of reach.
Approach: They propose a task of Debate Topic Expansion to find related topics for a given debate topic, along with an annotated dataset for the task.
Outcome: The proposed algorithms differ from well-studied lexical-semantic relations and show they work well in argumentation mining.
Welcome to the Real World: Efficient, Incremental and Scalable Key Point Analysis (2023.emnlp-industry)

Copied to clipboard

Challenge: Key Point Analysis (KPA) extracts the main points from opinions and quantifies their prevalence.
Approach: They propose a key point analysis framework that extracts the main points from opinions and quantifies their prevalence.
Outcome: The proposed system is able to match sentences to key points over five datasets and demonstrate its performance.
Knowledge is a Region in Weight Space for Fine-tuned Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: Specifically, language models that have been finetuned on the same dataset form a tight cluster in the weight space, while models finetuning on different datasets from the same underlying task form s looser clusters.
Approach: They analyze the weight space and the underlying loss landscape of different models to determine how they are interconnected and how they perform.
Outcome: The proposed method improves accuracy on 11 out of 12 datasets by starting from the center of the region, if not more, than using the pretrained model.
Financial Event Extraction Using Wikipedia-Based Weak Supervision (D19-51)

Copied to clipboard

Challenge: Existing methods for detecting financial and economic events from text have relied on a knowledge-base of financial events, or corresponding financial figures.
Approach: They propose to use Wikipedia sections to extract weak labels for sentences describing economic events from text.
Outcome: The proposed method can extract weak labels for sentences describing economic events from Wikipedia sentences.
Unitxt: Flexible, Shareable and Reusable Data Preparation and Evaluation for Generative AI (2024.naacl-demo)

Copied to clipboard

Challenge: Textual data processing pipelines are tailored to specific datasets, task and model combinations.
Approach: They propose a library for customizable textual data preparation and evaluation tailored to generative language models.
Outcome: Unitxt is a library for customizable textual data preparation and evaluation tailored to generative language models.
NERetrieve: Dataset for Next Generation Named Entity Recognition and Retrieval (2023.findings-emnlp)

Copied to clipboard

Challenge: Named Entity Recognition (NER) is a widely adopted NLP task . authors present three variants of NER task, with dataset to support them .
Approach: They propose three variants of the NER task, together with a dataset to support them . they propose a move towards more fine-grained entities and zero-shot recognition .
Outcome: The proposed model matches or surpasses existing models in NER tasks . the proposed model is based on a large, silver-annotated corpus of 4 million paragraphs .
NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings (2025.findings-emnlp)

Copied to clipboard

Challenge: NER Retriever uses a user-defined type description to retrieve documents mentioning entities of that type.
Approach: They propose a zero-shot retrieval framework for ad-hoc Named Entity Recognition . a user-defined type description is used to retrieve documents mentioning entities of that type .
Outcome: The proposed framework outperforms lexical and dense retrieval baselines on three benchmarks.
Zero-shot Topical Text Classification with LLMs - an Experimental Study (2023.findings-emnlp)

Copied to clipboard

Challenge: Topical text classification is an ancient, yet timely research area in natural language processing.
Approach: They compare the zero-shot performance of a variety of LMs over a large dataset of 23 publicly available TTC datasets.
Outcome: The proposed models outperform their counterparts over a large dataset and show that they perform better in a zero-shot scenario.
Multi-Domain Targeted Sentiment Analysis (2022.naacl-main)

Copied to clipboard

Challenge: Targeted Sentiment Analysis (TSA) is a task for generating insights from consumer reviews.
Approach: They propose a multi-domain TSA system that augments a given training set with diverse weak labels from assorted domains and augments it with Yelp reviews.
Outcome: The proposed model outperforms manual methods on three evaluation datasets across different domains and shows that it performs well.
Benchmark Data and Evaluation Framework for Intent Discovery Around COVID-19 Vaccine Hesitancy (2023.findings-eacl)

Copied to clipboard

Challenge: As COVID-19 vaccines were rolled out, they were met with widespread hesitancy.
Approach: They propose a new framework for intent discovery that leverages existing intent classifiers to provide a real-world conversational dataset of conversations conducted by actual users with VIRA.
Outcome: The proposed framework enables users to find out what they are doing and why they are hesitant.
Knowledge Navigator: LLM-guided Browsing Framework for Exploratory Search in Scientific Literature (2024.findings-emnlp)

Copied to clipboard

Challenge: Knowledge Navigator organizes retrieved documents into a navigable, two-level hierarchy of named and descriptive topics and subtopics.
Approach: They propose to organize retrieved scientific documents into a navigable, two-level hierarchy of named and descriptive topics and subtopics.
Outcome: The proposed system provides an overall view of the research themes in a domain while also enabling iterative search and deeper knowledge discovery within specific subtopics.
Where to start? Analyzing the potential value of intermediate models (2023.emnlp-main)

Copied to clipboard

Challenge: a finetuned model may be better base models than the vanilla pretrained model . this scheme, often referred to as intertraining, is the focus of the present work .
Approach: They propose a scheme to analyze the potential intertraining gain independently for the target dataset and for a base model being considered as a starting point.
Outcome: The proposed model is strong even if training data was not aligned with target dataset.
YASO: A Targeted Sentiment Analysis Evaluation Dataset for Open-Domain Reviews (2021.emnlp-main)

Copied to clipboard

Challenge: YASO contains 2,215 English sentences from dozens of review domains, annotated with target terms and their sentiment.
Approach: They propose a new TSA evaluation dataset of open-domain user reviews in English . YASO contains 2,215 English sentences annotated with target terms and their sentiment .
Outcome: The proposed dataset verifies the reliability of the annotations and explores the characteristics of the collected data.
Project Debater APIs: Decomposing the AI Grand Challenge (2021.emnlp-demo)

Copied to clipboard

Challenge: Project Debater is the first AI system that can debate human experts on complex topics.
Approach: They describe Project Debater's architecture and evaluate its performance . they will focus on Key Point Analysis, a novel technology that identifies main points .
Outcome: The proposed system can debate human experts on complex topics.
Active Learning for BERT: An Empirical Study (2020.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to deal with data scarcity are active learning (AL) and pre-trained models are not being considered.
Approach: They propose to use active learning techniques to cope with data scarcity in binary text classification scenarios where the annotation budget is very small and the data is often skewed.
Outcome: The proposed methods improve BERT performance in binary text classification scenarios where the annotation budget is very small and the data is often skewed.

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