Papers by Liat Ein-Dor

12 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.
Efficient Benchmarking (of Language Models) (2024.naacl-long)

Copied to clipboard

Challenge: Efficient Benchmarking is a method for reducing computation costs of LM evaluation without compromising reliability.
Approach: They propose to reduce the computation costs of LM evaluation without compromising reliability by using a new measure - Decision Impact on Reliability.
Outcome: The proposed benchmarks reduce computation costs by x100 or more, while maintaining reliability.
Fine-Grained Detection of Context-Grounded Hallucinations Using LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Existing representations of hallucinations limit the types of errors that can be expressed, so we propose a new representation based on free-form textual descriptions, capturing the full range of possible errors.
Approach: They propose a benchmark for localizing hallucinations using LLMs with a human annotation of over 1,000 examples and a protocol to verify its quality in a humans evaluation.
Outcome: The proposed representation captures the full range of possible errors, and the best model achieves an F1 score of 0.67.
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.
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 Explainability of Preferences (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for generating concept-based explanations of preferences are poorly understood.
Approach: They propose a method for generating local and global concept-based explanations of preferences across multiple domains using an LLM.
Outcome: The proposed method outperforms baselines while also being explainable.
Advances in Debating Technologies: Building AI That Can Debate Humans (2021.acl-tutorials)

Copied to clipboard

Challenge: This tutorial focuses on Debating Technologies, a sub-field of computational argumentation defined as "computational technologies developed directly to enhance, support, and engage with human debating" the tutorial provides a holistic view of a debated system, and discusses practical applications and future challenges of debation technologies.
Approach: They present a tutorial on Debating Technologies, a sub-field of computational argumentation . they introduce Project Debater, which is the first AI system to debate human experts .
Outcome: The project Debater is the first AI system to debate human experts on complex topics.
Active Learning for Natural Language Generation (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to NLG are limited by the lack of annotated data.
Approach: They propose to use active learning to reduce the cost of manual annotation to improve annotation efficiency by selecting the most informative examples to label.
Outcome: The proposed approach surpasses baseline of random example selection in some cases but not in others.
Zero-Shot Text Classification with Self-Training (2022.emnlp-main)

Copied to clipboard

Challenge: Recent advances in large pretrained language models have increased attention to zero-shot text classification.
Approach: They propose a plug-and-play method to bridge this gap by requiring only class names along with an unlabeled dataset.
Outcome: The proposed model can be trained on a natural language inference dataset and performs on dozens of unseen tasks without the need for domain expertise or trial and error.
Label-Efficient Model Selection for Text Generation (2024.acl-long)

Copied to clipboard

Challenge: Model selection for a given task can entail extensive annotation of the quality of outputs of different models.
Approach: They propose a model-agnostic method to make an informed decision between candidate text generation models based on preference annotations.
Outcome: The proposed method reduces the required number of annotations by up to 75% while maintaining high evaluation reliability.
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.
Quality Controlled Paraphrase Generation (2022.acl-long)

Copied to clipboard

Challenge: Recent studies have shown that high quality paraphrases are difficult to generate because of their low flexibility and scalability.
Approach: They propose a quality-guided controlled paraphrase generation model that allows directly controlling the quality dimensions of the generated paraphrase.
Outcome: The proposed method generates paraphrases which maintain original meaning while achieving higher diversity than the uncontrolled baseline.

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