Papers by Roee Aharoni

22 papers
SEAHORSE: A Multilingual, Multifaceted Dataset for Summarization Evaluation (2023.emnlp-main)

Copied to clipboard

Challenge: evaluating the quality of generated text is a difficult problem for large language models.
Approach: They propose a dataset for multilingual, multifaceted summarization evaluation.
Outcome: The proposed dataset can be used to train multilingual summarization systems . it shows that the dataset performs well on the out-of-domain meta-evaluation benchmarks TRUE and mFACE .
Unsupervised Domain Clusters in Pretrained Language Models (2020.acl-main)

Copied to clipboard

Challenge: Existing methods to select domains from large corpus of data are often over-simplistic and vague.
Approach: They propose to use pre-trained language models to learn sentence representations that cluster by domains without supervision.
Outcome: The proposed methods outperform established methods on domain selection and precision and recall with respect to an oracle selection.
DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering (2023.acl-long)

Copied to clipboard

Challenge: Question answering models have access to two sources of knowledge during inference time: parametric knowledge and contextual knowledge.
Approach: They propose a new paradigm in which QA models are trained to disentangle the two sources of knowledge.
Outcome: The proposed model generates two answers for a given question based on parametric and contextual knowledge.
Multilingual Summarization with Factual Consistency Evaluation (2023.findings-acl)

Copied to clipboard

Challenge: Abstractive summarization models generate factually inconsistent summaries, reducing their utility for real-world applications.
Approach: They propose to use data filtering and controlled generation to detect hallucinations in machine generated summaries.
Outcome: The proposed models detect factual inconsistencies in machine generated summaries, but they focus on English only.
Multilingual Sequence-to-Sequence Models for Hebrew NLP (2023.findings-acl)

Copied to clipboard

Challenge: Recent work on pretrained language models for Hebrew is under-parameterized and under-trained . previous work on pretraining Hebrew LMs focused on encoder-only architectures .
Approach: They propose to use sequence-to-sequence generative architectures to train large LMs in morphologically rich languages such as Hebrew.
Outcome: The proposed model improves on all existing Hebrew NLP benchmarks.
Evaluating and Modeling Attribution for Cross-Lingual Question Answering (2023.emnlp-main)

Copied to clipboard

Challenge: Open-retrieval question answering systems are lacking in attribution for cross-lingual question answering . open-research questions are available in 20 languages, but their raw generation often falls short in factuality .
Approach: They are the first to study attribution for cross-lingual question answering . they collect data in 5 languages to assess the attribution level of a state-of-the-art QA system .
Outcome: The proposed approach improves the attribution level of a state-of-the-art cross-lingual QA system.
Q2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering (2021.emnlp-main)

Copied to clipboard

Challenge: Existing evaluation methods for factual consistency in knowledge-grounded dialogues are unreliable and limit their applicability.
Approach: They propose an automatic evaluation metric for factual consistency in knowledge-grounded dialogue using automatic question generation and question answering.
Outcome: The proposed evaluation metric consistently shows higher correlation with human judgements.
Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback (2023.acl-long)

Copied to clipboard

Challenge: Recent advances in abstractive summarization systems produce factually inconsistent text . this is emphasized in tasks like summarizing, which often produce inconsistent text with no input article .
Approach: They use reinforcement learning to optimize for factual consistency and explore trade-offs . they use textual-entailment rewards to optimize the accuracy of the generated summaries .
Outcome: The proposed method improves faithfulness, salience and conciseness of the generated summaries.
Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words? (2024.emnlp-main)

Copied to clipboard

Challenge: Despite their unprecedented capabilities, large language models (LLMs) often output erroneous information, which may lead users to overly rely on their false output.
Approach: They formalize faithful response uncertainty based on the gap between the model’s intrinsic confidence in the assertions it makes and the decisiveness by which they are conveyed.
Outcome: The proposed model is poor at faithfully conveying uncertainty on knowledge-intensive questions.
Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers (2024.acl-long)

Copied to clipboard

Challenge: Standard question answering evaluation protocols do not take factual errors into account and compare a predicted answer against answers of a single granularity level.
Approach: They propose a new evaluation setting where a predicted answer is evaluated in terms of accuracy and informativeness against a set of multi-granularity answers.
Outcome: The proposed evaluation setting compares a predicted answer against a set of multi-granularity answers.
Split and Rephrase: Better Evaluation and Stronger Baselines (P18-2)

Copied to clipboard

Challenge: a dataset mapping a complex sentence to a sequence of sentences conveying the same meaning is challenging in NLP.
Approach: They propose a neural split and a copy-mechanism to break a complex sentence into several shorter sentences that convey the same meaning.
Outcome: The proposed model outperforms the baseline model by 8.68 BLEU and further improves on the task.
A Comprehensive Evaluation of Tool-Assisted Generation Strategies (2023.findings-emnlp)

Copied to clipboard

Challenge: Various few-shot tool-usage strategies have been proposed to overcome LMs' shortcomings.
Approach: They propose to augment language models with tools to overcome their shortcomings . they find strong no-tool baselines are competitive to tool-assisted strategies .
Outcome: The proposed strategies outperform those that refine incorrect outputs with tools in knowledge-retrieval tasks, the study finds . the findings suggest few-shot tool integration is still an open challenge .
A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains (2024.acl-long)

Copied to clipboard

Challenge: Recent literature discusses automatic methods to evaluate reasoning to improve their correctness, but no fine-grained step-level datasets are available to enable thorough evaluation of such verification methods.
Approach: They propose to benchmark automatic verifiers of complex Chain-of-Thought reasoning in open-domain question-answering settings using a dataset that includes comprehensive labels for relevance, attribution to evidence passages, and logical correctness of each reasoning step.
Outcome: The proposed dataset shows that verifiers struggle at verifying reasoning chains, particularly verifying logical correctness and detecting contradictions.
KoBE: Knowledge-Based Machine Translation Evaluation (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for machine translation evaluation do not require reference translations.
Approach: They propose a method for machine translation evaluation which does not require reference translations.
Outcome: The proposed method achieves highest correlation with human judgements on 9 out of 18 language pairs from the WMT19 benchmark for evaluation without references.
Keep Guessing? When Considering Inference Scaling, Mind the Baselines (2025.findings-naacl)

Copied to clipboard

Challenge: Experiments spanning mathematical reasoning and factual knowledge reveal that repeated sampling improves coverage in large language models.
Approach: They define a baseline that enumerates answers according to their prevalence in the training set and then scale it to measure coverage.
Outcome: The proposed model outperforms repeated model sampling for some LLMs while the coverage for others is on par with that of a mixture strategy that obtains k answers by using only 10 model samples and guessing the remaining k-10 attempts via enumeration.
TRUE: Re-evaluating Factual Consistency Evaluation (2022.naacl-main)

Copied to clipboard

Challenge: Grounded text generation systems often generate factual inconsistencies, hindering their real-world applicability.
Approach: They propose a method to assess factual consistency metrics on standardized texts . they recommend NLI and question generation-and-answering-based methods as starting points .
Outcome: The proposed method is more actionable and interpretable than previous methods.
Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations? (2024.emnlp-main)

Copied to clipboard

Challenge: Pre-training Large Language Models (LLMs) on textual corpora embeds substantial factual knowledge in their parameters, which is essential for excelling in various downstream applications.
Approach: They propose to use supervised fine-tuning to align large language models to new factual information that is not acquired through pre-training.
Outcome: The proposed model is trained to generate facts that are not grounded in pre-existing knowledge, but hallucinates when examples with new knowledge are learned.
q2d: Turning Questions into Dialogs to Teach Models How to Search (2023.emnlp-main)

Copied to clipboard

Challenge: Recent dialog generation models use external search APIs to generate grounded responses.
Approach: They propose an automatic data generation pipeline that generates dialogs from questions . they use a large language model to create conversational versions of question answering datasets .
Outcome: The proposed method improves query generation models on a QReCC dataset.
Localizing Factual Inconsistencies in Attributable Text Generation (2026.tacl-1)

Copied to clipboard

Challenge: Existing methods for detecting hallucinations in model-generated texts fail to pinpoint errors.
Approach: They propose a formalism for localizing factual inconsistencies in attributable text generation . they propose to decompose the generated text into simple question-answer pairs .
Outcome: The proposed method achieves substantial inter-annotator agreement while achieving a substantial consistency score.
Massively Multilingual Neural Machine Translation (N19-1)

Copied to clipboard

Challenge: Multilingual Neural Machine Translation models support translation from multiple source languages into multiple target languages.
Approach: They perform extensive experiments in training massively multilingual NMT models involving up to 103 distinct languages and 204 translation directions simultaneously.
Outcome: The proposed model outperforms the state-of-the-art in low resource settings while supporting up to 59 languages in 116 translation directions.
TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods for evaluating factual consistency are limited in their effectiveness.
Approach: They propose a method for generating synthetic data by annotating diverse model-generated summaries using a LLM.
Outcome: The proposed method outperforms state-of-the-art models and the LLM teacher on TRUE benchmarks.
Multilingual Instruction Tuning With Just a Pinch of Multilinguality (2024.findings-acl)

Copied to clipboard

Challenge: Using multilingual instruction tuning, large language models can be used to follow instructions in multiple languages . a multilingual model can be tuned on a wide range of languages, yet most datasets are limited to English .
Approach: They investigate how multilinguality during instruction tuning affects instruction-following across languages . they find that only 40 multilingual examples improve multilingual instruction- follow .
Outcome: The results show that multilingual models perform better on multilingual mixtures compared to monolingual models . the results suggest that building multilingual instruction-tuned models can be done with only 2-4 languages .

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