Papers by Roee Aharoni
SEAHORSE: A Multilingual, Multifaceted Dataset for Summarization Evaluation (2023.emnlp-main)
Copied to clipboard
Elizabeth Clark, Shruti Rijhwani, Sebastian Gehrmann, Joshua Maynez, Roee Aharoni, Vitaly Nikolaev, Thibault Sellam, Aditya Siddhant, Dipanjan Das, Ankur Parikh
| 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
Benjamin Muller, John Wieting, Jonathan Clark, Tom Kwiatkowski, Sebastian Ruder, Livio Soares, Roee Aharoni, Jonathan Herzig, Xinyi Wang
| 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
Paul Roit, Johan Ferret, Lior Shani, Roee Aharoni, Geoffrey Cideron, Robert Dadashi, Matthieu Geist, Sertan Girgin, Leonard Hussenot, Orgad Keller, Nikola Momchev, Sabela Ramos Garea, Piotr Stanczyk, Nino Vieillard, Olivier Bachem, Gal Elidan, Avinatan Hassidim, Olivier Pietquin, Idan Szpektor
| 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
Alon Jacovi, Yonatan Bitton, Bernd Bohnet, Jonathan Herzig, Or Honovich, Michael Tseng, Michael Collins, Roee Aharoni, Mor Geva
| 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
Or Honovich, Roee Aharoni, Jonathan Herzig, Hagai Taitelbaum, Doron Kukliansy, Vered Cohen, Thomas Scialom, Idan Szpektor, Avinatan Hassidim, Yossi Matias
| 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
Arie Cattan, Paul Roit, Shiyue Zhang, David Wan, Roee Aharoni, Idan Szpektor, Mohit Bansal, Ido Dagan
| 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 . |