Search Results for author: Idan Szpektor

Found 35 papers, 12 papers with code

Q^{2}: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering

no code implementations EMNLP 2021 Or Honovich, Leshem Choshen, Roee Aharoni, Ella Neeman, Idan Szpektor, Omri Abend

Neural knowledge-grounded generative models for dialogue often produce content that is factually inconsistent with the knowledge they rely on, making them unreliable and limiting their applicability.

Abstractive Text Summarization Natural Language Inference +3

Multi-turn Reinforcement Learning from Preference Human Feedback

no code implementations23 May 2024 Lior Shani, Aviv Rosenberg, Asaf Cassel, Oran Lang, Daniele Calandriello, Avital Zipori, Hila Noga, Orgad Keller, Bilal Piot, Idan Szpektor, Avinatan Hassidim, Yossi Matias, Rémi Munos

Reinforcement Learning from Human Feedback (RLHF) has become the standard approach for aligning Large Language Models (LLMs) with human preferences, allowing LLMs to demonstrate remarkable abilities in various tasks.

reinforcement-learning Reinforcement Learning (RL)

Generating Coherent Sequences of Visual Illustrations for Real-World Manual Tasks

no code implementations16 May 2024 João Bordalo, Vasco Ramos, Rodrigo Valério, Diogo Glória-Silva, Yonatan Bitton, Michal Yarom, Idan Szpektor, Joao Magalhaes

In addition, to maintain the visual coherence of the image sequence, we introduce a copy mechanism to initialise reverse diffusion processes with a latent vector iteration from a previously generated image from a relevant step.

TALC: Time-Aligned Captions for Multi-Scene Text-to-Video Generation

no code implementations7 May 2024 Hritik Bansal, Yonatan Bitton, Michal Yarom, Idan Szpektor, Aditya Grover, Kai-Wei Chang

As a result, we show that the pretrained T2V model can generate multi-scene videos that adhere to the multi-scene text descriptions and be visually consistent (e. g., w. r. t entity and background).

Text-to-Video Generation Video Generation

Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs

1 code implementation15 Apr 2024 Adi Simhi, Jonathan Herzig, Idan Szpektor, Yonatan Belinkov

In this work, we first introduce an approach for constructing datasets based on the model knowledge for detection and intervention methods in closed-book and open-book question-answering settings.

Hallucination Language Modelling +1

Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance

no code implementations10 Mar 2024 Omer Goldman, Avi Caciularu, Matan Eyal, Kris Cao, Idan Szpektor, Reut Tsarfaty

Despite it being the cornerstone of BPE, the most common tokenization algorithm, the importance of compression in the tokenization process is still unclear.

Language Modelling Text Compression

Multilingual Instruction Tuning With Just a Pinch of Multilinguality

no code implementations3 Jan 2024 Uri Shaham, Jonathan Herzig, Roee Aharoni, Idan Szpektor, Reut Tsarfaty, Matan Eyal

As instruction-tuned large language models (LLMs) gain global adoption, their ability to follow instructions in multiple languages becomes increasingly crucial.

Cross-Lingual Transfer Instruction Following

Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment

no code implementations5 Dec 2023 Brian Gordon, Yonatan Bitton, Yonatan Shafir, Roopal Garg, Xi Chen, Dani Lischinski, Daniel Cohen-Or, Idan Szpektor

While existing image-text alignment models reach high quality binary assessments, they fall short of pinpointing the exact source of misalignment.

Explanation Generation Visual Grounding

VideoCon: Robust Video-Language Alignment via Contrast Captions

1 code implementation CVPR 2024 Hritik Bansal, Yonatan Bitton, Idan Szpektor, Kai-Wei Chang, Aditya Grover

Despite being (pre)trained on a massive amount of data, state-of-the-art video-language alignment models are not robust to semantically-plausible contrastive changes in the video captions.

Language Modelling Large Language Model +5

Transferring Visual Attributes from Natural Language to Verified Image Generation

no code implementations24 May 2023 Rodrigo Valerio, Joao Bordalo, Michal Yarom, Yonatan Bitton, Idan Szpektor, Joao Magalhaes

In this paper, we propose to strengthen the consistency property of T2I methods in the presence of natural complex language, which often breaks the limits of T2I methods by including non-visual information, and textual elements that require knowledge for accurate generation.

Text-to-Image Generation Visual Question Answering (VQA)

TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models

1 code implementation18 May 2023 Zorik Gekhman, Jonathan Herzig, Roee Aharoni, Chen Elkind, Idan Szpektor

Factual consistency evaluation is often conducted using Natural Language Inference (NLI) models, yet these models exhibit limited success in evaluating summaries.

Natural Language Inference Synthetic Data Generation

What You See is What You Read? Improving Text-Image Alignment Evaluation

1 code implementation NeurIPS 2023 Michal Yarom, Yonatan Bitton, Soravit Changpinyo, Roee Aharoni, Jonathan Herzig, Oran Lang, Eran Ofek, Idan Szpektor

Automatically determining whether a text and a corresponding image are semantically aligned is a significant challenge for vision-language models, with applications in generative text-to-image and image-to-text tasks.

Question Answering Question Generation +5

Multilingual Sequence-to-Sequence Models for Hebrew NLP

no code implementations19 Dec 2022 Matan Eyal, Hila Noga, Roee Aharoni, Idan Szpektor, Reut Tsarfaty

We demonstrate that by casting tasks in the Hebrew NLP pipeline as text-to-text tasks, we can leverage powerful multilingual, pretrained sequence-to-sequence models as mT5, eliminating the need for a specialized, morpheme-based, separately fine-tuned decoder.

Decoder named-entity-recognition +2

DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering

1 code implementation10 Nov 2022 Ella Neeman, Roee Aharoni, Or Honovich, Leshem Choshen, Idan Szpektor, Omri Abend

Question answering models commonly have access to two sources of "knowledge" during inference time: (1) parametric knowledge - the factual knowledge encoded in the model weights, and (2) contextual knowledge - external knowledge (e. g., a Wikipedia passage) given to the model to generate a grounded answer.

counterfactual Data Augmentation +2

MaXM: Towards Multilingual Visual Question Answering

1 code implementation12 Sep 2022 Soravit Changpinyo, Linting Xue, Michal Yarom, Ashish V. Thapliyal, Idan Szpektor, Julien Amelot, Xi Chen, Radu Soricut

In this paper, we propose scalable solutions to multilingual visual question answering (mVQA), on both data and modeling fronts.

Question Answering Translation +1

Dynamic Planning in Open-Ended Dialogue using Reinforcement Learning

no code implementations25 Jul 2022 Deborah Cohen, MoonKyung Ryu, Yinlam Chow, Orgad Keller, Ido Greenberg, Avinatan Hassidim, Michael Fink, Yossi Matias, Idan Szpektor, Craig Boutilier, Gal Elidan

Despite recent advances in natural language understanding and generation, and decades of research on the development of conversational bots, building automated agents that can carry on rich open-ended conversations with humans "in the wild" remains a formidable challenge.

Natural Language Understanding reinforcement-learning +1

On the Robustness of Dialogue History Representation in Conversational Question Answering: A Comprehensive Study and a New Prompt-based Method

1 code implementation29 Jun 2022 Zorik Gekhman, Nadav Oved, Orgad Keller, Idan Szpektor, Roi Reichart

We find that high benchmark scores do not necessarily translate to strong robustness, and that various methods can perform extremely differently under different settings.

Conversational Question Answering

A Dataset for Sentence Retrieval for Open-Ended Dialogues

no code implementations24 May 2022 Itay Harel, Hagai Taitelbaum, Idan Szpektor, Oren Kurland

We report the performance of several retrieval baselines, including neural retrieval models, over the dataset.

Conversational Search Retrieval +2

All You May Need for VQA are Image Captions

2 code implementations NAACL 2022 Soravit Changpinyo, Doron Kukliansky, Idan Szpektor, Xi Chen, Nan Ding, Radu Soricut

Visual Question Answering (VQA) has benefited from increasingly sophisticated models, but has not enjoyed the same level of engagement in terms of data creation.

Image Captioning Question Answering +3

$Q^{2}$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering

1 code implementation16 Apr 2021 Or Honovich, Leshem Choshen, Roee Aharoni, Ella Neeman, Idan Szpektor, Omri Abend

Neural knowledge-grounded generative models for dialogue often produce content that is factually inconsistent with the knowledge they rely on, making them unreliable and limiting their applicability.

Abstractive Text Summarization Dialogue Evaluation +4

What's the best place for an AI conference, Vancouver or ______: Why completing comparative questions is difficult

no code implementations5 Apr 2021 Avishai Zagoury, Einat Minkov, Idan Szpektor, William W. Cohen

Here we study using such LMs to fill in entities in human-authored comparative questions, like ``Which country is older, India or ______?''

World Knowledge

DiscoFuse: A Large-Scale Dataset for Discourse-Based Sentence Fusion

2 code implementations NAACL 2019 Mor Geva, Eric Malmi, Idan Szpektor, Jonathan Berant

We author a set of rules for identifying a diverse set of discourse phenomena in raw text, and decomposing the text into two independent sentences.

Sentence Sentence Fusion +2

The Yahoo Query Treebank, V. 1.0

no code implementations10 May 2016 Yuval Pinter, Roi Reichart, Idan Szpektor

A description and annotation guidelines for the Yahoo Webscope release of Query Treebank, Version 1. 0, May 2016.

Cannot find the paper you are looking for? You can Submit a new open access paper.