Papers by Jonathan Herzig
Finding needles in a haystack: Sampling Structurally-diverse Training Sets from Synthetic Data for Compositional Generalization (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent research shows that automatic generation of synthetic utterance-program pairs can alleviate the first problem, but its potential for the second has thus far been under-explored. |
| Approach: | They propose to generate synthetic utterance-program pairs for improving compositional generalization in semantic parsing by using structurally-diverse examples. |
| Outcome: | The proposed approach leads to dramatic improvements in compositional generalization and moderate improvements in the traditional i.i.d setup. |
Open Domain Question Answering over Tables via Dense Retrieval (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent advances in open-domain QA focus on retrieving textual passages . a retriever designed to handle tabular context can improve retrieval quality . |
| Approach: | They propose a tabular-based retrieval model that improves retrieval quality over a BERT-based retriever. |
| Outcome: | The proposed retriever improves retrieval quality with mined hard negatives over a BERT-based retriever. |
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. |
Don’t paraphrase, detect! Rapid and Effective Data Collection for Semantic Parsing (D19-1)
Copied to clipboard
| Challenge: | a major hurdle on the road to conversational interfaces is the difficulty in collecting data that maps language utterances to logical forms . crowdsourcing and crowdsourcing have been used to generate pseudo-language paired with logical form . however, this data collection method often leads to low performance on real data . |
| Approach: | They propose a method that uses crowdsourcing to map language utterances to logical forms . they quantify the effects of mismatches between the true and induced distributions . |
| Outcome: | The proposed method leads to 70.6 accuracy on the true distribution, compared to 51.3 in paraphrase-based data collection. |
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. |
Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing (D18-1)
Copied to clipboard
| Challenge: | Existing methods for training semantic parsers in new domains require expensive supervision and lack the ability to generalize to new domain. |
| Approach: | They propose a zero-shot approach to parsing utterances in unseen domains . they map an utterant to an abstract, domain independent, logical form and replace slots with KB constants based on lexical alignment scores and global inference . |
| Outcome: | The proposed model achieves 53.4% accuracy on 7 domains in the OVERNIGHT dataset, significantly better than other zero-shot baselines and performs as good as a parser trained on over 30% of the target domain examples. |
Value-based Search in Execution Space for Mapping Instructions to Programs (N19-1)
Copied to clipboard
| Challenge: | Existing methods to map instructions to programs require searching for good programs at training time. |
| Approach: | They propose a search algorithm that uses the target world state to train a critic network that predicts the expected reward of every search state. |
| Outcome: | The proposed algorithm significantly improves on all three domains compared to baselines on the SCONE dataset. |
Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing (2022.emnlp-main)
Copied to clipboard
Linlu Qiu, Peter Shaw, Panupong Pasupat, Tianze Shi, Jonathan Herzig, Emily Pitler, Fei Sha, Kristina Toutanova
| Challenge: | Pre-trained language models struggle on out-of-distribution compositional generalization . recent work shows considerable improvements on many NLP tasks from model scaling . |
| Approach: | They evaluate encoder-decoder models up to 11B parameters and decoder-only models up 540B parameters . they compare scaling curves for fine-tuning, prompt tuning, and in-context learning methods . |
| Outcome: | The proposed scaling methods improve compositional generalization on many tasks . fine-tuning generally has flat or negative scaling curves on out-of-distribution compositional . larger models are better at modeling the syntax of the output space, the study finds . |
TalkSumm: A Dataset and Scalable Annotation Method for Scientific Paper Summarization Based on Conference Talks (P19-1)
Copied to clipboard
| Challenge: | Currently, no large-scale training data is available for the task of scientific paper summarization. |
| Approach: | They propose a method that automatically generates scientific paper summaries by utilizing videos of scientific conferences. |
| Outcome: | The proposed model performs similar to models trained on a dataset of summaries created manually. |
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. |
Improving Compositional Generalization in Semantic Parsing (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Generalization of models to out-of-distribution data has sparked substantial interest . compositional generalization is the ability to systematically generalize to test examples composed of components seen during training . |
| Approach: | They propose to extend compositional generalization in semantic parsing by using contextual representations and training attention to agree with pre-computed token alignments. |
| Outcome: | The proposed extensions improve compositional generalization on OOD compositions. |
Detecting Egregious Conversations between Customers and Virtual Agents (N18-1)
Copied to clipboard
Tommy Sandbank, Michal Shmueli-Scheuer, Jonathan Herzig, David Konopnicki, John Richards, David Piorkowski
| Challenge: | 80% of businesses plan to use chatbots by 2020, according to recent studies . but some bad conversations can be difficult to detect and could lead to litigation . |
| Approach: | They propose a method to detect bad conversations using behavioral cues from the user and patterns in agent responses. |
| Outcome: | The proposed method improves the detection F1 score by 20% over textual features. |
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. |
A Summarization System for Scientific Documents (D19-3)
Copied to clipboard
Shai Erera, Michal Shmueli-Scheuer, Guy Feigenblat, Ora Peled Nakash, Odellia Boni, Haggai Roitman, Doron Cohen, Bar Weiner, Yosi Mass, Or Rivlin, Guy Lev, Achiya Jerbi, Jonathan Herzig, Yufang Hou, Charles Jochim, Martin Gleize, Francesca Bonin, Francesca Bonin, David Konopnicki
| Challenge: | a qualitative user study identified the most valuable scenarios for scientific content consumption. |
| Approach: | They propose a system that retrieves and summarizes scientific documents for a given information need. |
| Outcome: | The proposed system ingested 270,000 scientific papers and validated with human experts. |
Span-based Semantic Parsing for Compositional Generalization (2021.acl-long)
Copied to clipboard
| Challenge: | despite success of sequence-to-sequence models, they fail in compositional generalization . a span-based parser that predicts a utterance over spans improves performance . |
| Approach: | They propose a span-based parser that predicts a utterance over a given span tree . they propose to use CKY to encode how partial programs compose over spans . |
| Outcome: | The proposed model performs better on random splits than baselines that require compositional generalization. |
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. |
Learning To Retrieve Prompts for In-Context Learning (2022.naacl-main)
Copied to clipboard
| Challenge: | In-context learning is a new paradigm in natural language understanding . large pre-trained language models can be expensive to update . |
| Approach: | They propose an efficient method for retrieving training examples as prompts from annotated data and an LM. |
| Outcome: | The proposed method outperforms prior work and multiple baselines on three sequence-to-sequence tasks. |
CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge (N19-1)
Copied to clipboard
| Challenge: | Recent work on question answering relies on factoid questions with little general knowledge. |
| Approach: | They propose a dataset to capture commonsense question answering with prior knowledge . they extract multiple-choice questions that discriminate between the source and target concepts . |
| Outcome: | The proposed dataset captures commonsense reasoning beyond associations . it obtains 56% accuracy, well below human performance, which is 89% . |
TaPas: Weakly Supervised Table Parsing via Pre-training (2020.acl-main)
Copied to clipboard
| Challenge: | Answering natural language questions over tables is often seen as a semantic parsing task. |
| Approach: | They propose an approach to question answering over tables without generating logical forms by selecting table cells and optionally applying a corresponding aggregation operator. |
| Outcome: | The proposed approach outperforms or rivals existing models on three different datasets and performs on par with the state-of-the-art on WikiSQL and WikiTQ. |
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 . |