Papers by Yizhong Wang
Synthetic Data in the Era of Large Language Models (2025.acl-tutorials)
Copied to clipboard
| Challenge: | 'synthetic data' is a data generated with the assistance of large language models to make dataset construction faster and cheaper. |
| Approach: | This tutorial seeks to build a shared understanding of recent progress in synthetic data generation from NLP and related fields by grouping and describing major methods, applications, and open problems. |
| Outcome: | This tutorial will describe methods, applications, and open problems that have been developed and are being used to improve the quality and efficiency of synthetic data generation. |
Evaluating Language Models as Synthetic Data Generators (2025.acl-long)
Copied to clipboard
Seungone Kim, Juyoung Suk, Xiang Yue, Vijay Viswanathan, Seongyun Lee, Yizhong Wang, Kiril Gashteovski, Carolin Lawrence, Sean Welleck, Graham Neubig
| Challenge: | Prior studies have focused on developing effective data generation methods, but lack systematic comparison of different LMs as data generators in a unified setting. |
| Approach: | They propose to use a benchmark to compare language models' data generation abilities against a set of standardized settings and metrics. |
| Outcome: | The proposed benchmark provides standardized settings and metrics to evaluate LMs’ data generation abilities. |
Do NLP Models Know Numbers? Probing Numeracy in Embeddings (D19-1)
Copied to clipboard
| Challenge: | Existing models cannot capture numeracy, but they can be useful for complex reasoning tasks. |
| Approach: | They investigate numerical reasoning capabilities of a question-answering model . they probe token embedding methods on synthetic list maximum, number decoding, and addition tasks. |
| Outcome: | The proposed model excels on questions that require numerical reasoning, i.e., it already captures numeracy. |
Probing Across Time: What Does RoBERTa Know and When? (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Current approaches to natural language processing rely on fixed artifacts such as language models . current studies have focused on how these models acquire and demonstrate knowledge . |
| Approach: | They apply probing techniques to examine how language models acquire knowledge . they aim to inform future work on more efficient pretraining and understanding dependencies . |
| Outcome: | The proposed model learns linguistic abstractions, factual and commonsense knowledge, and reasoning abilities fast, stably, and robustly across domains. |
HINT: Hypernetwork Instruction Tuning for Efficient Zero- and Few-Shot Generalisation (2023.acl-long)
Copied to clipboard
| Challenge: | Recent NLP models have shown the remarkable ability to generalise ‘zero-shot’ to new tasks using only natural language instructions as guidance. |
| Approach: | They introduce Hypernetworks for INstruction Tuning (HINT) which converts task instructions and examples into parameter-efficient modules inserted into an underlying model using a pretrained text encoder. |
| Outcome: | The proposed models outperform strong state-of-the-art models by over 10% when controlling for compute. |
Packing Analysis: Packing Is More Appropriate for Large Models or Datasets in Supervised Fine-tuning (2025.findings-acl)
Copied to clipboard
| Challenge: | Packing is an optimization technique that optimizes training time and resources by combining different training sequences to fit the model’s maximum input length. |
| Approach: | They perform extensive comparisons between packing and padding methods, covering datasets ranging from 69K to 1.2M and models from 8B to 70B. |
| Outcome: | The proposed method has been shown to improve training efficiency while maintaining performance. |
Self-Instruct: Aligning Language Models with Self-Generated Instructions (2023.acl-long)
Copied to clipboard
Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A. Smith, Daniel Khashabi, Hannaneh Hajishirzi
| Challenge: | Large “instruction-tuned” language models depend heavily on human-written instruction data . this limited quantity, diversity, and creativity hinders the generality of the tuned model . |
| Approach: | They propose a framework for improving instruction-following capabilities of pretrained language models by bootstrapping off their own generations. |
| Outcome: | The proposed framework outperforms existing public instruction datasets by 5% . it generates instructions, input, and output samples, then filters invalid or similar ones . |
PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization (2025.emnlp-main)
Copied to clipboard
Ruoxi Cheng, Yizhong Ding, Shuirong Cao, Ranjie Duan, Xiaoshuang Jia, Shaowei Yuan, Simeng Qin, Zhiqiang Wang, Xiaojun Jia
| Challenge: | Existing methods to jailbreak Large Vision Language Models do not consider interaction between images and text. |
| Approach: | They propose a prior-guided bimodal interactive black-box jailbreak attack for toxicity maximization that exploits the interaction of images and text. |
| Outcome: | The proposed method outperforms state-of-the-art jailbreak methods in black box scenarios and in closed-source LVLMs. |
TurkingBench: A Challenge Benchmark for Web Agents (2025.naacl-long)
Copied to clipboard
Kevin Xu, Yeganeh Kordi, Tanay Nayak, Adi Asija, Yizhong Wang, Kate Sanders, Adam Byerly, Jingyu Zhang, Benjamin Van Durme, Daniel Khashabi
| Challenge: | TurkingBench is a benchmark consisting of tasks presented as web pages with textual instructions and multi-modal contexts. |
| Approach: | They propose to use HTML pages to perform various annotation tasks on crowdsourcing platforms. |
| Outcome: | The proposed model outperforms other models on the TurkingBench benchmark. |
Set the Clock: Temporal Alignment of Pretrained Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Language models (LMs) are trained on web text originating from many points in time and, in general, without any explicit temporal grounding. |
| Approach: | They construct a time-sensitive question dataset and use it to examine temporal alignment methods to align their internal knowledge to a target time. |
| Outcome: | The proposed methods improve LLaMa2's performance by 62% if they are fine tuned to the year 2022 . |
One Embedder, Any Task: Instruction-Finetuned Text Embeddings (2023.findings-acl)
Copied to clipboard
Hongjin Su, Weijia Shi, Jungo Kasai, Yizhong Wang, Yushi Hu, Mari Ostendorf, Wen-tau Yih, Noah A. Smith, Luke Zettlemoyer, Tao Yu
| Challenge: | a new method for embedding text is developed for tasks that require specialized encoders . INSTRUCTOR is a single embedder that can generate text embeddables tailored to different tasks and domains based on instruction finetuning . |
| Approach: | They introduce a new method for computing text embeddings given task instructions . they first annotate instructions for 330 diverse tasks and train INSTRUCTOR on this multitask mixture . |
| Outcome: | The proposed method improves on 70 embedding evaluation tasks with fewer parameters than the previous best model. |
Toward Fast and Accurate Neural Discourse Segmentation (D18-1)
Copied to clipboard
| Challenge: | Existing discourse segmenters rely on complicated hand-crafted features and are not practical in actual use. |
| Approach: | They propose an end-to-end neural segmenter based on BiLSTM-CRF framework that can segment texts fast and accurately using a large corpus. |
| Outcome: | The proposed model is significantly faster than previous methods while achieving state-of-the-art performance on the RST-DT corpus. |
Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks (2022.emnlp-main)
Copied to clipboard
Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Yeganeh Kordi, Amirreza Mirzaei, Atharva Naik, Arjun Ashok, Arut Selvan Dhanasekaran, Anjana Arunkumar, David Stap, Eshaan Pathak, Giannis Karamanolakis, Haizhi Lai, Ishan Purohit, Ishani Mondal, Jacob Anderson, Kirby Kuznia, Krima Doshi, Kuntal Kumar Pal, Maitreya Patel, Mehrad Moradshahi, Mihir Parmar, Mirali Purohit, Neeraj Varshney, Phani Rohitha Kaza, Pulkit Verma, Ravsehaj Singh Puri, Rushang Karia, Savan Doshi, Shailaja Keyur Sampat, Siddhartha Mishra, Sujan Reddy A, Sumanta Patro, Tanay Dixit, Xudong Shen
| Challenge: | a benchmark of 1,616 diverse NLP tasks and their expert-written instructions is used to test generalization of models to unseen tasks . a recent study shows that instruction-following models outperform instruction-based models by over 9% . |
| Approach: | They build a benchmark of 1,616 diverse NLP tasks and their expert-written instructions. |
| Outcome: | The proposed model outperforms existing instruction-following models by over 9% on the benchmark despite being smaller. |
Bag-of-Words as Target for Neural Machine Translation (P18-2)
Copied to clipboard
| Challenge: | Existing neural machine translation models only use one correct sentence as the target, and the other correct sentences are punished as the incorrect ones. |
| Approach: | They propose an approach that uses both the sentences and the bag-of-words as targets in the training stage to encourage the model to generate the potentially correct sentences that are not appeared in the train set. |
| Outcome: | The proposed model outperforms baseline models on a Chinese-English translation dataset by the BLEU score of 4.55. |
Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification (P18-1)
Copied to clipboard
| Challenge: | Recent years have seen rapid growth in the MRC community . MRC is believed to be a crucial step in building a general intelligent agent . |
| Approach: | They propose an end-to-end neural model that enables multiple passages to verify each other based on their content representations. |
| Outcome: | The proposed model outperforms the baseline on the English MS-MARCO dataset and the Chinese DuReader dataset, and achieves state-of-the-art performance on both datasets. |
Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback (2025.acl-long)
Copied to clipboard
Lester James Validad Miranda, Yizhong Wang, Yanai Elazar, Sachin Kumar, Valentina Pyatkin, Faeze Brahman, Noah A. Smith, Hannaneh Hajishirzi, Pradeep Dasigi
| Challenge: | Learning from human feedback has enabled the alignment of language models (LMs) with human preferences. |
| Approach: | They propose a Hybrid Preference routER that defers an annotation to either humans or LMs, achieving better annotation quality while reducing the cost of human-only annotation. |
| Outcome: | The proposed model achieves better annotation quality while reducing the cost of human-only annotation. |
Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics (2020.emnlp-main)
Copied to clipboard
Swabha Swayamdipta, Roy Schwartz, Nicholas Lourie, Yizhong Wang, Hannaneh Hajishirzi, Noah A. Smith, Yejin Choi
| Challenge: | Large datasets have become commonplace in NLP research, but the emphasis on quantity has made it challenging to assess the quality of data. |
| Approach: | They propose a model-based tool to characterize and diagnose large datasets . they leverage the behavior of the model on individual instances during training . |
| Outcome: | Experiments on four datasets show that the tool can characterize and diagnose datasets with a model-based tool. |
Language Models over Large-Scale Knowledge Base: on Capacity, Flexibility and Reasoning for New Facts (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies on LMs lack systematic studies on their structured reasoning capabilities over the infused knowledge. |
| Approach: | They investigate how LMs of different sizes can store world knowledge of different frequencies in a large-scale KB after training on the abundant world knowledge triplets. |
| Outcome: | The proposed models can store and respond to natural language queries with flexibility and reasoning abilities, but they need to be enhanced to fully realize their potential. |
DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs (N19-1)
Copied to clipboard
| Challenge: | a large body of work has highlighted the brittleness of reading comprehension systems . a crowdsourced, adversarially-created, 55k-question benchmark requires a more comprehensive understanding of paragraphs . |
| Approach: | They propose a reading comprehension benchmark that requires Discrete Reasoning over the content of paragraphs. |
| Outcome: | The proposed benchmarks show that the best systems only achieve 38.4% F1 on the generalized accuracy metric, while human performance is 96%. |