Yichong Xu


2023

pdf
In-Context Demonstration Selection with Cross Entropy Difference
Dan Iter | Reid Pryzant | Ruochen Xu | Shuohang Wang | Yang Liu | Yichong Xu | Chenguang Zhu
Findings of the Association for Computational Linguistics: EMNLP 2023

Large language models (LLMs) can use in-context demonstrations to improve performance on zero-shot tasks. However, selecting the best in-context examples is challenging because model performance can vary widely depending on the selected examples. We present a cross-entropy difference (CED) method for selecting in-context demonstrations. Our method is based on the observation that the effectiveness of in-context demonstrations negatively correlates with the perplexity of the test example by a language model that was finetuned on that demonstration. We utilize parameter efficient finetuning to train small models on training data that are used for computing the cross-entropy difference between a test example and every candidate in-context demonstration. This metric is used to rank and select in-context demonstrations independently for each test input. We evaluate our method on a mix-domain dataset that combines 8 benchmarks, representing 4 text generation tasks, showing that CED for in-context demonstration selection can improve performance for a variety of LLMs over baseline selection methods.

pdf
Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models
Zhihan Zhang | Shuohang Wang | Wenhao Yu | Yichong Xu | Dan Iter | Qingkai Zeng | Yang Liu | Chenguang Zhu | Meng Jiang
Findings of the Association for Computational Linguistics: EMNLP 2023

Large language models (LLMs) can perform a wide range of tasks by following natural language instructions, without the necessity of task-specific fine-tuning. Unfortunately, the performance of LLMs is greatly influenced by the quality of these instructions, and manually writing effective instructions for each task is a laborious and subjective process. In this paper, we introduce Auto-Instruct, a novel method to automatically improve the quality of instructions provided to LLMs. Our method leverages the inherent generative ability of LLMs to produce diverse candidate instructions for a given task, and then ranks them using a scoring model trained on a variety of 575 existing NLP tasks. In experiments on 118 out-of-domain tasks, Auto-Instruct surpasses both human-written instructions and existing baselines of LLM-generated instructions. Furthermore, our method exhibits notable generalizability even with other LLMs that are not incorporated into its training process.

pdf
InheritSumm: A General, Versatile and Compact Summarizer by Distilling from GPT
Yichong Xu | Ruochen Xu | Dan Iter | Yang Liu | Shuohang Wang | Chenguang Zhu | Michael Zeng
Findings of the Association for Computational Linguistics: EMNLP 2023

While large models such as GPT-3 demonstrate exceptional performance in zeroshot and fewshot summarization tasks, their extensive serving and fine-tuning costs hinder their utilization in various applications. Conversely, previous studies have found that although automatic metrics tend to favor smaller fine-tuned models, the quality of the summaries they generate is inferior to that of larger models like GPT-3 when assessed by human evaluators. To address this issue, we propose InheritSumm, a versatile and compact summarization model derived from GPT-3.5 through distillation. InheritSumm not only exhibits comparable zeroshot and fewshot summarization capabilities to GPT-3.5 but is also sufficiently compact for fine-tuning purposes. Experimental results demonstrate that InheritSumm achieves similar or superior performance to GPT-3.5 in zeroshot and fewshot settings. Furthermore, it outperforms the previously established best small models in both prefix-tuning and full-data fine-tuning scenarios.

pdf
LMGQS: A Large-scale Dataset for Query-focused Summarization
Ruochen Xu | Song Wang | Yang Liu | Shuohang Wang | Yichong Xu | Dan Iter | Pengcheng He | Chenguang Zhu | Michael Zeng
Findings of the Association for Computational Linguistics: EMNLP 2023

Query-focused summarization (QFS) aims to extract or generate a summary of an input document that directly answers or is relevant to a given query. The lack of large-scale datasets in the form of documents, queries, and summaries has hindered model development in this area. In contrast, multiple large-scale high-quality datasets for generic summarization exist. We hypothesize that there is a hidden query for each summary sentence in a generic summarization annotation, and we utilize a large-scale pretrained language model to recover it. In this way, we convert four generic summarization benchmarks into a new QFS benchmark dataset, LMGQS, which consists of over 1 million document-query-summary samples. We thoroughly investigate the properties of our proposed dataset and establish baselines with state-of-the-art summarization models. By fine-tuning a language model on LMGQS, we achieve state-of-the-art zero-shot and supervised performance on multiple existing QFS benchmarks, demonstrating the high quality and diversity of LMGQS.

pdf
G-Eval: NLG Evaluation using Gpt-4 with Better Human Alignment
Yang Liu | Dan Iter | Yichong Xu | Shuohang Wang | Ruochen Xu | Chenguang Zhu
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

The quality of texts generated by natural language generation (NLG) systems is hard to measure automatically. Conventional reference-based metrics, such as BLEU and ROUGE, have been shown to have relatively low correlation with human judgments, especially for tasks that require creativity and diversity. Recent studies suggest using large language models (LLMs) as reference-free metrics for NLG evaluation, which have the benefit of being applicable to new tasks that lack human references. However, these LLM-based evaluators still have lower human correspondence than medium-size neural evaluators. In this work, we present G-Eval, a framework of using large language models with chain-of-thoughts (CoT) and a form-filling paradigm, to assess the quality of NLG outputs. We experiment with two generation tasks, text summarization and dialogue generation. We show that G-Eval with GPT-4 as the backbone model achieves a Spearman correlation of 0.514 with human on summarization task, outperforming all previous methods by a large margin. We also propose analysis on the behavior of LLM-based evaluators, and highlight the potential concern of LLM-based evaluators having a bias towards the LLM-generated texts.

pdf
APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning
Soumya Sanyal | Yichong Xu | Shuohang Wang | Ziyi Yang | Reid Pryzant | Wenhao Yu | Chenguang Zhu | Xiang Ren
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Logical reasoning over text is an important ability that requires understanding the semantics of the text and reasoning through them to arrive at correct inferences. Prior works on pretraining language models to improve the logical reasoning ability require complex processing of training data (e.g., aligning symbolic knowledge to text), yielding task-specific data augmentation that is not easy to adapt to any general text corpus. In this work, we propose APOLLO, a simple adaptive pretraining approach to improve the logical reasoning skills of language models. We select a subset of Wikipedia for adaptive pretraining using a set of logical inference keywords as filter words. Further, we propose two self-supervised loss functions for training. First, we modify the masked language modeling loss only to mask specific parts-of-speech words that likely require higher-order reasoning to predict them. Second, we propose a sentence-level classification loss that teaches the model to distinguish between entailment and contradiction types of sentences. The proposed pretraining paradigm is both simple and independent of task formats. We demonstrate the effectiveness of APOLLO by comparing it with prior baselines on two logical reasoning datasets. APOLLO performs comparably on ReClor and outperforms baselines on LogiQA.

pdf
MVP-Tuning: Multi-View Knowledge Retrieval with Prompt Tuning for Commonsense Reasoning
Yongfeng Huang | Yanyang Li | Yichong Xu | Lin Zhang | Ruyi Gan | Jiaxing Zhang | Liwei Wang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Recent advances in pre-trained language models (PLMs) have facilitated the development ofcommonsense reasoning tasks. However, existing methods rely on multi-hop knowledgeretrieval and thus suffer low accuracy due toembedded noise in the acquired knowledge. In addition, these methods often attain highcomputational costs and nontrivial knowledgeloss because they encode the knowledge independently of the PLM, making it less relevant to the task and thus resulting in a poorlocal optimum. In this work, we propose MultiView Knowledge Retrieval with Prompt Tuning (MVP-Tuning). MVP-Tuning leveragessimilar question-answer pairs in the training setto improve knowledge retrieval and employsa single prompt-tuned PLM to model knowledge and input text jointly. We conduct our experiments on five commonsense reasoning QAbenchmarks to show that MVP-Tuning outperforms all other baselines in 4 out of 5 datasetswith less than 2% trainable parameters. MVPTuning even gets a new state-of-the-art resulton OpenBookQA and is number one on theleaderboard.

2022

pdf
Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Data
Shuohang Wang | Yichong Xu | Yuwei Fang | Yang Liu | Siqi Sun | Ruochen Xu | Chenguang Zhu | Michael Zeng
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Retrieval-based methods have been shown to be effective in NLP tasks via introducing external knowledge. However, the indexing and retrieving of large-scale corpora bring considerable computational cost. Surprisingly, we found that REtrieving from the traINing datA (REINA) only can lead to significant gains on multiple NLG and NLU tasks. We retrieve the labeled training instances most similar to the input text and then concatenate them with the input to feed into the model to generate the output. Experimental results show that this simple method can achieve significantly better performance on a variety of NLU and NLG tasks, including summarization, machine translation, language modeling, and question answering tasks. For instance, our proposed method achieved state-of-the-art results on XSum, BigPatent, and CommonsenseQA. Our code is released, https://github.com/microsoft/REINA .

pdf
KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering
Donghan Yu | Chenguang Zhu | Yuwei Fang | Wenhao Yu | Shuohang Wang | Yichong Xu | Xiang Ren | Yiming Yang | Michael Zeng
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Current Open-Domain Question Answering (ODQA) models typically include a retrieving module and a reading module, where the retriever selects potentially relevant passages from open-source documents for a given question, and the reader produces an answer based on the retrieved passages. The recently proposed Fusion-in-Decoder (FiD) framework is a representative example, which is built on top of a dense passage retriever and a generative reader, achieving the state-of-the-art performance. In this paper we further improve the FiD approach by introducing a knowledge-enhanced version, namely KG-FiD. Our new model uses a knowledge graph to establish the structural relationship among the retrieved passages, and a graph neural network (GNN) to re-rank the passages and select only a top few for further processing. Our experiments on common ODQA benchmark datasets (Natural Questions and TriviaQA) demonstrate that KG-FiD can achieve comparable or better performance in answer prediction than FiD, with less than 40% of the computation cost.

pdf
Knowledge-Augmented Methods for Natural Language Processing
Chenguang Zhu | Yichong Xu | Xiang Ren | Bill Yuchen Lin | Meng Jiang | Wenhao Yu
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts

Knowledge in natural language processing (NLP) has been a rising trend especially after the advent of large scale pre-trained models. NLP models with attention to knowledge can i) access unlimited amount of external information; ii) delegate the task of storing knowledge from its parameter space to knowledge sources; iii) obtain up-to-date information; iv) make prediction results more explainable via selected knowledge. In this tutorial, we will introduce the key steps in integrating knowledge into NLP, including knowledge grounding from text, knowledge representation and fusing. In addition, we will introduce recent state-of-the-art applications in fusing knowledge into language understanding, language generation and commonsense reasoning.

pdf
Dict-BERT: Enhancing Language Model Pre-training with Dictionary
Wenhao Yu | Chenguang Zhu | Yuwei Fang | Donghan Yu | Shuohang Wang | Yichong Xu | Michael Zeng | Meng Jiang
Findings of the Association for Computational Linguistics: ACL 2022

Pre-trained language models (PLMs) aim to learn universal language representations by conducting self-supervised training tasks on large-scale corpora. Since PLMs capture word semantics in different contexts, the quality of word representations highly depends on word frequency, which usually follows a heavy-tailed distributions in the pre-training corpus. Therefore, the embeddings of rare words on the tail are usually poorly optimized. In this work, we focus on enhancing language model pre-training by leveraging definitions of the rare words in dictionaries (e.g., Wiktionary). To incorporate a rare word definition as a part of input, we fetch its definition from the dictionary and append it to the end of the input text sequence. In addition to training with the masked language modeling objective, we propose two novel self-supervised pre-training tasks on word and sentence-level alignment between input text sequence and rare word definitions to enhance language modeling representation with dictionary. We evaluate the proposed Dict-BERT model on the language understanding benchmark GLUE and eight specialized domain benchmark datasets. Extensive experiments demonstrate that Dict-BERT can significantly improve the understanding of rare words and boost model performance on various NLP downstream tasks.

pdf
Leveraging Knowledge in Multilingual Commonsense Reasoning
Yuwei Fang | Shuohang Wang | Yichong Xu | Ruochen Xu | Siqi Sun | Chenguang Zhu | Michael Zeng
Findings of the Association for Computational Linguistics: ACL 2022

Commonsense reasoning (CSR) requires models to be equipped with general world knowledge. While CSR is a language-agnostic process, most comprehensive knowledge sources are restricted to a small number of languages, especially English. Thus, it remains unclear how to effectively conduct multilingual commonsense reasoning (XCSR) for various languages. In this work, we propose to use English as a pivot language, utilizing English knowledge sources for our our commonsense reasoning framework via a translate-retrieve-translate (TRT) strategy. For multilingual commonsense questions and answer candidates, we collect related knowledge via translation and retrieval from the knowledge in the source language. The retrieved knowledge is then translated into the target language and integrated into a pre-trained multilingual language model via visible knowledge attention. Then we utilize a diverse of four English knowledge sources to provide more comprehensive coverage of knowledge in different formats. Extensive results on the XCSR benchmark demonstrate that TRT with external knowledge can significantly improve multilingual commonsense reasoning in both zero-shot and translate-train settings, consistently outperforming the state-of-the-art by more than 3% on the multilingual commonsense reasoning benchmark X-CSQA and X-CODAH.

pdf
Automatic Rule Induction for Efficient Semi-Supervised Learning
Reid Pryzant | Ziyi Yang | Yichong Xu | Chenguang Zhu | Michael Zeng
Findings of the Association for Computational Linguistics: EMNLP 2022

Semi-supervised learning has shown promise in allowing NLP models to generalize from small amounts of labeled data. Meanwhile, pretrained transformer models act as black-box correlation engines that are difficult to explain and sometimes behave unreliably. In this paper, we propose tackling both of these challenges via Automatic Rule Induction (ARI), a simple and general-purpose framework for the automatic discovery and integration of symbolic rules into pretrained transformer models. First, we extract weak symbolic rules from low-capacity machine learning models trained on small amounts of labeled data. Next, we use an attention mechanism to integrate these rules into high-capacity pretrained transformer models. Last, the rule-augmented system becomes part of a self-training framework to boost supervision signal on unlabeled data. These steps can be layered beneath a variety of existing weak supervision and semi-supervised NLP algorithms in order to improve performance and interpretability. Experiments across nine sequence classification and relation extraction tasks suggest that ARI can improve state-of-the-art methods with no manual effort and minimal computational overhead.

pdf
Unsupervised Multi-Granularity Summarization
Ming Zhong | Yang Liu | Suyu Ge | Yuning Mao | Yizhu Jiao | Xingxing Zhang | Yichong Xu | Chenguang Zhu | Michael Zeng | Jiawei Han
Findings of the Association for Computational Linguistics: EMNLP 2022

Text summarization is a user-preference based task, i.e., for one document, users often have different priorities for the summary. As a key aspect of customization in summarization, granularity is used to measure the semantic coverage between the summary and source document. However, developing systems that can generate summaries with customizable semantic coverage is still an under-explored topic. In this paper, we propose the first unsupervised multi-granularity summarization framework, GranuSum. We take events as the basic semantic units of the source documents and propose to rank these events by their salience. We also develop a model to summarize input documents with given events as anchors and hints. By inputting different numbers of events, GranuSum is capable of producing multi-granular summaries in an unsupervised manner. Meanwhile, we annotate a new benchmark GranuDUC that contains multiple summaries at different granularities for each document cluster. Experimental results confirm the substantial superiority of GranuSum on multi-granularity summarization over strong baselines. Furthermore, by exploiting the event information, GranuSum also exhibits state-of-the-art performance under the conventional unsupervised abstractive setting.

pdf
Task Compass: Scaling Multi-task Pre-training with Task Prefix
Zhuosheng Zhang | Shuohang Wang | Yichong Xu | Yuwei Fang | Wenhao Yu | Yang Liu | Hai Zhao | Chenguang Zhu | Michael Zeng
Findings of the Association for Computational Linguistics: EMNLP 2022

Leveraging task-aware annotated data as supervised signals to assist with self-supervised learning on large-scale unlabeled data has become a new trend in pre-training language models. Existing studies show that multi-task learning with large-scale supervised tasks suffers from negative effects across tasks. To tackle the challenge, we propose a task prefix guided multi-task pre-training framework to explore the relationships among tasks. We conduct extensive experiments on 40 datasets, which show that our model can not only serve as the strong foundation backbone for a wide range of tasks but also be feasible as a probing tool for analyzing task relationships. The task relationships reflected by the prefixes align transfer learning performance between tasks. They also suggest directions for data augmentation with complementary tasks, which help our model achieve human-parity results on commonsense reasoning leaderboards. Code is available at https://github.com/cooelf/CompassMTL.

pdf
Empowering Language Models with Knowledge Graph Reasoning for Open-Domain Question Answering
Ziniu Hu | Yichong Xu | Wenhao Yu | Shuohang Wang | Ziyi Yang | Chenguang Zhu | Kai-Wei Chang | Yizhou Sun
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Answering open-domain questions requires world knowledge about in-context entities. As pre-trained Language Models (LMs) lack the power to store all required knowledge, external knowledge sources, such as knowledge graphs, are often used to augment LMs. In this work, we propose knOwledge REasOning empowered Language Model(OREO-LM), which consists of a novel Knowledge Interaction Layer that can be flexibly plugged into existing Transformer-based LMs to interact with a differentiable Knowledge Graph Reasoning module collaboratively. In this way, LM guides KG to walk towards the desired answer, while the retrieved knowledge improves LM.By adopting OREO-LM to RoBERTa and T5, we show significant performance gain, achieving state-of-art results in the Closed-Book setting. The performance enhancement is mainly from the KG reasoning’s capacity to infer missing relational facts. In addition, OREO-LM provides reasoning paths as rationales to interpret the model’s decision.

2021

pdf
Fusing Context Into Knowledge Graph for Commonsense Question Answering
Yichong Xu | Chenguang Zhu | Ruochen Xu | Yang Liu | Michael Zeng | Xuedong Huang
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf
Retrieval Enhanced Model for Commonsense Generation
Han Wang | Yang Liu | Chenguang Zhu | Linjun Shou | Ming Gong | Yichong Xu | Michael Zeng
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf
Want To Reduce Labeling Cost? GPT-3 Can Help
Shuohang Wang | Yang Liu | Yichong Xu | Chenguang Zhu | Michael Zeng
Findings of the Association for Computational Linguistics: EMNLP 2021

Data annotation is a time-consuming and labor-intensive process for many NLP tasks. Although there exist various methods to produce pseudo data labels, they are often task-specific and require a decent amount of labeled data to start with. Recently, the immense language model GPT-3 with 170 billion parameters has achieved tremendous improvement across many few-shot learning tasks. In this paper, we explore ways to leverage GPT-3 as a low-cost data labeler to train other models. We find that to make the downstream model achieve the same performance on a variety of NLU and NLG tasks, it costs 50% to 96% less to use labels from GPT-3 than using labels from humans. Furthermore, we propose a novel framework of combining pseudo labels from GPT-3 with human labels, which leads to even better performance. These results present a cost-effective data labeling methodology that is generalizable to many practical applications.

2019

pdf
DoubleTransfer at MEDIQA 2019: Multi-Source Transfer Learning for Natural Language Understanding in the Medical Domain
Yichong Xu | Xiaodong Liu | Chunyuan Li | Hoifung Poon | Jianfeng Gao
Proceedings of the 18th BioNLP Workshop and Shared Task

This paper describes our competing system to enter the MEDIQA-2019 competition. We use a multi-source transfer learning approach to transfer the knowledge from MT-DNN and SciBERT to natural language understanding tasks in the medical domain. For transfer learning fine-tuning, we use multi-task learning on NLI, RQE and QA tasks on general and medical domains to improve performance. The proposed methods are proved effective for natural language understanding in the medical domain, and we rank the first place on the QA task.

pdf
Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension
Yichong Xu | Xiaodong Liu | Yelong Shen | Jingjing Liu | Jianfeng Gao
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

We propose a multi-task learning framework to learn a joint Machine Reading Comprehension (MRC) model that can be applied to a wide range of MRC tasks in different domains. Inspired by recent ideas of data selection in machine translation, we develop a novel sample re-weighting scheme to assign sample-specific weights to the loss. Empirical study shows that our approach can be applied to many existing MRC models. Combined with contextual representations from pre-trained language models (such as ELMo), we achieve new state-of-the-art results on a set of MRC benchmark datasets. We release our code at https://github.com/xycforgithub/MultiTask-MRC.