Evaluation of text generation to date has primarily focused on content created sequentially, rather than improvements on a piece of text. Writing, however, is naturally an iterative and incremental process that requires expertise in different modular skills such as fixing outdated information or making the writing style more consistent. Even so, comprehensive evaluation of a model’s capacity to perform these skills and the ability to edit remains sparse. This work introduces EditEval: An instruction-based, benchmark and evaluation suite that leverages high-quality existing and new datasets in English for the automatic evaluation of editing capabilities, such as making text more cohesive and paraphrasing. We evaluate several pre-trained models, which shows that InstructGPT and PEER on average perform the best, but that most baselines fall below the supervised state-of-the-art, particularly when neutralizing and updating information. Our analysis also shows that commonly used metrics for editing tasks do not always correlate well, and that prompts leading to the strongest performance do not necessarily elicit strong performance across different models. Through the release of this benchmark (code and data available at https://github.com/facebookresearch/EditEval) and a publicly available leaderboard challenge, we hope to unlock future work on developing models more capable of controllable and iterative editing.

Generative Artificial Intelligence (AI) has enabled the development of sophisticated models that are capable of producing high-caliber text, images, and other outputs through the utilization of large pre-trained models.Nevertheless, assessing the quality of the generation is an even more arduous task than the generation itself, and this issue has not been given adequate consideration recently.This paper proposes a novel evaluation framework, GPTScore, which utilizes the emergent abilities (e.g., in-context learning, zero-shot instruction) of generative pre-trained models to score generated texts. There are 19 pre-trained models explored in this paper, ranging in size from 80M (e.g., Flan-T5-small) to 175B (e.g., GPT3).Experimental results on four text generation tasks, 22 evaluation aspects, and corresponding 37 datasets demonstrate that this approach can effectively allow us to achieve what one desires to evaluate for texts simply by natural language instructions.This nature helps us overcome several long-standing challenges in text evaluation–how to achieve customized, multi-faceted evaluation without model training. We make our code publicly available.

Recent developments in Language Models (LMs) have shown their effectiveness in NLP tasks, particularly in knowledge-intensive tasks.However, the mechanisms underlying knowledge storage and memory access within their parameters remain elusive. In this paper, we investigate whether a generative LM (e.g., GPT-2) is able to access its memory sequentially or randomly. Through carefully-designed synthetic tasks, covering the scenarios of full recitation, selective recitation and grounded question answering, we reveal that LMs manage to sequentially access their memory while encountering challenges in randomly accessing memorized content. We find that techniques including recitation and permutation improve the random memory access capability of LMs. Furthermore, by applying this intervention to realistic scenarios of open-domain question answering, we validate that enhancing random access by recitation leads to notable improvements in question answering. The code to reproduce our experiments can be found at https://github.com/sail-sg/lm-random-memory-access.

In order for large language model (LLM)-based assistants to effectively adapt to evolving information needs, it must be possible to update their factual knowledge through continued training on new data. The standard recipe for doing so involves continued pre-training on new documents followed by instruction-tuning on question-answer (QA) pairs. However, we find that LLMs trained with this recipe struggle to answer questions, even though the perplexity of documents is minimized. We found that QA pairs are generally straightforward, while documents are more complex, weaving many factual statements together in an intricate manner. Therefore, we hypothesize that it is beneficial to expose LLMs to QA pairs before continued pre-training on documents so that the process of encoding knowledge from complex documents takes into account how this knowledge is accessed through questions. Based on this, we propose pre-instruction-tuning (PIT), a method that instruction-tunes on questions prior to training on documents. This contrasts with standard instruction-tuning, which learns how to extract knowledge after training on documents. Extensive experiments and ablation studies demonstrate that pre-instruction-tuning significantly enhances the ability of LLMs to absorb knowledge from new documents, outperforming standard instruction-tuning by 17.8%.

Despite the remarkable ability of large language models (LMs) to comprehend and generate language, they have a tendency to hallucinate and create factually inaccurate output. Augmenting LMs by retrieving information from external knowledge resources is one promising solution. Most existing retrieval augmented LMs employ a retrieve-and-generate setup that only retrieves information once based on the input. This is limiting, however, in more general scenarios involving generation of long texts, where continually gathering information throughout generation is essential. In this work, we provide a generalized view of active retrieval augmented generation, methods that actively decide when and what to retrieve across the course of the generation. We propose Forward-Looking Active REtrieval augmented generation (FLARE), a generic method which iteratively uses a prediction of the upcoming sentence to anticipate future content, which is then utilized as a query to retrieve relevant documents to regenerate the sentence if it contains low-confidence tokens. We test FLARE along with baselines comprehensively over 4 long-form knowledge-intensive generation tasks/datasets. FLARE achieves superior or competitive performance on all tasks, demonstrating the effectiveness of our method.

The information in tables can be an important complement to text, making table-based question answering (QA) systems of great value. The intrinsic complexity of handling tables often adds an extra burden to both model design and data annotation. In this paper, we aim to develop a simple table-based QA model with minimal annotation effort. Motivated by the fact that table-based QA requires both alignment between questions and tables and the ability to perform complicated reasoning over multiple table elements, we propose an omnivorous pretraining approach that consumes both natural and synthetic data to endow models with these respective abilities. Specifically, given freely available tables, we leverage retrieval to pair them with relevant natural sentences for mask-based pretraining, and synthesize NL questions by converting SQL sampled from tables for pretraining with a QA loss. We perform extensive experiments in both few-shot and full settings, and the results clearly demonstrate the superiority of our model OmniTab, with the best multitasking approach achieving an absolute gain of 16.2% and 2.7% in 128-shot and full settings respectively, also establishing a new state-of-the-art on WikiTableQuestions. Detailed ablations and analyses reveal different characteristics of natural and synthetic data, shedding light on future directions in omnivorous pretraining.

Systems for knowledge-intensive tasks such as open-domain question answering (QA) usually consist of two stages: efficient retrieval of relevant documents from a large corpus and detailed reading of the selected documents. This is usually done through two separate models, a retriever that encodes the query and finds nearest neighbors, and a reader based on Transformers. These two components are usually modeled separately, which necessitates a cumbersome implementation and is awkward to optimize in an end-to-end fashion. In this paper, we revisit this design and eschew the separate architecture and training in favor of a single Transformer that performs retrieval as attention (RAA), and end-to-end training solely based on supervision from the end QA task. We demonstrate for the first time that an end-to-end trained single Transformer can achieve both competitive retrieval and QA performance on in-domain datasets, matching or even slightly outperforming state-of-the-art dense retrievers and readers. Moreover, end-to-end adaptation of our model significantly boosts its performance on out-of-domain datasets in both supervised and unsupervised settings, making our model a simple and adaptable end-to-end solution for knowledge-intensive tasks.

Pretrained language models (PLMs) have been shown to accumulate factual knowledge during pretraining (Petroni et al. 2019). Recent works probe PLMs for the extent of this knowledge through prompts either in discrete or continuous forms. However, these methods do not consider symmetry of the task: object prediction and subject prediction. In this work, we propose Symmetrical Prompt Enhancement (SPE), a continuous prompt-based method for factual probing in PLMs that leverages the symmetry of the task by constructing symmetrical prompts for subject and object prediction. Our results on a popular factual probing dataset, LAMA, show significant improvement of SPE over previous probing methods.

Tables are an important form of structured data for both human and machine readers alike, providing answers to questions that cannot, or cannot easily, be found in texts. Recent work has designed special models and training paradigms for table-related tasks such as table-based question answering and table retrieval. Though effective, they add complexity in both modeling and data acquisition compared to generic text solutions and obscure which elements are truly beneficial. In this work, we focus on the task of table retrieval, and ask: “is table-specific model design necessary for table retrieval, or can a simpler text-based model be effectively used to achieve a similar result?’’ First, we perform an analysis on a table-based portion of the Natural Questions dataset (NQ-table), and find that structure plays a negligible role in more than 70% of the cases. Based on this, we experiment with a general Dense Passage Retriever (DPR) based on text and a specialized Dense Table Retriever (DTR) that uses table-specific model designs. We find that DPR performs well without any table-specific design and training, and even achieves superior results compared to DTR when fine-tuned on properly linearized tables. We then experiment with three modules to explicitly encode table structures, namely auxiliary row/column embeddings, hard attention masks, and soft relation-based attention biases. However, none of these yielded significant improvements, suggesting that table-specific model design may not be necessary for table retrieval.

Generative question answering (QA) models generate answers to questions either solely based on the parameters of the model (the closed-book setting) or additionally retrieving relevant evidence (the open-book setting). Generative QA models can answer some relatively complex questions, but the mechanism through which they do so is still poorly understood. We perform several studies aimed at better understanding the multi-hop reasoning capabilities of generative QA models. First, we decompose multi-hop questions into multiple corresponding single-hop questions, and find marked inconsistency in QA models’ answers on these pairs of ostensibly identical question chains. Second, we find that models lack zero-shot multi-hop reasoning ability: when trained only on single-hop questions, models generalize poorly to multi-hop questions. Finally, we demonstrate that it is possible to improve models’ zero-shot multi-hop reasoning capacity through two methods that approximate real multi-hop natural language (NL) questions by training on either concatenation of single-hop questions or logical forms (SPARQL). In sum, these results demonstrate that multi-hop reasoning does not emerge naturally in generative QA models, but can be encouraged by advances in training or modeling techniques. Code is available at https://github.com/jzbjyb/multihop.

Integrating extracted knowledge from the Web to knowledge graphs (KGs) can facilitate tasks like question answering. We study relation integration that aims to align free-text relations in subject-relation-object extractions to relations in a target KG. To address the challenge that free-text relations are ambiguous, previous methods exploit neighbor entities and relations for additional context. However, the predictions are made independently, which can be mutually inconsistent. We propose a two-stage Collective Relation Integration (CoRI) model, where the first stage independently makes candidate predictions, and the second stage employs a collective model that accesses all candidate predictions to make globally coherent predictions. We further improve the collective model with augmented data from the portion of the target KG that is otherwise unused. Experiment results on two datasets show that CoRI can significantly outperform the baselines, improving AUC from .677 to .748 and from .716 to .780, respectively.

Recent works have shown that language models (LM) capture different types of knowledge regarding facts or common sense. However, because no model is perfect, they still fail to provide appropriate answers in many cases. In this paper, we ask the question, “How can we know when language models know, with confidence, the answer to a particular query?” We examine this question from the point of view of calibration, the property of a probabilistic model’s predicted probabilities actually being well correlated with the probabilities of correctness. We examine three strong generative models—T5, BART, and GPT-2—and study whether their probabilities on QA tasks are well calibrated, finding the answer is a relatively emphatic no. We then examine methods to calibrate such models to make their confidence scores correlate better with the likelihood of correctness through fine-tuning, post-hoc probability modification, or adjustment of the predicted outputs or inputs. Experiments on a diverse range of datasets demonstrate the effectiveness of our methods. We also perform analysis to study the strengths and limitations of these methods, shedding light on further improvements that may be made in methods for calibrating LMs. We have released the code at https://github.com/jzbjyb/lm-calibration.

Neural abstractive summarization models are flexible and can produce coherent summaries, but they are sometimes unfaithful and can be difficult to control. While previous studies attempt to provide different types of guidance to control the output and increase faithfulness, it is not clear how these strategies compare and contrast to each other. In this paper, we propose a general and extensible guided summarization framework (GSum) that can effectively take different kinds of external guidance as input, and we perform experiments across several different varieties. Experiments demonstrate that this model is effective, achieving state-of-the-art performance according to ROUGE on 4 popular summarization datasets when using highlighted sentences as guidance. In addition, we show that our guided model can generate more faithful summaries and demonstrate how different types of guidance generate qualitatively different summaries, lending a degree of controllability to the learned models.

Natural language processing covers a wide variety of tasks predicting syntax, semantics, and information content, and usually each type of output is generated with specially designed architectures. In this paper, we provide the simple insight that a great variety of tasks can be represented in a single unified format consisting of labeling spans and relations between spans, thus a single task-independent model can be used across different tasks. We perform extensive experiments to test this insight on 10 disparate tasks spanning dependency parsing (syntax), semantic role labeling (semantics), relation extraction (information content), aspect based sentiment analysis (sentiment), and many others, achieving performance comparable to state-of-the-art specialized models. We further demonstrate benefits of multi-task learning, and also show that the proposed method makes it easy to analyze differences and similarities in how the model handles different tasks. Finally, we convert these datasets into a unified format to build a benchmark, which provides a holistic testbed for evaluating future models for generalized natural language analysis.

Open-domain code generation aims to generate code in a general-purpose programming language (such as Python) from natural language (NL) intents. Motivated by the intuition that developers usually retrieve resources on the web when writing code, we explore the effectiveness of incorporating two varieties of external knowledge into NL-to-code generation: automatically mined NL-code pairs from the online programming QA forum StackOverflow and programming language API documentation. Our evaluations show that combining the two sources with data augmentation and retrieval-based data re-sampling improves the current state-of-the-art by up to 2.2% absolute BLEU score on the code generation testbed CoNaLa. The code and resources are available at https://github.com/neulab/external-knowledge-codegen.

Recent work has presented intriguing results examining the knowledge contained in language models (LMs) by having the LM fill in the blanks of prompts such as “Obama is a __ by profession”. These prompts are usually manually created, and quite possibly sub-optimal; another prompt such as “Obama worked as a __ ” may result in more accurately predicting the correct profession. Because of this, given an inappropriate prompt, we might fail to retrieve facts that the LM does know, and thus any given prompt only provides a lower bound estimate of the knowledge contained in an LM. In this paper, we attempt to more accurately estimate the knowledge contained in LMs by automatically discovering better prompts to use in this querying process. Specifically, we propose mining-based and paraphrasing-based methods to automatically generate high-quality and diverse prompts, as well as ensemble methods to combine answers from different prompts. Extensive experiments on the LAMA benchmark for extracting relational knowledge from LMs demonstrate that our methods can improve accuracy from 31.1% to 39.6%, providing a tighter lower bound on what LMs know. We have released the code and the resulting LM Prompt And Query Archive (LPAQA) at https://github.com/jzbjyb/LPAQA.

Language models (LMs) have proven surprisingly successful at capturing factual knowledge by completing cloze-style fill-in-the-blank questions such as “Punta Cana is located in _.” However, while knowledge is both written and queried in many languages, studies on LMs’ factual representation ability have almost invariably been performed on English. To assess factual knowledge retrieval in LMs in different languages, we create a multilingual benchmark of cloze-style probes for typologically diverse languages. To properly handle language variations, we expand probing methods from single- to multi-word entities, and develop several decoding algorithms to generate multi-token predictions. Extensive experimental results provide insights about how well (or poorly) current state-of-the-art LMs perform at this task in languages with more or fewer available resources. We further propose a code-switching-based method to improve the ability of multilingual LMs to access knowledge, and verify its effectiveness on several benchmark languages. Benchmark data and code have be released at https://x-factr.github.io.

Open information extraction (IE) is the task of extracting open-domain assertions from natural language sentences. A key step in open IE is confidence modeling, ranking the extractions based on their estimated quality to adjust precision and recall of extracted assertions. We found that the extraction likelihood, a confidence measure used by current supervised open IE systems, is not well calibrated when comparing the quality of assertions extracted from different sentences. We propose an additional binary classification loss to calibrate the likelihood to make it more globally comparable, and an iterative learning process, where extractions generated by the open IE model are incrementally included as training samples to help the model learn from trial and error. Experiments on OIE2016 demonstrate the effectiveness of our method. Code and data are available at https://github.com/jzbjyb/oie_rank.