Selecting the “right” amount of information to include in a summary is a difficult task. A good summary should be detailed and entity-centric without being overly dense and hard to follow. To better understand this tradeoff, we solicit increasingly dense GPT-4 summaries with what we refer to as a “Chain of Density” (CoD) prompt. Specifically, GPT-4 generates an initial entity-sparse summary before iteratively incorporating missing salient entities without increasing the length. Summaries generated by CoD are more abstractive, exhibit more fusion, and have less of a lead bias than GPT-4 summaries generated by a vanilla prompt. We conduct a human preference study on 100 CNN DailyMail articles and find that humans prefer GPT-4 summaries that are more dense than those generated by a vanilla prompt and almost as dense as human written summaries. Qualitative analysis supports the notion that there exists a tradeoff between informativeness and readability. 500 annotated CoD summaries, as well as an extra 5,000 unannotated summaries, are freely available on HuggingFace (https://huggingface.co/datasets/griffin/chain_of_density).

Effective human learning depends on a wide selection of educational materials that align with the learner’s current understanding of the topic. While the Internet has revolutionized human learning or education, a substantial resource accessibility barrier still exists. Namely, the excess of online information can make it challenging to navigate and discover high-quality learning materials in a given subject area. In this paper, we propose an automatic pipeline for building an educational resource discovery system for new domains. The pipeline consists of three main steps: resource searching, feature extraction, and resource classification. We first collect frequent queries from a set of seed documents, and search the web with these queries to obtain candidate resources such as lecture slides and introductory blog posts. Then, we process these resources for BERT-based features and meta-features. Next, we train a tree-based classifier to decide whether they are suitable learning materials. The pipeline achieves F1 scores of 0.94 and 0.82 when evaluated on two similar but novel domains. Finally, we demonstrate how this pipeline can benefit two applications: prerequisite chain learning and leading paragraph generation for surveys. We also release a corpus of 39,728 manually labeled web resources and 659 queries from NLP, Computer Vision (CV), and Statistics (STATS).

Two-step approaches, in which summary candidates are generated-then-reranked to return a single summary, can improve ROUGE scores over the standard single-step approach. Yet, standard decoding methods (i.e., beam search, nucleus sampling, and diverse beam search) produce candidates with redundant, and often low quality, content. In this paper, we design a novel method to generate candidates for re-ranking that addresses these issues. We ground each candidate abstract on its own unique content plan and generate distinct plan-guided abstracts using a model’s top beam. More concretely, a standard language model (a BART LM) auto-regressively generates elemental discourse unit (EDU) content plans with an extractive copy mechanism. The top K beams from the content plan generator are then used to guide a separate LM, which produces a single abstractive candidate for each distinct plan. We apply an existing re-ranker (BRIO) to abstractive candidates generated from our method, as well as baseline decoding methods. We show large relevance improvements over previously published methods on widely used single document news article corpora, with ROUGE-2 F1 gains of 0.88, 2.01, and 0.38 on CNN / Dailymail, NYT, and Xsum, respectively. A human evaluation on CNN / DM validates these results. Similarly, on 1k samples from CNN / DM, we show that prompting GPT-3 to follow EDU plans outperforms sampling-based methods by by 1.05 ROUGE-2 F1 points. Code to generate and realize plans is available at https://github.com/griff4692/edu-sum.

Human evaluation is the foundation upon which the evaluation of both summarization systems and automatic metrics rests. However, existing human evaluation studies for summarization either exhibit a low inter-annotator agreement or have insufficient scale, and an in-depth analysis of human evaluation is lacking. Therefore, we address the shortcomings of existing summarization evaluation along the following axes: (1) We propose a modified summarization salience protocol, Atomic Content Units (ACUs), which is based on fine-grained semantic units and allows for a high inter-annotator agreement. (2) We curate the Robust Summarization Evaluation (RoSE) benchmark, a large human evaluation dataset consisting of 22,000 summary-level annotations over 28 top-performing systems on three datasets. (3) We conduct a comparative study of four human evaluation protocols, underscoring potential confounding factors in evaluation setups. (4) We evaluate 50 automatic metrics and their variants using the collected human annotations across evaluation protocols and demonstrate how our benchmark leads to more statistically stable and significant results. The metrics we benchmarked include recent methods based on large language models (LLMs), GPTScore and G-Eval. Furthermore, our findings have important implications for evaluating LLMs, as we show that LLMs adjusted by human feedback (e.g., GPT-3.5) may overfit unconstrained human evaluation, which is affected by the annotators’ prior, input-agnostic preferences, calling for more robust, targeted evaluation methods.

The propensity of abstractive summarization models to make factual errors has been studied extensively, including design of metrics to detect factual errors and annotation of errors in current systems’ outputs. However, the ever-evolving nature of summarization systems, metrics, and annotated benchmarks makes factuality evaluation a moving target, and drawing clear comparisons among metrics has become increasingly difficult. In this work, we aggregate factuality error annotations from nine existing datasets and stratify them according to the underlying summarization model. We compare performance of state-of-the-art factuality metrics, including recent ChatGPT-based metrics, on this stratified benchmark and show that their performance varies significantly across different types of summarization models. Critically, our analysis shows that much of the recent improvement in the factuality detection space has been on summaries from older (pre-Transformer) models instead of more relevant recent summarization models. We further perform a finer-grained analysis per error-type and find similar performance variance across error types for different factuality metrics. Our results show that no one metric is superior in all settings or for all error types, and we provide recommendations for best practices given these insights.

In long document controllable summarization, where labeled data is scarce, pretrained models struggle to adapt to the task and effectively respond to user queries. In this paper, we introduce Socratic pretraining, a question-driven, unsupervised pretraining objective specifically designed to improve controllability in summarization tasks. By training a model to generate and answer relevant questions in a given context, Socratic pretraining enables the model to more effectively adhere to user-provided queries and identify relevant content to be summarized. We demonstrate the effectiveness of this approach through extensive experimentation on two summarization domains, short stories and dialogue, and multiple control strategies: keywords, questions, and factoid QA pairs. Our pretraining method relies only on unlabeled documents and a question generation system and outperforms pre-finetuning approaches that use additional supervised data. Furthermore, our results show that Socratic pretraining cuts task-specific labeled data requirements in half, is more faithful to user-provided queries, and achieves state-of-the-art performance on QMSum and SQuALITY.

Large language models have shown impressive performance across a wide variety of tasks, including text summarization. In this paper, we show that this strong performance extends to opinion summarization. We explore several pipeline methods for applying GPT-3.5 to summarize a large collection of user reviews in aprompted fashion. To handle arbitrarily large numbers of user reviews, we explore recursive summarization as well as methods for selecting salient content to summarize through supervised clustering or extraction. On two datasets, an aspect-oriented summarization dataset of hotel reviews (SPACE) and a generic summarization dataset of Amazon and Yelp reviews (FewSum), we show that GPT-3.5 models achieve very strong performance in human evaluation. We argue that standard evaluation metrics do not reflect this, and introduce three new metrics targeting faithfulness, factuality, and genericity to contrast these different methods.

Hallucination is a known issue for neural abstractive summarization models. Recent work suggests that the degree of hallucination may depend on factual errors in the training data. In this work, we propose a new method called Contrastive Parameter Ensembling (CaPE) to use training data more effectively, utilizing variations in noise in training samples to reduce hallucination. Starting with a base model fine-tuned on an entire dataset, we additionally train expert and anti-expert models on clean and noisy subsets of the data, respectively. We then adjust the parameters of the base model by adding (subtracting) the parameters of the expert (anti-expert), advancing the recent work on additive parameter ensembling approaches. Trained on a much smaller data subset, expert and anti-expert models only fractionally (<14%) increases the total training time. Further, CaPE uses parameter ensembling and does not increase the inference time. Experimental results show that CaPE improves performance across different automatic factual metrics and human evaluation, with a maximum improvement of 16.69% and 15.38% on summary-level dependency-arc entailment accuracy for the XSUM and CNN/DM datasets. The CaPE model performs comparably to the base model on metrics of informativeness such as ROUGE.

Fast-developing fields such as Artificial Intelligence (AI) often outpace the efforts of encyclopedic sources such as Wikipedia, which either do not completely cover recently-introduced topics or lack such content entirely. As a result, methods for automatically producing content are valuable tools to address this information overload. We show that recent advances in pretrained language modeling can be combined for a two-stage extractive and abstractive approach for Wikipedia lead paragraph generation. We extend this approach to generate longer Wikipedia-style summaries with sections and examine how such methods struggle in this application through detailed studies with 100 reference human-collected surveys. This is the first study on utilizing web resources for long Wikipedia-style summaries to the best of our knowledge.

State-of-the-art summarization models still struggle to be factually consistent with the input text. A model-agnostic way to address this problem is post-editing the generated summaries. However, existing approaches typically fail to remove entity errors if a suitable input entity replacement is not available or may insert erroneous content. In our work, we focus on removing extrinsic entity errors, or entities not in the source, to improve consistency while retaining the summary’s essential information and form. We propose to use sentence-compression data to train the post-editing model to take a summary with extrinsic entity errors marked with special tokens and output a compressed, well-formed summary with those errors removed. We show that this model improves factual consistency while maintaining ROUGE, improving entity precision by up to 30% on XSum, and that this model can be applied on top of another post-editor, improving entity precision by up to a total of 38%. We perform an extensive comparison of post-editing approaches that demonstrate trade-offs between factual consistency, informativeness, and grammaticality, and we analyze settings where post-editors show the largest improvements.