BooookScore: A systematic exploration of book-length summarization in the era of LLMs

• URL: http://arxiv.org/abs/2310.00785v4
• Date: Sat, 13 Apr 2024 22:02:23 GMT
• Title: BooookScore: A systematic exploration of book-length summarization in the era of LLMs
• Authors: Yapei Chang, Kyle Lo, Tanya Goyal, Mohit Iyyer,
• Abstract summary: We develop an automatic metric, BooookScore, that measures the proportion of sentences in a summary that do not contain any of the identified error types. We find that closed-source LLMs such as GPT-4 and 2 produce summaries with higher BooookScore than those generated by open-source models.
• Score: 53.42917858142565
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Summarizing book-length documents (>100K tokens) that exceed the context window size of large language models (LLMs) requires first breaking the input document into smaller chunks and then prompting an LLM to merge, update, and compress chunk-level summaries. Despite the complexity and importance of this task, it has yet to be meaningfully studied due to the challenges of evaluation: existing book-length summarization datasets (e.g., BookSum) are in the pretraining data of most public LLMs, and existing evaluation methods struggle to capture errors made by modern LLM summarizers. In this paper, we present the first study of the coherence of LLM-based book-length summarizers implemented via two prompting workflows: (1) hierarchically merging chunk-level summaries, and (2) incrementally updating a running summary. We obtain 1193 fine-grained human annotations on GPT-4 generated summaries of 100 recently-published books and identify eight common types of coherence errors made by LLMs. Because human evaluation is expensive and time-consuming, we develop an automatic metric, BooookScore, that measures the proportion of sentences in a summary that do not contain any of the identified error types. BooookScore has high agreement with human annotations and allows us to systematically evaluate the impact of many other critical parameters (e.g., chunk size, base LLM) while saving $15K USD and 500 hours in human evaluation costs. We find that closed-source LLMs such as GPT-4 and Claude 2 produce summaries with higher BooookScore than those generated by open-source models. While LLaMA 2 falls behind other models, Mixtral achieves performance on par with GPT-3.5-Turbo. Incremental updating yields lower BooookScore but higher level of detail than hierarchical merging, a trade-off sometimes preferred by annotators.

Related papers

• FineSurE: Fine-grained Summarization Evaluation using LLMs [22.62504593575933]
  FineSurE is a fine-grained evaluator specifically tailored for the summarization task using large language models (LLMs) It also employs completeness and conciseness criteria, in addition to faithfulness, enabling multi-dimensional assessment.
  arXiv  Detail & Related papers  (2024-07-01T02:20:28Z)
• WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia [59.96425443250666]
  Retrieval-augmented generation (RAG) has emerged as a promising solution to mitigate the limitations of large language models (LLMs) In this work, we conduct a comprehensive evaluation of LLM-generated answers to questions based on contradictory passages from Wikipedia. We benchmark a diverse range of both closed and open-source LLMs under different QA scenarios, including RAG with a single passage, and RAG with 2 contradictory passages.
  arXiv  Detail & Related papers  (2024-06-19T20:13:42Z)
• FABLES: Evaluating faithfulness and content selection in book-length summarization [55.50680057160788]
  In this paper, we conduct the first large-scale human evaluation of faithfulness and content selection on book-length documents. We collect FABLES, a dataset of annotations on 3,158 claims made in LLM-generated summaries of 26 books, at a cost of $5.2K USD. An analysis of the annotations reveals that most unfaithful claims relate to events and character states, and they generally require indirect reasoning over the narrative to invalidate.
  arXiv  Detail & Related papers  (2024-04-01T17:33:38Z)
• Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation [0.0]
  We analyze the behaviors of open large language models (LLMs) on the task of data-to-text (D2T) generation. We find that open LLMs can generate fluent and coherent texts in zero-shot settings from data in common formats collected with Quintd.
  arXiv  Detail & Related papers  (2024-01-18T18:15:46Z)
• Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization [132.25202059478065]
  We benchmark large language models (LLMs) on instruction controllable text summarization. Our study reveals that instruction controllable text summarization remains a challenging task for LLMs.
  arXiv  Detail & Related papers  (2023-11-15T18:25:26Z)
• Summarization is (Almost) Dead [49.360752383801305]
  We develop new datasets and conduct human evaluation experiments to evaluate the zero-shot generation capability of large language models (LLMs) Our findings indicate a clear preference among human evaluators for LLM-generated summaries over human-written summaries and summaries generated by fine-tuned models.
  arXiv  Detail & Related papers  (2023-09-18T08:13:01Z)
• Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought Method [35.181659789684545]
  Automatic summarization generates concise summaries that contain key ideas of source documents. References from CNN/DailyMail and BBC XSum are noisy, mainly in terms of factual hallucination and information redundancy. We propose a Summary Chain-of-Thought (SumCoT) technique to elicit LLMs to generate summaries step by step. Experimental results show our method outperforms state-of-the-art fine-tuned PLMs and zero-shot LLMs by +4.33/+4.77 in ROUGE-L.
  arXiv  Detail & Related papers  (2023-05-22T18:54:35Z)
• Evaluating the Factual Consistency of Large Language Models Through News Summarization [97.04685401448499]
  We propose a new benchmark called FIB(Factual Inconsistency Benchmark) that focuses on the task of summarization. For factually consistent summaries, we use human-written reference summaries that we manually verify as factually consistent. For factually inconsistent summaries, we generate summaries from a suite of summarization models that we have manually annotated as factually inconsistent.
  arXiv  Detail & Related papers  (2022-11-15T18:50:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.