FABLES: Evaluating faithfulness and content selection in book-length summarization

While long-context large language models (LLMs) can technically summarize book-length documents (>100K tokens), the length and complexity of the documents have so far prohibited evaluations of input-dependent aspects like faithfulness. In this paper, we conduct the first large-scale human evaluation of faithfulness and content selection on LLM-generated summaries of fictional books. Our study mitigates the issue of data contamination by focusing on summaries of books published in 2023 or 2024, and we hire annotators who have fully read each book prior to the annotation task to minimize cost and cognitive burden. 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, which allows us to rank LLM summarizers based on faithfulness: Claude-3-Opus significantly outperforms all closed-source LLMs, while the open-source Mixtral is on par with GPT-3.5-Turbo. 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. While LLM-based auto-raters have proven reliable for factuality and coherence in other settings, we implement several LLM raters of faithfulness and find that none correlates strongly with human annotations, especially with regard to detecting unfaithful claims. Our experiments suggest that detecting unfaithful claims is an important future direction not only for summarization evaluation but also as a testbed for long-context understanding. Finally, we move beyond faithfulness by exploring content selection errors in book-length summarization: we develop a typology of omission errors related to crucial narrative elements and also identify a systematic over-emphasis on events occurring towards the end of the book.

GEE! Grammar Error Explanation with Large Language Models

Grammatical error correction tools are effective at correcting grammatical errors in users' input sentences but do not provide users with \textit{natural language} explanations about their errors. Such explanations are essential for helping users learn the language by gaining a deeper understanding of its grammatical rules (DeKeyser, 2003; Ellis et al., 2006). To address this gap, we propose the task of grammar error explanation, where a system needs to provide one-sentence explanations for each grammatical error in a pair of erroneous and corrected sentences. We analyze the capability of GPT-4 in grammar error explanation, and find that it only produces explanations for 60.2% of the errors using one-shot prompting. To improve upon this performance, we develop a two-step pipeline that leverages fine-tuned and prompted large language models to perform structured atomic token edit extraction, followed by prompting GPT-4 to generate explanations. We evaluate our pipeline on German and Chinese grammar error correction data sampled from language learners with a wide range of proficiency levels. Human evaluation reveals that our pipeline produces 93.9% and 98.0% correct explanations for German and Chinese data, respectively. To encourage further research in this area, we will open-source our data and code.

Multistage Collaborative Knowledge Distillation from Large Language Models

We study semi-supervised sequence prediction tasks where labeled data are too scarce to effectively finetune a model and at the same time few-shot prompting of a large language model (LLM) has suboptimal performance. This happens when a task, such as parsing, is expensive to annotate and also unfamiliar to a pretrained LLM. In this paper, we present a discovery that student models distilled from a prompted LLM can often generalize better than their teacher on such tasks. Leveraging this finding, we propose a new distillation method, multistage collaborative knowledge distillation from an LLM (MCKD), for such tasks. MCKD first prompts an LLM using few-shot in-context learning to produce pseudolabels for unlabeled data. Then, at each stage of distillation, a pair of students are trained on disjoint partitions of the pseudolabeled data. Each student subsequently produces new and improved pseudolabels for the unseen partition to supervise the next round of student(s) with. We show the benefit of multistage cross-partition labeling on two constituency parsing tasks. On CRAFT biomedical parsing, 3-stage MCKD with 50 labeled examples matches the performance of supervised finetuning with 500 examples and outperforms the prompted LLM and vanilla KD by 7.5% and 3.7% parsing F1, respectively.

TopicGPT: A Prompt-based Topic Modeling Framework

Topic modeling is a well-established technique for exploring text corpora. Conventional topic models (e.g., LDA) represent topics as bags of words that often require "reading the tea leaves" to interpret; additionally, they offer users minimal semantic control over topics. To tackle these issues, we introduce TopicGPT, a prompt-based framework that uses large language models (LLMs) to uncover latent topics within a provided text collection. TopicGPT produces topics that align better with human categorizations compared to competing methods: for example, it achieves a harmonic mean purity of 0.74 against human-annotated Wikipedia topics compared to 0.64 for the strongest baseline. Its topics are also more interpretable, dispensing with ambiguous bags of words in favor of topics with natural language labels and associated free-form descriptions. Moreover, the framework is highly adaptable, allowing users to specify constraints and modify topics without the need for model retraining. TopicGPT can be further extended to hierarchical topical modeling, enabling users to explore topics at various levels of granularity. By streamlining access to high-quality and interpretable topics, TopicGPT represents a compelling, human-centered approach to topic modeling.

PaRaDe: Passage Ranking using Demonstrations with Large Language Models

Recent studies show that large language models (LLMs) can be instructed to effectively perform zero-shot passage re-ranking, in which the results of a first stage retrieval method, such as BM25, are rated and reordered to improve relevance. In this work, we improve LLM-based re-ranking by algorithmically selecting few-shot demonstrations to include in the prompt. Our analysis investigates the conditions where demonstrations are most helpful, and shows that adding even one demonstration is significantly beneficial. We propose a novel demonstration selection strategy based on difficulty rather than the commonly used semantic similarity. Furthermore, we find that demonstrations helpful for ranking are also effective at question generation. We hope our work will spur more principled research into question generation and passage ranking.

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

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 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 the oft-repetitive ones generated by LLaMA 2. Incremental updating yields lower BooookScore but higher level of detail than hierarchical merging, a trade-off sometimes preferred by human annotators. We release code and annotations after blind review to spur more principled research on book-length summarization.

FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation

Most large language models (LLMs) are trained once and never updated; thus, they lack the ability to dynamically adapt to our ever-changing world. In this work, we perform a detailed study of the factuality of LLM-generated text in the context of answering questions that test current world knowledge. Specifically, we introduce FreshQA, a novel dynamic QA benchmark encompassing a diverse range of question and answer types, including questions that require fast-changing world knowledge as well as questions with false premises that need to be debunked. We benchmark a diverse array of both closed and open-source LLMs under a two-mode evaluation procedure that allows us to measure both correctness and hallucination. Through human evaluations involving more than 50K judgments, we shed light on limitations of these models and demonstrate significant room for improvement: for instance, all models (regardless of model size) struggle on questions that involve fast-changing knowledge and false premises. Motivated by these results, we present FreshPrompt, a simple few-shot prompting method that substantially boosts the performance of an LLM on FreshQA by incorporating relevant and up-to-date information retrieved from a search engine into the prompt. Our experiments show that FreshPrompt outperforms both competing search engine-augmented prompting methods such as Self-Ask (Press et al., 2022) as well as commercial systems such as Perplexity.AI. Further analysis of FreshPrompt reveals that both the number of retrieved evidences and their order play a key role in influencing the correctness of LLM-generated answers. Additionally, instructing the LLM to generate concise and direct answers helps reduce hallucination compared to encouraging more verbose answers. To facilitate future work, we release FreshQA at github.com/freshllms/freshqa and commit to updating it at regular intervals.

Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF

During the last stage of RLHF, a large language model is aligned to human intents via PPO training, a process that generally requires large-scale computational resources. In this technical report, we empirically investigate an efficient implementation of RLHF using low-rank adaptation (LoRA), which allows us to align the LLaMA 7B checkpoint on the Alpaca dataset using only two A100 GPUs instead of the eight required for full model fine-tuning. Despite tuning only 0.2% of LLaMA 7B's parameters, our implementation achieves better performance than the publicly-released AlpacaFarm checkpoint with full model fine-tuning. Next, we analyze several configurations of our LoRA-based PPO implementation, varying the form of the KL regularization term in the training objective. We find that (1) removing this penalty term does not harm performance on the AlpacaFarm evaluation set under our LoRA setup; (2) other regularizers, such as Jensen-Shannon divergence, lead to improved performance; and (3) while PPO training negatively impacts the factuality of model-generated responses, training with LoRA largely mitigates this effect. We release our code and pretrained checkpoints to facilitate future research on more efficient RLHF.

A Critical Evaluation of Evaluations for Long-form Question Answering

Long-form question answering (LFQA) enables answering a wide range of questions, but its flexibility poses enormous challenges for evaluation. We perform the first targeted study of the evaluation of long-form answers, covering both human and automatic evaluation practices. We hire domain experts in seven areas to provide preference judgments over pairs of answers, along with free-form justifications for their choices. We present a careful analysis of experts' evaluation, which focuses on new aspects such as the comprehensiveness of the answer. Next, we examine automatic text generation metrics, finding that no existing metrics are predictive of human preference judgments. However, some metrics correlate with fine-grained aspects of answers (e.g., coherence). We encourage future work to move away from a single "overall score" of the answer and adopt a multi-faceted evaluation, targeting aspects such as factuality and completeness. We publicly release all of our annotations and code to spur future work into LFQA evaluation.

KNN-LM Does Not Improve Open-ended Text Generation

In this paper, we study the generation quality of interpolation-based retrieval-augmented language models (LMs). These methods, best exemplified by the KNN-LM, interpolate the LM's predicted distribution of the next word with a distribution formed from the most relevant retrievals for a given prefix. While the KNN-LM and related methods yield impressive decreases in perplexity, we discover that they do not exhibit corresponding improvements in open-ended generation quality, as measured by both automatic evaluation metrics (e.g., MAUVE) and human evaluations. Digging deeper, we find that interpolating with a retrieval distribution actually increases perplexity compared to a baseline Transformer LM for the majority of tokens in the WikiText-103 test set, even though the overall perplexity is lower due to a smaller number of tokens for which perplexity dramatically decreases after interpolation. However, when decoding a long sequence at inference time, significant improvements on this smaller subset of tokens are washed out by slightly worse predictions on most tokens. Furthermore, we discover that the entropy of the retrieval distribution increases faster than that of the base LM as the generated sequence becomes longer, which indicates that retrieval is less reliable when using model-generated text as queries (i.e., is subject to exposure bias). We hope that our analysis spurs future work on improved decoding algorithms and interpolation strategies for retrieval-augmented language models.