Multimodal Large Language Models (MLLMs) have advanced in integrating diverse modalities but frequently suffer from hallucination. A promising solution to mitigate this issue is to generate text with citations, providing a transparent chain for verification. However, existing work primarily focuses on generating citations for text-only content, overlooking the challenges and opportunities of multimodal contexts. To address this gap, we introduce MCiteBench, the first benchmark designed to evaluate and analyze the multimodal citation text generation ability of MLLMs. Our benchmark comprises data derived from academic papers and review-rebuttal interactions, featuring diverse information sources and multimodal content. We comprehensively evaluate models from multiple dimensions, including citation quality, source reliability, and answer accuracy. Through extensive experiments, we observe that MLLMs struggle with multimodal citation text generation. We also conduct deep analyses of models' performance, revealing that the bottleneck lies in attributing the correct sources rather than understanding the multimodal content.

A key challenge in citation text generation is that the length of generated text often differs from the length of the target, lowering the quality of the generation. While prior works have investigated length-controlled generation, their effectiveness depends on knowing the appropriate generation length. In this work, we present an in-depth study of the limitations of predicting scientific citation text length and explore the use of heuristic estimates of desired length.

Large language models (LLMs) bring unprecedented flexibility in defining and executing complex, creative natural language generation (NLG) tasks. Yet, this flexibility brings new challenges, as it introduces new degrees of freedom in formulating the task inputs and instructions and in evaluating model performance. To facilitate the exploration of creative NLG tasks, we propose a three-component research framework that consists of systematic input manipulation, reference data, and output measurement. We use this framework to explore citation text generation -- a popular scholarly NLP task that lacks consensus on the task definition and evaluation metric and has not yet been tackled within the LLM paradigm. Our results highlight the importance of systematically investigating both task instruction and input configuration when prompting LLMs, and reveal non-trivial relationships between different evaluation metrics used for citation text generation. Additional human generation and human evaluation experiments provide new qualitative insights into the task to guide future research in citation text generation. We make our code and data publicly available.

Citation text plays a pivotal role in elucidating the connection between scientific documents, demanding an in-depth comprehension of the cited paper. Constructing citations is often time-consuming, requiring researchers to delve into extensive literature and grapple with articulating relevant content. To address this challenge, the field of citation text generation (CTG) has emerged. However, while earlier methods have primarily centered on creating single-sentence citations, practical scenarios frequently necessitate citing multiple papers within a single paragraph. To bridge this gap, we propose a method that leverages Large Language Models (LLMs) to generate multi-citation sentences. Our approach involves a single source paper and a collection of target papers, culminating in a coherent paragraph containing multi-sentence citation text. Furthermore, we introduce a curated dataset named MCG-S2ORC, composed of English-language academic research papers in Computer Science, showcasing multiple citation instances. In our experiments, we evaluate three LLMs LLaMA, Alpaca, and Vicuna to ascertain the most effective model for this endeavor. Additionally, we exhibit enhanced performance by integrating knowledge graphs from target papers into the prompts for generating citation text. This research underscores the potential of harnessing LLMs for citation generation, opening a compelling avenue for exploring the intricate connections between scientific documents.

Due to the rapid pace of research publications, keeping up to date with all the latest related papers is very time-consuming, even with daily feed tools. There is a need for automatically generated, short, customized literature reviews of sets of papers to help researchers decide what to read. While several works in the last decade have addressed the task of explaining a single research paper, usually in the context of another paper citing it, the relationship among multiple papers has been ignored; prior works have focused on generating a single citation sentence in isolation, without addressing the expository and transition sentences needed to connect multiple papers in a coherent story. In this work, we explore a feature-based, LLM-prompting approach to generate richer citation texts, as well as generating multiple citations at once to capture the complex relationships among research papers. We perform an expert evaluation to investigate the impact of our proposed features on the quality of the generated paragraphs and find a strong correlation between human preference and integrative writing style, suggesting that humans prefer high-level, abstract citations, with transition sentences between them to provide an overall story.

Science progresses by building upon the prior body of knowledge documented in scientific publications. The acceleration of research makes it hard to stay up-to-date with the recent developments and to summarize the ever-growing body of prior work. To address this, the task of citation text generation aims to produce accurate textual summaries given a set of papers-to-cite and the citing paper context. Due to otherwise rare explicit anchoring of cited documents in the citing paper, citation text generation provides an excellent opportunity to study how humans aggregate and synthesize textual knowledge from sources. Yet, existing studies are based upon widely diverging task definitions, which makes it hard to study this task systematically. To address this challenge, we propose CiteBench: a benchmark for citation text generation that unifies multiple diverse datasets and enables standardized evaluation of citation text generation models across task designs and domains. Using the new benchmark, we investigate the performance of multiple strong baselines, test their transferability between the datasets, and deliver new insights into the task definition and evaluation to guide future research in citation text generation. We make the code for CiteBench publicly available at https://github.com/UKPLab/citebench.

Automatic related work generation must ground their outputs to the content of the cited papers to avoid non-factual hallucinations, but due to the length of scientific documents, existing abstractive approaches have conditioned only on the cited paper \textit{abstracts}. We demonstrate that the abstract is not always the most appropriate input for citation generation and that models trained in this way learn to hallucinate. We propose to condition instead on the \textit{cited text span} (CTS) as an alternative to the abstract. Because manual CTS annotation is extremely time- and labor-intensive, we experiment with automatic, ROUGE-based labeling of candidate CTS sentences, achieving sufficiently strong performance to substitute for expensive human annotations, and we propose a human-in-the-loop, keyword-based CTS retrieval approach that makes generating citation texts grounded in the full text of cited papers both promising and practical.