Understanding the Role of LLMs in Multimodal Evaluation Benchmarks

The rapid advancement of Multimodal Large Language Models (MLLMs) has been accompanied by the development of various benchmarks to evaluate their capabilities. However, the true nature of these evaluations and the extent to which they assess multimodal reasoning versus merely leveraging the underlying Large Language Model (LLM) backbone remain unclear. This paper presents a comprehensive investigation into the role of LLM backbones in MLLM evaluation, focusing on two critical aspects: the degree to which current benchmarks truly assess multimodal reasoning and the influence of LLM prior knowledge on performance. Specifically, we introduce a modified evaluation protocol to disentangle the contributions of the LLM backbone from multimodal integration, and an automatic knowledge identification technique for diagnosing whether LLMs equip the necessary knowledge for corresponding multimodal questions. Our study encompasses four diverse MLLM benchmarks and eight state-of-the-art MLLMs. Key findings reveal that some benchmarks allow high performance even without visual inputs and up to 50\% of error rates can be attributed to insufficient world knowledge in the LLM backbone, indicating a heavy reliance on language capabilities. To address knowledge deficiencies, we propose a knowledge augmentation pipeline that achieves significant performance gains, with improvements of up to 60\% on certain datasets, resulting in a approximately 4x increase in performance. Our work provides crucial insights into the role of the LLM backbone in MLLMs, and highlights the need for more nuanced benchmarking approaches.

TMGBench: A Systematic Game Benchmark for Evaluating Strategic Reasoning Abilities of LLMs

The rapid advancement of large language models (LLMs) has accelerated their application in reasoning, with strategic reasoning drawing increasing attention. To evaluate LLMs' strategic reasoning capabilities, game theory, with its concise structure, has become a preferred approach. However, current research focuses on a limited selection of games, resulting in low coverage. Classic game scenarios risk data leakage, and existing benchmarks often lack extensibility, making them inadequate for evaluating state-of-the-art models. To address these challenges, we propose TMGBench, a benchmark with comprehensive game type coverage, novel scenarios, and flexible organization. Specifically, we incorporate all 144 game types summarized by the Robinson-Goforth topology of 2x2 games, constructed as classic games. We also employ synthetic data generation to create diverse, higher-quality scenarios through topic guidance and human inspection, referred to as story-based games. Lastly, we provide a sustainable framework for increasingly powerful LLMs by treating these games as atomic units and organizing them into more complex forms via sequential, parallel, and nested structures. Our comprehensive evaluation of mainstream LLMs covers tests on rational reasoning, robustness, Theory-of-Mind (ToM), and reasoning in complex forms. Results reveal flaws in accuracy, consistency, and varying mastery of ToM. Additionally, o1-mini, OpenAI's latest reasoning model, achieved accuracy rates of 66.6%, 60.0%, and 70.0% on sequential, parallel, and nested games, highlighting TMGBench's challenges.

GlobeSumm: A Challenging Benchmark Towards Unifying Multi-lingual, Cross-lingual and Multi-document News Summarization

News summarization in today's global scene can be daunting with its flood of multilingual content and varied viewpoints from different sources. However, current studies often neglect such real-world scenarios as they tend to focus solely on either single-language or single-document tasks. To bridge this gap, we aim to unify Multi-lingual, Cross-lingual and Multi-document Summarization into a novel task, i.e., MCMS, which encapsulates the real-world requirements all-in-one. Nevertheless, the lack of a benchmark inhibits researchers from adequately studying this invaluable problem. To tackle this, we have meticulously constructed the GLOBESUMM dataset by first collecting a wealth of multilingual news reports and restructuring them into event-centric format. Additionally, we introduce the method of protocol-guided prompting for high-quality and cost-effective reference annotation. In MCMS, we also highlight the challenge of conflicts between news reports, in addition to the issues of redundancies and omissions, further enhancing the complexity of GLOBESUMM. Through extensive experimental analysis, we validate the quality of our dataset and elucidate the inherent challenges of the task. We firmly believe that GLOBESUMM, given its challenging nature, will greatly contribute to the multilingual communities and the evaluation of LLMs.

Learning Fine-Grained Grounded Citations for Attributed Large Language Models

Despite the impressive performance on information-seeking tasks, large language models (LLMs) still struggle with hallucinations. Attributed LLMs, which augment generated text with in-line citations, have shown potential in mitigating hallucinations and improving verifiability. However, current approaches suffer from suboptimal citation quality due to their reliance on in-context learning. Furthermore, the practice of citing only coarse document identifiers makes it challenging for users to perform fine-grained verification. In this work, we introduce FRONT, a training framework designed to teach LLMs to generate Fine-Grained Grounded Citations. By grounding model outputs in fine-grained supporting quotes, these quotes guide the generation of grounded and consistent responses, not only improving citation quality but also facilitating fine-grained verification. Experiments on the ALCE benchmark demonstrate the efficacy of FRONT in generating superior grounded responses and highly supportive citations. With LLaMA-2-7B, the framework significantly outperforms all the baselines, achieving an average of 14.21% improvement in citation quality across all datasets, even surpassing ChatGPT.

Large Language Models Meet NLP: A Survey

While large language models (LLMs) like ChatGPT have shown impressive capabilities in Natural Language Processing (NLP) tasks, a systematic investigation of their potential in this field remains largely unexplored. This study aims to address this gap by exploring the following questions: (1) How are LLMs currently applied to NLP tasks in the literature? (2) Have traditional NLP tasks already been solved with LLMs? (3) What is the future of the LLMs for NLP? To answer these questions, we take the first step to provide a comprehensive overview of LLMs in NLP. Specifically, we first introduce a unified taxonomy including (1) parameter-frozen application and (2) parameter-tuning application to offer a unified perspective for understanding the current progress of LLMs in NLP. Furthermore, we summarize the new frontiers and the associated challenges, aiming to inspire further groundbreaking advancements. We hope this work offers valuable insights into the {potential and limitations} of LLMs in NLP, while also serving as a practical guide for building effective LLMs in NLP.

Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models

Large vision-language models (LVLMs), exemplified by GPT-4V, excel across diverse tasks involving concrete images from natural scenes. However, their ability to interpret abstract figures, such as geometry shapes and scientific plots, remains limited due to a scarcity of training datasets in scientific domains. To fill this gap, we introduce Multimodal ArXiv, consisting of ArXivCap and ArXivQA, for enhancing LVLMs scientific comprehension. ArXivCap is a figure-caption dataset comprising 6.4M images and 3.9M captions sourced from 572K ArXiv papers spanning various scientific domains. Drawing from ArXivCap, we introduce ArXivQA, a question-answering dataset generated by prompting GPT-4V based on scientific figures. ArXivQA greatly enhances LVLMs' mathematical reasoning capabilities, achieving a 10.4% absolute accuracy gain on a multimodal mathematical reasoning benchmark. Furthermore, employing ArXivCap, we devise four vision-to-text tasks for benchmarking LVLMs. Evaluation results with state-of-the-art LVLMs underscore their struggle with the nuanced semantics of academic figures, with domain-specific training yielding substantial performance gains. Our error analysis uncovers misinterpretations of visual context, recognition errors, and the production of overly simplified captions by current LVLMs, shedding light on future improvements.

Length Extrapolation of Transformers: A Survey from the Perspective of Position Encoding

Transformer has taken the natural language processing (NLP) field by storm since birth, owing to its superior ability to model complex dependencies in sequences. Despite the great success of pretrained language models (PLMs) based on Transformer across almost all NLP tasks, they all suffer from a preset length limit and thus can hardly extend this success to longer sequences beyond seen data, namely the length extrapolation problem. Length extrapolation has aroused great interest among researchers, as it is the core feature of human language capacity. To enhance length extrapolation of Transformers, a plethora of methods have been proposed, mostly focusing on extrapolatable position encodings. In this article, we provide an organized and systematical review of these research efforts in a unified notation from a position encoding perspective, aiming to enable the reader to gain a deep understanding of existing methods and provide stimuli for future research.

Adapter-based Selective Knowledge Distillation for Federated Multi-domain Meeting Summarization

Meeting summarization has emerged as a promising technique for providing users with condensed summaries. However, existing work has focused on training models on centralized data, neglecting real-world scenarios where meeting data are infeasible to collect centrally, due to their sensitive nature. This gap motivates us to explore federated learning for meeting summarization. Two critical challenges impede progress. First, state-of-the-art summarizers are based on parameter-heavy pre-trained models. Exchanging such a model's parameters across clients imposes large bandwidth costs. Second, as real-world meeting data belong to various domains and are distributed across clients, they are instances of non-identically and independently distributed (non-IID). IID assumptions do not hold, which changes which forms of learning algorithms best apply. To address this, we propose Adapter-based Federated Selective Knowledge Distillation (AdaFedSelecKD) for training performant client models. Specifically, we develop an adapter-based summarization model where two adapters cooperatively facilitate learning using fewer parameters to reduce communication costs. Then, we devise a selective knowledge distillation strategy, assisting clients in robustly handling domain-focused modelling on their own data, while leveraging global parameters based on non-IID data. Extensive experiments on the QMSum benchmark demonstrate AdaFedSelecKD can achieve comparable performance with powerful centralized training methods, and shows its generalizability and robustness.

The Role of Summarization in Generative Agents: A Preliminary Perspective

Generative agents that simulate human society show tremendous potential for further research and practical applications. Specifically, the generative agent architecture comprising several meticulously designed modules constitutes the most critical component. To facilitate progress in this research, this report presents our integrated perspective on comprehending generative agents through summarization, since we believe summarization is the most fundamental and indispensable capacity of generative agents manifested across diverse scenarios. We hope this report can provide insight into understanding the importance of summarization capacity in generative agents and motivate future research.

Hierarchical Catalogue Generation for Literature Review: A Benchmark

Multi-document scientific summarization can extract and organize important information from an abundant collection of papers, arousing widespread attention recently. However, existing efforts focus on producing lengthy overviews lacking a clear and logical hierarchy. To alleviate this problem, we present an atomic and challenging task named Hierarchical Catalogue Generation for Literature Review (HiCatGLR), which aims to generate a hierarchical catalogue for a review paper given various references. We carefully construct a novel English Hierarchical Catalogues of Literature Reviews Dataset (HiCaD) with 13.8k literature review catalogues and 120k reference papers, where we benchmark diverse experiments via the end-to-end and pipeline methods. To accurately assess the model performance, we design evaluation metrics for similarity to ground truth from semantics and structure. Besides, our extensive analyses verify the high quality of our dataset and the effectiveness of our evaluation metrics. Furthermore, we discuss potential directions for this task to motivate future research.