VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation

Large multimodal models (LMMs) with advanced video analysis capabilities have recently garnered significant attention. However, most evaluations rely on traditional methods like multiple-choice questions in benchmarks such as VideoMME and LongVideoBench, which are prone to lack the depth needed to capture the complex demands of real-world users. To address this limitation-and due to the prohibitive cost and slow pace of human annotation for video tasks-we introduce VideoAutoArena, an arena-style benchmark inspired by LMSYS Chatbot Arena's framework, designed to automatically assess LMMs' video analysis abilities. VideoAutoArena utilizes user simulation to generate open-ended, adaptive questions that rigorously assess model performance in video understanding. The benchmark features an automated, scalable evaluation framework, incorporating a modified ELO Rating System for fair and continuous comparisons across multiple LMMs. To validate our automated judging system, we construct a 'gold standard' using a carefully curated subset of human annotations, demonstrating that our arena strongly aligns with human judgment while maintaining scalability. Additionally, we introduce a fault-driven evolution strategy, progressively increasing question complexity to push models toward handling more challenging video analysis scenarios. Experimental results demonstrate that VideoAutoArena effectively differentiates among state-of-the-art LMMs, providing insights into model strengths and areas for improvement. To further streamline our evaluation, we introduce VideoAutoBench as an auxiliary benchmark, where human annotators label winners in a subset of VideoAutoArena battles. We use GPT-4o as a judge to compare responses against these human-validated answers. Together, VideoAutoArena and VideoAutoBench offer a cost-effective, and scalable framework for evaluating LMMs in user-centric video analysis.

From General to Specific: Utilizing General Hallucation to Automatically Measure the Role Relationship Fidelity for Specific Role-Play Agents

The advanced role-playing capabilities of Large Language Models (LLMs) have paved the way for developing Role-Playing Agents (RPAs). However, existing benchmarks, such as HPD, which incorporates manually scored character relationships into the context for LLMs to sort coherence, and SocialBench, which uses specific profiles generated by LLMs in the context of multiple-choice tasks to assess character preferences, face limitations like poor generalizability, implicit and inaccurate judgments, and excessive context length. To address the above issues, we propose an automatic, scalable, and generalizable paradigm. Specifically, we construct a benchmark by extracting relations from a general knowledge graph and leverage RPA's inherent hallucination properties to prompt it to interact across roles, employing ChatGPT for stance detection and defining relationship hallucination along with three related metrics. Extensive experiments validate the effectiveness and stability of our metrics. Our findings further explore factors influencing these metrics and discuss the trade-off between relationship hallucination and factuality.

Towards Low-Resource Harmful Meme Detection with LMM Agents

The proliferation of Internet memes in the age of social media necessitates effective identification of harmful ones. Due to the dynamic nature of memes, existing data-driven models may struggle in low-resource scenarios where only a few labeled examples are available. In this paper, we propose an agency-driven framework for low-resource harmful meme detection, employing both outward and inward analysis with few-shot annotated samples. Inspired by the powerful capacity of Large Multimodal Models (LMMs) on multimodal reasoning, we first retrieve relative memes with annotations to leverage label information as auxiliary signals for the LMM agent. Then, we elicit knowledge-revising behavior within the LMM agent to derive well-generalized insights into meme harmfulness. By combining these strategies, our approach enables dialectical reasoning over intricate and implicit harm-indicative patterns. Extensive experiments conducted on three meme datasets demonstrate that our proposed approach achieves superior performance than state-of-the-art methods on the low-resource harmful meme detection task.

AMR-Evol: Adaptive Modular Response Evolution Elicits Better Knowledge Distillation for Large Language Models in Code Generation

The impressive performance of proprietary LLMs like GPT4 in code generation has led to a trend to replicate these capabilities in open-source models through knowledge distillation (e.g. Code Evol-Instruct). However, these efforts often neglect the crucial aspect of response quality, relying heavily on teacher models for direct response distillation. This paradigm, especially for complex instructions, can degrade the quality of synthesized data, compromising the knowledge distillation process. To this end, our study introduces the Adaptive Modular Response Evolution (AMR-Evol) framework, which employs a two-stage process to refine response distillation. The first stage, modular decomposition, breaks down the direct response into more manageable sub-modules. The second stage, adaptive response evolution, automatically evolves the response with the related function modules. Our experiments with three popular code benchmarks (HumanEval, MBPP, and EvalPlus) attest to the superiority of the AMR-Evol framework over baseline response distillation methods. By comparing with the open-source Code LLMs trained on a similar scale of data, we observed performance enhancements: more than +3.0 points on HumanEval-Plus and +1.0 points on MBPP-Plus, which underscores the effectiveness of our framework. Our codes are available at https://github.com/ChiYeungLaw/AMR-Evol.

CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?

Recent advancements in large language models (LLMs) have showcased impressive code generation capabilities, primarily evaluated through language-to-code benchmarks. However, these benchmarks may not fully capture a model's code understanding abilities. We introduce CodeJudge-Eval (CJ-Eval), a novel benchmark designed to assess LLMs' code understanding abilities from the perspective of code judging rather than code generation. CJ-Eval challenges models to determine the correctness of provided code solutions, encompassing various error types and compilation issues. By leveraging a diverse set of problems and a fine-grained judging system, CJ-Eval addresses the limitations of traditional benchmarks, including the potential memorization of solutions. Evaluation of 12 well-known LLMs on CJ-Eval reveals that even state-of-the-art models struggle, highlighting the benchmark's ability to probe deeper into models' code understanding abilities. Our benchmark will be available at \url{https://github.com/CodeLLM-Research/CodeJudge-Eval}.

MFC-Bench: Benchmarking Multimodal Fact-Checking with Large Vision-Language Models

Large vision-language models (LVLMs) have significantly improved multimodal reasoning tasks, such as visual question answering and image captioning. These models embed multimodal facts within their parameters, rather than relying on external knowledge bases to store factual information explicitly. However, the content discerned by LVLMs may deviate from actual facts due to inherent bias or incorrect inference. To address this issue, we introduce MFC-Bench, a rigorous and comprehensive benchmark designed to evaluate the factual accuracy of LVLMs across three tasks: Manipulation, Out-of-Context, and Veracity Classification. Through our evaluation on MFC-Bench, we benchmarked 12 diverse and representative LVLMs, uncovering that current models still fall short in multimodal fact-checking and demonstrate insensitivity to various forms of manipulated content. We hope that MFC-Bench could raise attention to the trustworthy artificial intelligence potentially assisted by LVLMs in the future. The MFC-Bench and accompanying resources are publicly accessible at https://github.com/wskbest/MFC-Bench, contributing to ongoing research in the multimodal fact-checking field.

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

In this paper, we present the VideoLLaMA 2, a set of Video Large Language Models (Video-LLMs) designed to enhance spatial-temporal modeling and audio understanding in video and audio-oriented tasks. Building upon its predecessor, VideoLLaMA 2 incorporates a tailor-made Spatial-Temporal Convolution (STC) connector, which effectively captures the intricate spatial and temporal dynamics of video data. Additionally, we integrate an Audio Branch into the model through joint training, thereby enriching the multimodal understanding capabilities of the model by seamlessly incorporating audio cues. Comprehensive evaluations on multiple-choice video question answering (MC-VQA), open-ended video question answering (OE-VQA), and video captioning (VC) tasks demonstrate that VideoLLaMA 2 consistently achieves competitive results among open-source models and even gets close to some proprietary models on several benchmarks. Furthermore, VideoLLaMA 2 exhibits reasonable improvements in audio-only and audio-video question-answering (AQA & OE-AVQA) benchmarks over existing models. These advancements underline VideoLLaMA 2's superior performance in multimodal comprehension, setting a new standard for intelligent video analysis systems. All models are public to facilitate further research.

CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal Models

Social media abounds with multimodal sarcasm, and identifying sarcasm targets is particularly challenging due to the implicit incongruity not directly evident in the text and image modalities. Current methods for Multimodal Sarcasm Target Identification (MSTI) predominantly focus on superficial indicators in an end-to-end manner, overlooking the nuanced understanding of multimodal sarcasm conveyed through both the text and image. This paper proposes a versatile MSTI framework with a coarse-to-fine paradigm, by augmenting sarcasm explainability with reasoning and pre-training knowledge. Inspired by the powerful capacity of Large Multimodal Models (LMMs) on multimodal reasoning, we first engage LMMs to generate competing rationales for coarser-grained pre-training of a small language model on multimodal sarcasm detection. We then propose fine-tuning the model for finer-grained sarcasm target identification. Our framework is thus empowered to adeptly unveil the intricate targets within multimodal sarcasm and mitigate the negative impact posed by potential noise inherently in LMMs. Experimental results demonstrate that our model far outperforms state-of-the-art MSTI methods, and markedly exhibits explainability in deciphering sarcasm as well.

CodeHalu: Code Hallucinations in LLMs Driven by Execution-based Verification

Large Language Models (LLMs) have made significant advancements in the field of code generation, offering unprecedented support for automated programming and assisting developers. However, LLMs sometimes generate code that appears plausible but fails to meet the expected requirements or executes incorrectly. This phenomenon of hallucinations in the coding field has not been explored. To advance the community's understanding and research on code hallucinations in LLMs, we propose a definition method for these hallucinations based on execution verification and introduce the concept of code hallucinations for the first time. We categorize code hallucinations into four main types: mapping, naming, resource, and logic hallucinations, each further divided into different subcategories to better understand and address the unique challenges faced by LLMs during code generation. To systematically evaluate code hallucinations, we propose a dynamic detection algorithm for code hallucinations and construct the CodeHalu benchmark, which includes 8,883 samples from 699 tasks, to actively detect hallucination phenomena in LLMs during programming. We tested 16 popular LLMs on this benchmark to evaluate the frequency and nature of their hallucinations during code generation. The findings reveal significant variations in the accuracy and reliability of LLMs in generating code, highlighting the urgent need to improve models and training methods to ensure the functional correctness and safety of automatically generated code. This study not only classifies and quantifies code hallucinations but also provides insights for future improvements in LLM-based code generation research. The CodeHalu benchmark and code are publicly available at https://github.com/yuchen814/CodeHalu.

MMCode: Evaluating Multi-Modal Code Large Language Models with Visually Rich Programming Problems

Programming often involves converting detailed and complex specifications into code, a process during which developers typically utilize visual aids to more effectively convey concepts. While recent developments in Large Multimodal Models have demonstrated remarkable abilities in visual reasoning and mathematical tasks, there is little work on investigating whether these models can effectively interpret visual elements for code generation. To this end, we present MMCode, the first multi-modal coding dataset for evaluating algorithmic problem-solving skills in visually rich contexts. MMCode contains 3,548 questions and 6,620 images collected from real-world programming challenges harvested from 10 code competition websites, presenting significant challenges due to the extreme demand for reasoning abilities. Our experiment results show that current state-of-the-art models struggle to solve these problems. The results highlight the lack of powerful vision-code models, and we hope MMCode can serve as an inspiration for future works in this domain. The data and code are publicly available at https://github.com/happylkx/MMCode.