MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs

Recent large language models (LLMs) have demonstrated versatile capabilities in long-context scenarios. Although some recent benchmarks have been developed to evaluate the long-context capabilities of LLMs, there is a lack of benchmarks evaluating the mathematical reasoning abilities of LLMs over long contexts, which is crucial for LLMs' application in real-world scenarios. In this paper, we introduce MathHay, an automated benchmark designed to assess the long-context mathematical reasoning capabilities of LLMs. Unlike previous benchmarks like Needle in a Haystack, which focus primarily on information retrieval within long texts, MathHay demands models with both information-seeking and complex mathematical reasoning abilities. We conduct extensive experiments on MathHay to assess the long-context mathematical reasoning abilities of eight top-performing LLMs. Even the best-performing model, Gemini-1.5-Pro-002, still struggles with mathematical reasoning over long contexts, achieving only 51.26% accuracy at 128K tokens. This highlights the significant room for improvement on the MathHay benchmark.

Speaker Verification in Agent-Generated Conversations

The recent success of large language models (LLMs) has attracted widespread interest to develop role-playing conversational agents personalized to the characteristics and styles of different speakers to enhance their abilities to perform both general and special purpose dialogue tasks. However, the ability to personalize the generated utterances to speakers, whether conducted by human or LLM, has not been well studied. To bridge this gap, our study introduces a novel evaluation challenge: speaker verification in agent-generated conversations, which aimed to verify whether two sets of utterances originate from the same speaker. To this end, we assemble a large dataset collection encompassing thousands of speakers and their utterances. We also develop and evaluate speaker verification models under experiment setups. We further utilize the speaker verification models to evaluate the personalization abilities of LLM-based role-playing models. Comprehensive experiments suggest that the current role-playing models fail in accurately mimicking speakers, primarily due to their inherent linguistic characteristics.

OVFoodSeg: Elevating Open-Vocabulary Food Image Segmentation via Image-Informed Textual Representation

In the realm of food computing, segmenting ingredients from images poses substantial challenges due to the large intra-class variance among the same ingredients, the emergence of new ingredients, and the high annotation costs associated with large food segmentation datasets. Existing approaches primarily utilize a closed-vocabulary and static text embeddings setting. These methods often fall short in effectively handling the ingredients, particularly new and diverse ones. In response to these limitations, we introduce OVFoodSeg, a framework that adopts an open-vocabulary setting and enhances text embeddings with visual context. By integrating vision-language models (VLMs), our approach enriches text embedding with image-specific information through two innovative modules, eg, an image-to-text learner FoodLearner and an Image-Informed Text Encoder. The training process of OVFoodSeg is divided into two stages: the pre-training of FoodLearner and the subsequent learning phase for segmentation. The pre-training phase equips FoodLearner with the capability to align visual information with corresponding textual representations that are specifically related to food, while the second phase adapts both the FoodLearner and the Image-Informed Text Encoder for the segmentation task. By addressing the deficiencies of previous models, OVFoodSeg demonstrates a significant improvement, achieving an 4.9\% increase in mean Intersection over Union (mIoU) on the FoodSeg103 dataset, setting a new milestone for food image segmentation.

The Whole is Better than the Sum: Using Aggregated Demonstrations in In-Context Learning for Sequential Recommendation

Large language models (LLMs) have shown excellent performance on various NLP tasks. To use LLMs as strong sequential recommenders, we explore the in-context learning approach to sequential recommendation. We investigate the effects of instruction format, task consistency, demonstration selection, and number of demonstrations. As increasing the number of demonstrations in ICL does not improve accuracy despite using a long prompt, we propose a novel method called LLMSRec-Syn that incorporates multiple demonstration users into one aggregated demonstration. Our experiments on three recommendation datasets show that LLMSRec-Syn outperforms state-of-the-art LLM-based sequential recommendation methods. In some cases, LLMSRec-Syn can perform on par with or even better than supervised learning methods. Our code is publicly available at https://github.com/demoleiwang/LLMSRec_Syn.

All in a Single Image: Large Multimodal Models are In-Image Learners

This paper introduces a new in-context learning (ICL) mechanism called In-Image Learning (I$^2$L) that combines demonstration examples, visual cues, and instructions into a single image to enhance the capabilities of GPT-4V. Unlike previous approaches that rely on converting images to text or incorporating visual input into language models, I$^2$L consolidates all information into one image and primarily leverages image processing, understanding, and reasoning abilities. This has several advantages: it avoids inaccurate textual descriptions of complex images, provides flexibility in positioning demonstration examples, reduces the input burden, and avoids exceeding input limits by eliminating the need for multiple images and lengthy text. To further combine the strengths of different ICL methods, we introduce an automatic strategy to select the appropriate ICL method for a data example in a given task. We conducted experiments on MathVista and Hallusionbench to test the effectiveness of I$^2$L in complex multimodal reasoning tasks and mitigating language hallucination and visual illusion. Additionally, we explored the impact of image resolution, the number of demonstration examples, and their positions on the effectiveness of I$^2$L. Our code is publicly available at https://github.com/AGI-Edgerunners/IIL.

Generative Semi-supervised Graph Anomaly Detection

This work considers a practical semi-supervised graph anomaly detection (GAD) scenario, where part of the nodes in a graph are known to be normal, contrasting to the unsupervised setting in most GAD studies with a fully unlabeled graph. As expected, we find that having access to these normal nodes helps enhance the detection performance of existing unsupervised GAD methods when they are adapted to the semi-supervised setting. However, their utilization of these normal nodes is limited. In this paper, we propose a novel Generative GAD approach (GGAD) for the semi-supervised scenario to better exploit the normal nodes. The key idea is to generate outlier nodes that assimilate anomaly nodes in both local structure and node representations for providing effective negative node samples in training a discriminative one-class classifier. There have been many generative anomaly detection approaches, but they are designed for non-graph data, and as a result, they fail to take account of the graph structure information. Our approach tackles this problem by generating graph structure-aware outlier nodes that have asymmetric affinity separability from normal nodes while being enforced to achieve egocentric closeness to normal nodes in the node representation space. Comprehensive experiments on four real-world datasets are performed to establish a benchmark for semi-supervised GAD and show that GGAD substantially outperforms state-of-the-art unsupervised and semi-supervised GAD methods with varying numbers of training normal nodes. Code will be made available at https://github.com/mala-lab/GGAD.

Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewrites

Large language models (LLMs) have shown remarkable performance in natural language processing (NLP) tasks. To comprehend and execute diverse human instructions over image data, instruction-tuned large vision-language models (LVLMs) have been introduced. However, LVLMs may suffer from different types of object hallucinations. Nevertheless, LVLMs are evaluated for coarse-grained object hallucinations only (i.e., generated objects non-existent in the input image). The fine-grained object attributes and behaviors non-existent in the image may still be generated but not measured by the current evaluation methods. In this paper, we thus focus on reducing fine-grained hallucinations of LVLMs. We propose \textit{ReCaption}, a framework that consists of two components: rewriting captions using ChatGPT and fine-tuning the instruction-tuned LVLMs on the rewritten captions. We also propose a fine-grained probing-based evaluation method named \textit{Fine-Grained Object Hallucination Evaluation} (\textit{FGHE}). Our experiment results demonstrate that ReCaption effectively reduces fine-grained object hallucination for different LVLM options and improves their text generation quality. The code can be found at https://github.com/Anonymousanoy/FOHE.

On Exploring the Reasoning Capability of Large Language Models with Knowledge Graphs

This paper examines the capacity of LLMs to reason with knowledge graphs using their internal knowledge graph, i.e., the knowledge graph they learned during pre-training. Two research questions are formulated to investigate the accuracy of LLMs in recalling information from pre-training knowledge graphs and their ability to infer knowledge graph relations from context. To address these questions, we employ LLMs to perform four distinct knowledge graph reasoning tasks. Furthermore, we identify two types of hallucinations that may occur during knowledge reasoning with LLMs: content and ontology hallucination. Our experimental results demonstrate that LLMs can successfully tackle both simple and complex knowledge graph reasoning tasks from their own memory, as well as infer from input context.

LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay

This paper aims to investigate the open research problem of uncovering the social behaviors of LLM-based agents. To achieve this goal, we adopt Avalon, a representative communication game, as the environment and use system prompts to guide LLM agents to play the game. While previous studies have conducted preliminary investigations into gameplay with LLM agents, there lacks research on their social behaviors. In this paper, we present a novel framework designed to seamlessly adapt to Avalon gameplay. The core of our proposed framework is a multi-agent system that enables efficient communication and interaction among agents. We evaluate the performance of our framework based on metrics from two perspectives: winning the game and analyzing the social behaviors of LLM agents. Our results demonstrate the effectiveness of our framework in generating adaptive and intelligent agents and highlight the potential of LLM-based agents in addressing the challenges associated with dynamic social environment interaction. By analyzing the social behaviors of LLM agents from the aspects of both collaboration and confrontation, we provide insights into the research and applications of this domain.

LLM4Vis: Explainable Visualization Recommendation using ChatGPT

Data visualization is a powerful tool for exploring and communicating insights in various domains. To automate visualization choice for datasets, a task known as visualization recommendation has been proposed. Various machine-learning-based approaches have been developed for this purpose, but they often require a large corpus of dataset-visualization pairs for training and lack natural explanations for their results. To address this research gap, we propose LLM4Vis, a novel ChatGPT-based prompting approach to perform visualization recommendation and return human-like explanations using very few demonstration examples. Our approach involves feature description, demonstration example selection, explanation generation, demonstration example construction, and inference steps. To obtain demonstration examples with high-quality explanations, we propose a new explanation generation bootstrapping to iteratively refine generated explanations by considering the previous generation and template-based hint. Evaluations on the VizML dataset show that LLM4Vis outperforms or performs similarly to supervised learning models like Random Forest, Decision Tree, and MLP in both few-shot and zero-shot settings. The qualitative evaluation also shows the effectiveness of explanations generated by LLM4Vis. We make our code publicly available at \href{https://github.com/demoleiwang/LLM4Vis}{https://github.com/demoleiwang/LLM4Vis}.