Low-Rank Adaptation (LoRA) is widely used for adapting large language models (LLMs) to specific domains due to its efficiency and modularity. However, vanilla LoRA struggles with task conflicts in multi-task scenarios. Recent works adopt Mixture of Experts (MoE) by treating each LoRA module as an expert, thereby mitigating task interference through multiple specialized LoRA modules. While effective, these methods often isolate knowledge within individual tasks, failing to fully exploit the shared knowledge across related tasks. In this paper, we establish a connection between single LoRA and multi-LoRA MoE, integrating them into a unified framework. We demonstrate that the dynamic routing of multiple LoRAs is functionally equivalent to rank partitioning and block-level activation within a single LoRA. To systematically study the role of expert granularity in multi-task learning, we conduct an in-depth investigation within our unified framework. Our empirical results show that a finer-grained expert partitioning not only yields significant performance gains but also captures more diverse parameter patterns. These empirical findings are supported by our theoretical analysis, which proves that finer granularity expands parameter space diversity and tightens the model's error bound. Building on these findings, we propose Single-ranked Mixture of Experts LoRA (SMoRA ), which embeds MoE into LoRA by treating each rank as an independent expert. With a dynamic rank-wise activation mechanism, SMoRA facilitates a flexible composition of knowledge, enabling the model to learn deeper and more diverse features while mitigating task conflicts. Experiments demonstrate that SMoRA activates fewer parameters yet achieves better performance in multi-task scenarios.

We present InsQABench-the first comprehensive benchmark for evaluating LLMs’ capabilities in Chinese insurance QA. InsQABench comprises 95K carefully curated QA pairs derived from real-world insurance documents, covering 3 distinct tasks, 44 question types, and 55 specialized insurance topics. Our experiments evaluated and reported the performance of mainstream LLMs under both fine-tuned and zero-shot settings, demonstrating that fine-tuning on InsQABench can significantly improve model performance. We also introduced two frameworks that further enhanced task-specific performance, achieving 4.91% and 5.11% enhancement in accuracy over the next best-performing model.

Recent research has shed light on the capabilities of Large Multimodal Models (LMMs) across various general vision and language tasks. The performance of LMMs in specialized domains, such as social media, which integrates text, images, videos, and sometimes audio, remains an area of active interest. Effective analysis of such content requires models to interpret the complex interactions between different communication modalities and their influence on the conveyed message. This article explores GPT-4V(ision)’s performance in social multimedia analysis. We evaluate GPT-4V across five representative tasks: sentiment analysis, hate speech detection, fake news identification, demographic inference, and political ideology detection. Our approach includes a preliminary quantitative analysis for each task using existing benchmark datasets, followed by a review of the results and a selection of qualitative samples to demonstrate GPT-4V’s performance in multimodal social media content analysis. GPT-4V shows effectiveness in these tasks, exhibiting capabilities like joint image–text understanding, contextual and cultural awareness, and commonsense knowledge application. However, challenges persist, including struggles with multilingual social multimedia comprehension and difficulty in adapting to the latest social media trends. It also sometimes generates incorrect information about evolving knowledge of celebrities and politicians. This preliminary study aims to inform further research across disciplines, particularly in computational social science and social media studies. The findings highlight the potential of LMMs to enhance our understanding of social media content and its users through multimodal analysis. All images and prompts used in this study will be available at https://github.com/VIStA-H/GPT-4V_Social_Media .

Leveraging Large Multimodal Models (LMMs) to simulate human behaviors when processing multimodal information, especially in the context of social media, has garnered immense interest due to its broad potential and far-reaching implications. Emojis, as one of the most unique aspects of digital communication, are pivotal in enriching and often clarifying the emotional and tonal dimensions. Yet, there is a notable gap in understanding how these advanced models, such as GPT-4V, interpret and employ emojis in the nuanced context of online interaction. This study intends to bridge this gap by examining the behavior of GPT-4V in replicating human-like use of emojis. The findings reveal a discernible discrepancy between human and GPT-4V behaviors, likely due to the subjective nature of human interpretation and the limitations of GPT-4V's English-centric training, suggesting cultural biases and inadequate representation of non-English cultures.

Large Language Models (LLMs) have revolutionized solutions for general natural language processing (NLP) tasks. However, deploying these models in specific domains still faces challenges like hallucination. While existing knowledge graph retrieval-based approaches offer partial solutions, they cannot be well adapted to the political domain. On one hand, existing generic knowledge graphs lack vital political context, hindering deductions for practical tasks. On the other hand, the nature of political questions often renders the direct facts elusive, necessitating deeper aggregation and comprehension of retrieved evidence. To address these challenges, we propose a Political Experts through Knowledge Graph Integration (PEG) framework. PEG entails the creation and utilization of a multi-view political knowledge graph (MVPKG), which integrates U.S. legislative, election, and diplomatic data, as well as conceptual knowledge from Wikidata. With MVPKG as its foundation, PEG enhances existing methods through knowledge acquisition, aggregation, and injection. This process begins with refining evidence through semantic filtering, followed by its aggregation into global knowledge via implicit or explicit methods. The integrated knowledge is then utilized by LLMs through prompts. Experiments on three real-world datasets across diverse LLMs confirm PEG's superiority in tackling political modeling tasks.

Existing research for image text retrieval mainly relies on sentence-level supervision to distinguish matched and mismatched sentences for a query image. However, semantic mismatch between an image and sentences usually happens in finer grain, i.e., phrase level. In this paper, we explore to introduce additional phrase-level supervision for the better identification of mismatched units in the text. In practice, multi-grained semantic labels are automatically constructed for a query image in both sentence-level and phrase-level. We construct text scene graphs for the matched sentences and extract entities and triples as the phrase-level labels. In order to integrate both supervision of sentence-level and phrase-level, we propose Semantic Structure Aware Multimodal Transformer (SSAMT) for multi-modal representation learning. Inside the SSAMT, we utilize different kinds of attention mechanisms to enforce interactions of multi-grained semantic units in both sides of vision and language. For the training, we propose multi-scale matching from both global and local perspectives, and penalize mismatched phrases. Experimental results on MS-COCO and Flickr30K show the effectiveness of our approach compared to some state-of-the-art models.

Existing system dealing with online complaint provides a final decision without explanations. We propose to analyse the complaint text of internet fraud in a fine-grained manner. Considering the complaint text includes multiple clauses with various functions, we propose to identify the role of each clause and classify them into different types of fraud element. We construct a large labeled dataset originated from a real finance service platform. We build an element identification model on top of BERT and propose additional two modules to utilize the context of complaint text for better element label classification, namely, global context encoder and label refiner. Experimental results show the effectiveness of our model.

Users usually consult the manufacturers or the internet when they encounter operation questions with an electronics product. In this paper, we explore to represent an operation question as a procedure graph and formulate the problem of operation diagnosis as two sub-tasks, namely error node detection, and correction, on top of the graph. We construct the first benchmark for this task and propose a transformer-based model to integrate external knowledge and context information to enhance the performance. Experimental results show the effectiveness of our proposed model.

This paper focuses on a novel financial event prediction task that takes a historical event chain as input and predicts what event will happen next. We introduce financial news as supplementary information to solve problems of multiple interpretations of same financial event. Besides, a gated graph neural network based approach is utilized to capture complicated relationships between event graphs for better event prediction. For the evaluation, we build a new dataset consisting of financial events for thousands of Chinese listed companies from 2013 to 2017. Experimental results show the effectiveness of our proposed model.

In this paper, we propose to incorporate information of related corporations of a target company for its stock price prediction. We first construct a graph including all involved corporations based on investment facts from real market and learn a distributed representation for each corporation via node embedding methods applied on the graph. Two approaches are then explored to utilize information of related corporations based on a pipeline model and a joint model via graph convolutional neural networks respectively. Experiments on the data collected from stock market in Mainland China show that the representation learned from our model is able to capture relationships between corporations, and prediction models incorporating related corporations' information are able to make more accurate predictions on stock market.

Automatically identifying rumors from online social media especially microblogging websites is an important research issue. Most of existing work for rumor detection focuses on modeling features related to microblog contents, users and propagation patterns, but ignore the importance of the variation of these social context features during the message propagation over time. In this study, we propose a novel approach to capture the temporal characteristics of these features based on the time series of rumor's lifecycle, for which time series modeling technique is applied to incorporate various social context information. Our experiments using the events in two microblog datasets confirm that the method outperforms state-of-the-art rumor detection approaches by large margins. Moreover, our model demonstrates strong performance on detecting rumors at early stage after their initial broadcast.

Single-document summarization is a challenging task. In this paper, we explore effective ways using the tweets linking to news for generating extractive summary of each document. We reveal the very basic value of tweets that can be utilized by regarding every tweet as a vote for candidate sentences. Base on such finding, we resort to unsupervised summarization models by leveraging the linking tweets to master the ranking of candidate extracts via random walk on a heterogeneous graph. The advantage is that we can use the linking tweets to opportunistically "supervise" the summarization with no need of reference summaries. Furthermore, we analyze the influence of the volume and latency of tweets on the quality of output summaries since tweets come after news release. Compared to truly supervised summarizer unaware of tweets, our method achieves significantly better results with reasonably small tradeoff on latency; compared to the same using tweets as auxiliary features, our method is comparable while needing less tweets and much shorter time to achieve significant outperformance.