This paper studies the limitations of (retrieval-augmented) large language models (LLMs) in generating diverse and comprehensive responses, and introduces the Plan-and-Refine (P&R) framework based on a two phase system design. In the global exploration phase, P&R generates a diverse set of plans for the given input, where each plan consists of a list of diverse query aspects with corresponding additional descriptions. This phase is followed by a local exploitation phase that generates a response proposal for the input query conditioned on each plan and iteratively refines the proposal for improving the proposal quality. Finally, a reward model is employed to select the proposal with the highest factuality and coverage. We conduct our experiments based on the ICAT evaluation methodology--a recent approach for answer factuality and comprehensiveness evaluation. Experiments on the two diverse information seeking benchmarks adopted from non-factoid question answering and TREC search result diversification tasks demonstrate that P&R significantly outperforms baselines, achieving up to a 13.1% improvement on the ANTIQUE dataset and a 15.41% improvement on the TREC dataset. Furthermore, a smaller scale user study confirms the substantial efficacy of the P&R framework.

Video-based Large Language Models (Video-LLMs) have witnessed substantial advancements in recent years, propelled by the advancement in multi-modal LLMs. Although these models have demonstrated proficiency in providing the overall description of videos, they struggle with fine-grained understanding, particularly in aspects such as visual dynamics and video details inquiries. T o tackle these shortcomings, we find that fine-tuning Video-LLMs on self-supervised fragment tasks, greatly improve their fine-grained video understanding abilities. Hence we propose two key contributions: (1) Self-Supervised Fragment Fine-Tuning (SF 2 T), a novel effortless fine-tuning method, employs the rich inherent characteristics of videos for training, while unlocking more fine-grained understanding ability of Video-LLMs. Moreover, it relieves researchers from labor-intensive annotations and smartly circumvents the limitations of natural language, which often fails to capture the complex spatiotemporal variations in videos; (2) A novel benchmark dataset, namely FineVidBench, for rigorously assessing Video-LLMs' performance at both the scene and fragment levels, offering a comprehensive evaluation of their capabilities. W e assessed multiple models and validated the effectiveness of SF 2 T on them. Experimental results reveal that our approach improves their ability to capture and interpret spatiotemporal details. 1. Introduction Large Language Models (LLMs) have showcased significant emergent capabilities, such as in-context learning [19], instruction-following [23], and chain-of-thought reasoning [30], driven by expansive datasets and advanced model architectures. Performance w/ and w/o SF 2 T .We evaluated four advanced Video-LLMs w/ and w/o SF 2 T on our proposed FineV - idBench with two baselines: (1) Base: performance without any fine-tuning (blue dashed), and (2) Base (SFT): performance with supervised fine-tuning (red dashed). After applying SF 2 T, all models showed significant improvements (solid blue and red), underscoring its broad effectiveness. V arious Video-LLMs, exemplified by GPT4-V, VideoL-LaMA 2 [4], MiniCPM-V [34], and Qwen2-VL [28], have been crafted by leading corporations and research institutions, demonstrating proficiency in capturing the overar-ching content of videos.

Code search aims to retrieve semantically relevant code snippets for natural language queries. While pre-trained language models (PLMs) have shown remarkable performance in this task, they struggle in cross-domain scenarios, often requiring costly fine-tuning or facing performance drops in zero-shot settings. RAPID, which generates synthetic data for model fine-tuning, is currently the only effective method for zero-shot cross-domain code search. Despite its effectiveness, RAPID demands substantial computational resources for fine-tuning and needs to maintain specialized models for each domain, underscoring the need for a zero-shot, fine-tuning-free approach for cross-domain code search. The key to tackling zero-shot cross-domain code search lies in bridging the gaps among domains. In this work, we propose to break the query-code matching process of code search into two simpler tasks: query-comment matching and code-code matching. Our empirical study reveals the strong complementarity among the three matching schemas in zero-shot cross-domain settings, i.e., query-code, query-comment, and code-code matching. Based on the findings, we propose CodeBridge, a zero-shot, fine-tuning-free approach for cross-domain code search. Specifically, CodeBridge uses Large Language Models (LLMs) to generate comments and pseudo-code, then combines query-code, query-comment, and code-code matching via PLM-based similarity scoring and sampling-based fusion. Experimental results show that our approach outperforms the state-of-the-art PLM-based code search approaches, i.e., CoCoSoDa and UniXcoder, by an average of 21.4% and 24.9% in MRR, respectively, across three datasets. Our approach also yields results that are better than or comparable to those of the zero-shot cross-domain code search approach RAPID, which requires costly fine-tuning.

D EEPG REEN: E FFECTIVE LLM-D RIVEN G REEN-WASHING M ONITORING S YSTEM D ESIGNED FOR E MPIRICAL T ESTING --E VIDENCE FROM C HINA Congluo Xu Business School Sichuan University Chengdu, 610065 Y u Miao School of Economics Sichuan University Chengdu, 610065 Yiling Xiao Business School Sichuan University Chengdu, 610065 Chengmengjia Lin Business School Sichuan University Chengdu, 610065 April 11, 2025 A BSTRACT This paper proposes DeepGreen, an Large Language Model Driven (LLM-Driven) system for detecting corporate green-washing behaviour. Utilizing dual-layer LLM analysis, DeepGreen preliminar-ily identifies potential green keywords in financial statements and then assesses their implementation degree via iterative semantic analysis of LLM. A core variable GreenImplement is derived from the ratio from the two layers' output. We extract 204 financial statements of 68 companies from A-share market over three years, comprising 89,893 words, and analyse them through DeepGreen. Our analysis, supported by violin plots and K-means clustering, reveals insights and validates the variable against the Huazheng ESG rating. It offers a novel perspective for regulatory agencies and investors, serving as a proactive monitoring tool that complements traditional methods.Empirical tests show that green implementation can significantly boost the asset return rate of companies, but there is heterogeneity in scale. Small and medium-sized companies have limited contribution to asset return via green implementation, so there is a stronger motivation for green-washing. K eywords Green-washing Monitoring Large Language Models Financial Statement Analysis Unstructured Data Analysis 1 Introduction Amid intensifying global focus on sustainable development and environmental protection, the phenomenon of corporate "green-washing" has emerged as a contentious issue. "Green-washing" typically refers to those companies exaggerating or misrepresenting their environmental protection efforts in promotional materials, while their actual practices fail to meet sustainable development standards [1]. However, a more elusive challenge lies in "general green-washing", which involves subtler tactics that distort perceptions by repeatedly invoking terms such as "carbon peak" or "green development" without substantive evidence [2]. The elusiveness of general green-washing stems from its exploitation of human psychology and information processing mechanisms.

Chat-oriented dialogue systems designed to provide tangible benefits, such as sharing the latest news or preventing frailty in senior citizens, often require Proactive acquisition of specific user Information via chats on user-faVOred Topics (PIVOT). This study proposes the PIVOT task, designed to advance the technical foundation for these systems. In this task, a system needs to acquire the answers of a user to predefined questions without making the user feel abrupt while engaging in a chat on a predefined topic. We found that even recent large language models (LLMs) show a low success rate in the PIVOT task. We constructed a dataset suitable for the analysis to develop more effective systems. Finally, we developed a simple but effective system for this task by incorporating insights obtained through the analysis of this dataset.

This study examines hallucinations in Large Language Model (LLM) translations into Irish, specifically focusing on instances where the models generate novel, non-existent words. We classify these hallucinations within verb and noun categories, identifying six distinct patterns among the latter. Additionally, we analyse whether these hallucinations adhere to Irish morphological rules and what linguistic tendencies they exhibit. Our findings show that while both GPT-4.o and GPT-4.o Mini produce similar types of hallucinations, the Mini model generates them at a significantly higher frequency. Beyond classification, the discussion raises speculative questions about the implications of these hallucinations for the Irish language. Rather than seeking definitive answers, we offer food for thought regarding the increasing use of LLMs and their potential role in shaping Irish vocabulary and linguistic evolution. We aim to prompt discussion on how such technologies might influence language over time, particularly in the context of low-resource, morphologically rich languages.

The Chinese Spelling Correction (CSC) task focuses on detecting and correcting spelling errors in sentences. Current research primarily explores two approaches: traditional multimodal pre-trained models and large language models (LLMs). However, LLMs face limitations in CSC, particularly over-correction, making them suboptimal for this task. While existing studies have investigated the use of phonetic and graphemic information in multimodal CSC models, effectively leveraging these features to enhance correction performance remains a challenge. To address this, we propose the Multimodal Analysis for Character Usage (\textbf{MACU}) experiment, identifying potential improvements for multimodal correctison. Based on empirical findings, we introduce \textbf{NamBert}, a novel multimodal model for Chinese spelling correction. Experiments on benchmark datasets demonstrate NamBert's superiority over SOTA methods. We also conduct a comprehensive comparison between NamBert and LLMs, systematically evaluating their strengths and limitations in CSC. Our code and model are available at https://github.com/iioSnail/NamBert.

In this paper, we introduce CollEx, an innovative multimodal agentic Retrieval-Augmented Generation (RAG) system designed to enhance interactive exploration of extensive scientific collections. Given the overwhelming volume and inherent complexity of scientific collections, conventional search systems often lack necessary intuitiveness and interactivity, presenting substantial barriers for learners, educators, and researchers. CollEx addresses these limitations by employing state-of-the-art Large Vision-Language Models (LVLMs) as multimodal agents accessible through an intuitive chat interface. By abstracting complex interactions via specialized agents equipped with advanced tools, CollEx facilitates curiosity-driven exploration, significantly simplifying access to diverse scientific collections and records therein. Our system integrates textual and visual modalities, supporting educational scenarios that are helpful for teachers, pupils, students, and researchers by fostering independent exploration as well as scientific excitement and curiosity. Furthermore, CollEx serves the research community by discovering interdisciplinary connections and complementing visual data. We illustrate the effectiveness of our system through a proof-of-concept application containing over 64,000 unique records across 32 collections from a local scientific collection from a public university.

Retrieval Augmented Generation (RAG) has enjoyed increased attention in the recent past and recent advancements in Large Language Models (LLMs) have highlighted the importance of integrating world knowledge into these systems. Current RAG methodologies often modify the internal architecture of pre-trained language models (PLMs) or rely on textifying knowledge graphs (KGs), which is inefficient in terms of token usage. This paper introduces ConceptFormer, a new approach to augment LLMs with structured knowledge from KGs, such as Wikidata, without altering their internal structure or relying on textual input of KGs. ConceptFormer operates in the LLM embedding vector space, creating and injecting \emph{concept vectors} that encapsulate the information of the KG nodes directly. Trained in conjunction with a frozen LLM, ConceptFormer generates a comprehensive lookup table that maps KG nodes to their respective concept vectors. The approach aims to enhance the factual recall capabilities of LLMs by enabling them to process these concept vectors natively, thus enriching them with structured world knowledge in an efficient and scalable manner. Our experiments demonstrate that the addition of concept vectors to GPT-2 0.1B substantially increases its factual recall ability (Hit@10) by up to 272\% when tested on sentences from Wikipedia and up to 348\% on synthetically generated sentences. Even injecting only a single concept vector into the prompt increases factual recall ability (Hit@10) by up to 213\% on Wikipedia sentences, significantly outperforming RAG with graph textification while consuming 130x fewer input tokens.

-- In the domain of autonomous household robots, it is of utmost importance for robots to understand human behaviors and provide appropriate services. This requires the robots to possess the capability to analyze complex human behaviors and predict the true intentions of humans. Traditionally, humans are perceived as flawless, with their decisions acting as the standards that robots should strive to align with. However, this raises a pertinent question: What if humans make mistakes? In this research, we present a unique task, termed "long short-term intention prediction". This task requires robots can predict the long-term intention of humans, which aligns with human values, and the short term intention of humans, which reflects the immediate action intention. Meanwhile, the robots need to detect the potential non-consistency between the short-term and long-term intentions, and provide necessary warnings and suggestions. T o facilitate this task, we propose a long short-term intention model to represent the complex intention states, and build a dataset to train this intention model. Then we propose a two-stage method to integrate the intention model for robots: i) predicting human intentions of both value-based long-term intentions and action-based short-term intentions; and 2) analyzing the consistency between the long-term and short-term intentions. Experimental results indicate that the proposed long short-term intention model can assist robots in comprehending human behavioral patterns over both long-term and short-term durations, which helps determine the consistency between long-term and short-term intentions of humans.