Understanding urban socioeconomic conditions through visual data is a challenging yet essential task for sustainable urban development and policy planning. In this work, we introduce $\textbf{CityLens}$, a comprehensive benchmark designed to evaluate the capabilities of large language-vision models (LLVMs) in predicting socioeconomic indicators from satellite and street view imagery. We construct a multi-modal dataset covering a total of 17 globally distributed cities, spanning 6 key domains: economy, education, crime, transport, health, and environment, reflecting the multifaceted nature of urban life. Based on this dataset, we define 11 prediction tasks and utilize three evaluation paradigms: Direct Metric Prediction, Normalized Metric Estimation, and Feature-Based Regression. We benchmark 17 state-of-the-art LLVMs across these tasks. Our results reveal that while LLVMs demonstrate promising perceptual and reasoning capabilities, they still exhibit limitations in predicting urban socioeconomic indicators. CityLens provides a unified framework for diagnosing these limitations and guiding future efforts in using LLVMs to understand and predict urban socioeconomic patterns. Our codes and datasets are open-sourced via https://github.com/tsinghua-fib-lab/CityLens.

Retrieval-Augmented Generation (RAG) systems in the Intellectual Property (IP) field often struggle with diverse user queries, including colloquial expressions, spelling errors, and ambiguous terminology, leading to inaccurate retrieval and suboptimal responses. To address this challenge, we propose Multi-Angle Question Generation and Retrieval Fine-Tuning Method (MQG-RFM), a novel framework that leverages large language models (LLMs) to simulate varied user inquiries and fine-tunes retrieval models to align semantically equivalent but linguistically diverse questions. Unlike complex architectural modifications, MQG-RFM adopts a lightweight Data-to-Tune paradigm, combining prompt-engineered query generation with hard negative mining to enhance retrieval robustness without costly infrastructure changes. Experimental results on a Taiwan patent Q&A dataset show 185.62% improvement in retrieval accuracy on the Patent Consultation dataset and 262.26% improvement on the Novel Patent Technology Report dataset, with 14.22% and 53.58% improvements in generation quality over the baselines, respectively. By bridging the gap between user intent and system comprehension through semantic-aware retrieval optimization, MQG-RFM offers a practical, scalable approach for rapid, cost-effective deployment among small and medium-sized agencies seeking reliable patent intelligence solutions. Additionally, our proposed method has already been adopted by ScholarMate, the largest professional research social networking platform in China, to support real-world development and deployment. A demo version of the instantiated is available at https://github.com/renruntao/patent_rag.

In commonsense generation, given a set of input concepts, a model must generate a response that is not only commonsense bearing, but also capturing multiple diverse viewpoints. Numerous evaluation metrics based on form- and content-level overlap have been proposed in prior work for evaluating the diversity of a commonsense generation model. However, it remains unclear as to which metrics are best suited for evaluating the diversity in commonsense generation. To address this gap, we conduct a systematic meta-evaluation of diversity metrics for commonsense generation. We find that form-based diversity metrics tend to consistently overestimate the diversity in sentence sets, where even randomly generated sentences are assigned overly high diversity scores. We then use an Large Language Model (LLM) to create a novel dataset annotated for the diversity of sentences generated for a commonsense generation task, and use it to conduct a meta-evaluation of the existing diversity evaluation metrics. Our experimental results show that content-based diversity evaluation metrics consistently outperform the form-based counterparts, showing high correlations with the LLM-based ratings. We recommend that future work on commonsense generation should use content-based metrics for evaluating the diversity of their outputs.

Large language models (LLMs) have demonstrated strong performance across various tasks, leveraging their exceptional in-context learning ability with only a few examples. Accordingly, the selection of optimal in-context examples has been actively studied in the field of machine translation. However, these studies presuppose the presence of a demonstration pool with human-annotated pairs, making them less applicable to low-resource languages where such an assumption is challenging to meet. To overcome this limitation, this paper explores the research direction of in-context example generation for machine translation. Specifically, we propose Demonstration Augmentation for Translation (DAT), a simple yet effective approach that generates example pairs without relying on any external resources. This method builds upon two prior criteria, relevance and diversity, which have been highlighted in previous work as key factors for in-context example selection. Through experiments and analysis on low-resource languages where human-annotated pairs are scarce, we show that DAT achieves superior translation quality compared to the baselines. Furthermore, we investigate the potential of progressively accumulating generated pairs during test time to build and reuse a demonstration pool. Our implementation is publicly available at https://github.com/aiclaudev/DAT.

Large Language Models (LLMs) can assist multimodal fake news detection by predicting pseudo labels. However, LLM-generated pseudo labels alone demonstrate poor performance compared to traditional detection methods, making their effective integration non-trivial. In this paper, we propose Global Label Propagation Network with LLM-based Pseudo Labeling (GLPN-LLM) for multimodal fake news detection, which integrates LLM capabilities via label propagation techniques. The global label propagation can utilize LLM-generated pseudo labels, enhancing prediction accuracy by propagating label information among all samples. For label propagation, a mask-based mechanism is designed to prevent label leakage during training by ensuring that training nodes do not propagate their own labels back to themselves. Experimental results on benchmark datasets show that by synergizing LLMs with label propagation, our model achieves superior performance over state-of-the-art baselines.

Multi-hop questions still stump large language models (LLMs), which struggle to link information across multiple reasoning steps. We introduce Auto-Patch, a novel method that dynamically patches hidden states during inference to enhance multi-hop reasoning in LLMs. Building on the PatchScopes framework, Auto-Patch selectively modifies internal representations using a learned classifier. Evaluated on the MuSiQue dataset, Auto-Patch improves the solve rate from 18.45\% (baseline) to 23.63~$\pm$~0.7\% (3 runs), narrowing the gap to Chain-of-Thought prompting (27.44\%). Our results highlight the potential of dynamic hidden state interventions for advancing complex reasoning in LLMs.

As large language models (LLMs) continue to advance, the need for up-to-date and well-organized benchmarks becomes increasingly critical. However, many existing datasets are scattered, difficult to manage, and make it challenging to perform evaluations tailored to specific needs or domains, despite the growing importance of domain-specific models in areas such as math or code. In this paper, we introduce BenchHub, a dynamic benchmark repository that empowers researchers and developers to evaluate LLMs more effectively. BenchHub aggregates and automatically classifies benchmark datasets from diverse domains, integrating 303K questions across 38 benchmarks. It is designed to support continuous updates and scalable data management, enabling flexible and customizable evaluation tailored to various domains or use cases. Through extensive experiments with various LLM families, we demonstrate that model performance varies significantly across domain-specific subsets, emphasizing the importance of domain-aware benchmarking. We believe BenchHub can encourage better dataset reuse, more transparent model comparisons, and easier identification of underrepresented areas in existing benchmarks, offering a critical infrastructure for advancing LLM evaluation research.

Large Vision-Language Models (LVLMs) have achieved remarkable success, yet their significant computational demands hinder practical deployment. While efforts to improve LVLM efficiency are growing, existing methods lack comprehensive evaluation across diverse backbones, benchmarks, and metrics. In this work, we systematically evaluate mainstream acceleration techniques for LVLMs, categorized into token and parameter compression. We introduce EffiVLM-Bench, a unified framework for assessing not only absolute performance but also generalization and loyalty, while exploring Pareto-optimal trade-offs. Our extensive experiments and in-depth analyses offer insights into optimal strategies for accelerating LVLMs. We open-source code and recipes for EffiVLM-Bench to foster future research.

Large Language Models (LLMs) have shown remarkable performance across diverse tasks without domain-specific training, fueling interest in their potential for time-series forecasting. While LLMs have shown potential in zero-shot forecasting through prompting alone, recent studies suggest that LLMs lack inherent effectiveness in forecasting. Given these conflicting findings, a rigorous validation is essential for drawing reliable conclusions. In this paper, we evaluate the effectiveness of LLMs as zero-shot forecasters compared to state-of-the-art domain-specific models. Our experiments show that LLM-based zero-shot forecasters often struggle to achieve high accuracy due to their sensitivity to noise, underperforming even simple domain-specific models. We have explored solutions to reduce LLMs' sensitivity to noise in the zero-shot setting, but improving their robustness remains a significant challenge. Our findings suggest that rather than emphasizing zero-shot forecasting, a more promising direction would be to focus on fine-tuning LLMs to better process numerical sequences. Our experimental code is available at https://github.com/junwoopark92/revisiting-LLMs-zeroshot-forecaster.

Hallucinations in large language models (LLMs) during summarization of patient-clinician dialogues pose significant risks to patient care and clinical decision-making. However, the phenomenon remains understudied in the clinical domain, with uncertainty surrounding the applicability of general-domain hallucination detectors. The rarity and randomness of hallucinations further complicate their investigation. In this paper, we conduct an evaluation of hallucination detection methods in the medical domain, and construct two datasets for the purpose: A fact-controlled Leave-N-out dataset -- generated by systematically removing facts from source dialogues to induce hallucinated content in summaries; and a natural hallucination dataset -- arising organically during LLM-based medical summarization. We show that general-domain detectors struggle to detect clinical hallucinations, and that performance on fact-controlled hallucinations does not reliably predict effectiveness on natural hallucinations. We then develop fact-based approaches that count hallucinations, offering explainability not available with existing methods. Notably, our LLM-based detectors, which we developed using fact-controlled hallucinations, generalize well to detecting real-world clinical hallucinations. This research contributes a suite of specialized metrics supported by expert-annotated datasets to advance faithful clinical summarization systems.