Large Language Models (LLMs) have succeeded remarkably in understanding long-form contents. However, exploring their capability for generating long-form contents, such as reports and articles, has been relatively unexplored and inadequately assessed by existing benchmarks. The prevalent evaluation methods, which predominantly rely on crowdsourcing, are recognized for their labor-intensive nature and lack of efficiency, whereas automated metrics, such as the ROUGE score, demonstrate discordance with human judgment criteria. In this paper, we propose ProxyQA, an innovative framework dedicated to assessing long-text generation. ProxyQA comprises in-depth human-curated meta-questions spanning various domains, each accompanied by specific proxy-questions with pre-annotated answers. LLMs are tasked to generate extensive content in response to these meta-questions, by engaging an evaluator and incorporating the generated texts as contextual background, ProxyQA assesses the generated content's quality through the evaluator's accuracy in addressing the proxy-questions. We examine multiple LLMs, emphasizing ProxyQA's demanding nature as a high-quality assessment tool. Human evaluation demonstrates that the proxy-question method is notably self-consistent and aligns closely with human evaluative standards. The dataset and leaderboard is available at \url{//proxy-qa.com}.
相關內容
Large Multi-modal Models (LMMs) have significantly advanced a variety of vision-language tasks. The scalability and availability of high-quality training data play a pivotal role in the success of LMMs. In the realm of food, while comprehensive food datasets such as Recipe1M offer an abundance of ingredient and recipe information, they often fall short of providing ample data for nutritional analysis. The Recipe1M+ dataset, despite offering a subset for nutritional evaluation, is limited in the scale and accuracy of nutrition information. To bridge this gap, we introduce Uni-Food, a unified food dataset that comprises over 100,000 images with various food labels, including categories, ingredients, recipes, and ingredient-level nutritional information. Uni-Food is designed to provide a more holistic approach to food data analysis, thereby enhancing the performance and capabilities of LMMs in this domain. To mitigate the conflicts arising from multi-task supervision during fine-tuning of LMMs, we introduce a novel Linear Rectification Mixture of Diverse Experts (RoDE) approach. RoDE utilizes a diverse array of experts to address tasks of varying complexity, thereby facilitating the coordination of trainable parameters, i.e., it allocates more parameters for more complex tasks and, conversely, fewer parameters for simpler tasks. RoDE implements linear rectification union to refine the router's functionality, thereby enhancing the efficiency of sparse task allocation. These design choices endow RoDE with features that ensure GPU memory efficiency and ease of optimization. Our experimental results validate the effectiveness of our proposed approach in addressing the inherent challenges of food-related multitasking.
Recently, 3D Gaussian Splatting (3DGS) has emerged as an efficient approach for accurately representing scenes. However, despite its superior novel view synthesis capabilities, extracting the geometry of the scene directly from the Gaussian properties remains a challenge, as those are optimized based on a photometric loss. While some concurrent models have tried adding geometric constraints during the Gaussian optimization process, they still produce noisy, unrealistic surfaces. We propose a novel approach for bridging the gap between the noisy 3DGS representation and the smooth 3D mesh representation, by injecting real-world knowledge into the depth extraction process. Instead of extracting the geometry of the scene directly from the Gaussian properties, we instead extract the geometry through a pre-trained stereo-matching model. We render stereo-aligned pairs of images corresponding to the original training poses, feed the pairs into a stereo model to get a depth profile, and finally fuse all of the profiles together to get a single mesh. The resulting reconstruction is smoother, more accurate and shows more intricate details compared to other methods for surface reconstruction from Gaussian Splatting, while only requiring a small overhead on top of the fairly short 3DGS optimization process. We performed extensive testing of the proposed method on in-the-wild scenes, obtained using a smartphone, showcasing its superior reconstruction abilities. Additionally, we tested the method on the Tanks and Temples and DTU benchmarks, achieving state-of-the-art results.
Machine Learning (ML) is continuously permeating a growing amount of application domains. Generative AI such as Large Language Models (LLMs) also sees broad adoption to process multi-modal data such as text, images, audio, and video. While the trend is to use ever-larger datasets for training, managing this data efficiently has become a significant practical challenge in the industry-double as much data is certainly not double as good. Rather the opposite is important since getting an understanding of the inherent quality and diversity of the underlying data lakes is a growing challenge for application-specific ML as well as for fine-tuning foundation models. Furthermore, information retrieval (IR) from expanding data lakes is complicated by the temporal dimension inherent in time-series data which must be considered to determine its semantic value. This study focuses on the different semantic-aware techniques to extract embeddings from mono-modal, multi-modal, and cross-modal data to enhance IR capabilities in a growing data lake. Articles were collected to summarize information about the state-of-the-art techniques focusing on applications of embedding for three different categories of data modalities.
Jailbreak attacks cause large language models (LLMs) to generate harmful, unethical, or otherwise objectionable content. Evaluating these attacks presents a number of challenges, which the current collection of benchmarks and evaluation techniques do not adequately address. First, there is no clear standard of practice regarding jailbreaking evaluation. Second, existing works compute costs and success rates in incomparable ways. And third, numerous works are not reproducible, as they withhold adversarial prompts, involve closed-source code, or rely on evolving proprietary APIs. To address these challenges, we introduce JailbreakBench, an open-sourced benchmark with the following components: (1) an evolving repository of state-of-the-art adversarial prompts, which we refer to as jailbreak artifacts; (2) a jailbreaking dataset comprising 100 behaviors -- both original and sourced from prior work (Zou et al., 2023; Mazeika et al., 2023, 2024) -- which align with OpenAI's usage policies; (3) a standardized evaluation framework at //github.com/JailbreakBench/jailbreakbench that includes a clearly defined threat model, system prompts, chat templates, and scoring functions; and (4) a leaderboard at //jailbreakbench.github.io/ that tracks the performance of attacks and defenses for various LLMs. We have carefully considered the potential ethical implications of releasing this benchmark, and believe that it will be a net positive for the community.
Large Language Models (LLMs) are increasingly used for boosting organizational efficiency and automating tasks. While not originally designed for complex cognitive processes, recent efforts have further extended to employ LLMs in activities such as reasoning, planning, and decision-making. In business processes, such abilities could be invaluable for leveraging on the massive corpora LLMs have been trained on for gaining deep understanding of such processes. In this work, we plant the seeds for the development of a benchmark to assess the ability of LLMs to reason about causal and process perspectives of business operations. We refer to this view as Causally-augmented Business Processes (BP^C). The core of the benchmark comprises a set of BP^C related situations, a set of questions about these situations, and a set of deductive rules employed to systematically resolve the ground truth answers to these questions. Also with the power of LLMs, the seed is then instantiated into a larger-scale set of domain-specific situations and questions. Reasoning on BP^C is of crucial importance for process interventions and process improvement. Our benchmark, accessible at //huggingface.co/datasets/ibm/BPC, can be used in one of two possible modalities: testing the performance of any target LLM and training an LLM to advance its capability to reason about BP^C.
Large Language Models (LLMs) like ChatGPT and Llama have revolutionized natural language processing and search engine dynamics. However, these models incur exceptionally high computational costs. For instance, GPT-3 consists of 175 billion parameters, where inference demands billions of floating-point operations. Caching is a natural solution to reduce LLM inference costs on repeated queries, which constitute about 31% of the total queries. However, existing caching methods are incapable of finding semantic similarities among LLM queries nor do they operate on contextual queries, leading to unacceptable false hit-and-miss rates. This paper introduces MeanCache, a user-centric semantic cache for LLM-based services that identifies semantically similar queries to determine cache hit or miss. Using MeanCache, the response to a user's semantically similar query can be retrieved from a local cache rather than re-querying the LLM, thus reducing costs, service provider load, and environmental impact. MeanCache leverages Federated Learning (FL) to collaboratively train a query similarity model without violating user privacy. By placing a local cache in each user's device and using FL, MeanCache reduces the latency and costs and enhances model performance, resulting in lower false hit rates. MeanCache also encodes context chains for every cached query, offering a simple yet highly effective mechanism to discern contextual query responses from standalone. Our experiments benchmarked against the state-of-the-art caching method, reveal that MeanCache attains an approximately 17% higher F-score and a 20% increase in precision during semantic cache hit-and-miss decisions while performing even better on contextual queries. It also reduces the storage requirement by 83% and accelerates semantic cache hit-and-miss decisions by 11%.
Large Language Models (LLMs) have emerged as a new paradigm for embodied reasoning and control, most recently by generating robot policy code that utilizes a custom library of vision and control primitive skills. However, prior arts fix their skills library and steer the LLM with carefully hand-crafted prompt engineering, limiting the agent to a stationary range of addressable tasks. In this work, we introduce LRLL, an LLM-based lifelong learning agent that continuously grows the robot skill library to tackle manipulation tasks of ever-growing complexity. LRLL achieves this with four novel contributions: 1) a soft memory module that allows dynamic storage and retrieval of past experiences to serve as context, 2) a self-guided exploration policy that proposes new tasks in simulation, 3) a skill abstractor that distills recent experiences into new library skills, and 4) a lifelong learning algorithm for enabling human users to bootstrap new skills with minimal online interaction. LRLL continuously transfers knowledge from the memory to the library, building composable, general and interpretable policies, while bypassing gradient-based optimization, thus relieving the learner from catastrophic forgetting. Empirical evaluation in a simulated tabletop environment shows that LRLL outperforms end-to-end and vanilla LLM approaches in the lifelong setup while learning skills that are transferable to the real world. Project material will become available at the webpage //gtziafas.github.io/LRLL_project.
Recommendation systems usually recommend the existing contents to different users. However, in comparison to static recommendation methods, a recommendation logic that dynamically adjusts based on user interest preferences may potentially attract a larger user base. Thus, we consider paraphrasing existing content based on the interests of the users to modify the content to better align with the preferences of users. In this paper, we propose a new task named Target-Audience Oriented Content Paraphrase aims to generate more customized contents for the target audience. We introduce the task definition and the corresponding framework for the proposed task and the creation of the corresponding datasets. We utilize the Large Language Models (LLMs) and Large Vision Models (LVMs) to accomplish the base implementation of the TOP framework and provide the referential baseline results for the proposed task.
Recently learned image compression (LIC) has achieved great progress and even outperformed the traditional approach using DCT or discrete wavelet transform (DWT). However, LIC mainly reduces spatial redundancy in the autoencoder networks and entropy coding, but has not fully removed the frequency-domain correlation explicitly as in DCT or DWT. To leverage the best of both worlds, we propose a surprisingly simple but efficient framework, which introduces the DWT to both the convolution layers and entropy coding of CNN-based LIC. First, in both the core and hyperprior autoencoder networks, we propose a Wavelet-domain Convolution (WeConv) module, which performs convolution after DWT, and then converts the data back to spatial domain via inverse DWT. This module is used at selected layers in a CNN network to reduce the frequency-domain correlation explicitly and make the signal sparser in DWT domain. We also propose a wavelet-domain Channel-wise Auto-Regressive entropy Model (WeChARM), where the output latent representations from the encoder network are first transformed by the DWT, before applying quantization and entropy coding, as in the traditional paradigm. Moreover, the entropy coding is split into two steps. We first code all low-frequency DWT coefficients, and then use them as prior to code high-frequency coefficients. The channel-wise entropy coding is further used in each step. By combining WeConv and WeChARM, the proposed WeConvene scheme achieves superior R-D performance compared to other state-of-the-art LIC methods as well as the latest H.266/VVC. For the Kodak dataset and the baseline network with -0.4% BD-Rate saving over H.266/VVC, introducing WeConv with the simplest Haar transform improves the saving to -4.7%. This is quite impressive given the simplicity of the Haar transform. Enabling Haar-based WeChARM entropy coding further boosts the saving to -8.2%.
Visual Question Answering (VQA) models have struggled with counting objects in natural images so far. We identify a fundamental problem due to soft attention in these models as a cause. To circumvent this problem, we propose a neural network component that allows robust counting from object proposals. Experiments on a toy task show the effectiveness of this component and we obtain state-of-the-art accuracy on the number category of the VQA v2 dataset without negatively affecting other categories, even outperforming ensemble models with our single model. On a difficult balanced pair metric, the component gives a substantial improvement in counting over a strong baseline by 6.6%.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191