In this work, we introduce a novel evaluation paradigm for Large Language Models, one that challenges them to engage in meta-reasoning. This approach addresses critical shortcomings in existing math problem-solving benchmarks, traditionally used to evaluate the cognitive capabilities of agents. Our paradigm shifts the focus from result-oriented assessments, which often overlook the reasoning process, to a more holistic evaluation that effectively differentiates the cognitive capabilities among models. For example, in our benchmark, GPT-4 demonstrates a performance five times better than GPT3-5. The significance of this new paradigm lies in its ability to reveal potential cognitive deficiencies in LLMs that current benchmarks, such as GSM8K, fail to uncover due to their saturation and lack of effective differentiation among varying reasoning abilities. Our comprehensive analysis includes several state-of-the-art math models from both open-source and closed-source communities, uncovering fundamental deficiencies in their training and evaluation approaches. This paper not only advocates for a paradigm shift in the assessment of LLMs but also contributes to the ongoing discourse on the trajectory towards Artificial General Intelligence (AGI). By promoting the adoption of meta-reasoning evaluation methods similar to ours, we aim to facilitate a more accurate assessment of the true cognitive abilities of LLMs.
相關內容
The integration of learning and reasoning is high on the research agenda in AI. Nevertheless, there is only a little attention to use existing background knowledge for reasoning about partially observed scenes to answer questions about the scene. Yet, we as humans use such knowledge frequently to infer plausible answers to visual questions (by eliminating all inconsistent ones). Such knowledge often comes in the form of constraints about objects and it tends to be highly domain or environment-specific. We contribute a novel benchmark called CLEVR-POC for reasoning-intensive visual question answering (VQA) in partially observable environments under constraints. In CLEVR-POC, knowledge in the form of logical constraints needs to be leveraged to generate plausible answers to questions about a hidden object in a given partial scene. For instance, if one has the knowledge that all cups are colored either red, green or blue and that there is only one green cup, it becomes possible to deduce the color of an occluded cup as either red or blue, provided that all other cups, including the green one, are observed. Through experiments, we observe that the low performance of pre-trained vision language models like CLIP (~ 22%) and a large language model (LLM) like GPT-4 (~ 46%) on CLEVR-POC ascertains the necessity for frameworks that can handle reasoning-intensive tasks where environment-specific background knowledge is available and crucial. Furthermore, our demonstration illustrates that a neuro-symbolic model, which integrates an LLM like GPT-4 with a visual perception network and a formal logical reasoner, exhibits exceptional performance on CLEVR-POC.
In this paper, we propose an architecture of a novel adaptive fault-tolerant approximate multiplier tailored for ASIC-based DNN accelerators.
Many of the world's workers rely on digital platforms for their income. In Venezuela, a nation grappling with extreme inflation and where most of the workforce is self-employed, data production platforms for machine learning have emerged as a viable opportunity for many to earn a flexible income in US dollars. Platform workers are deeply interconnected within a vast network of firms and entities that act as intermediaries for wage payments in digital currencies and its subsequent conversion to the national currency, the bolivar. Past research on embeddedness has noted that being intertwined in multi-tiered socioeconomic networks of companies and individuals can offer significant rewards to social participants, while also connoting a particular set of limitations. This paper furnishes qualitative evidence regarding how this deep embeddedness impacts platform workers in Venezuela. Given the backdrop of a national crisis and rampant hyperinflation, the perks of receiving wages through various financial platforms include access to a more stable currency and the ability to save and invest outside the national financial system. However, relying on numerous digital and local intermediaries often diminishes income due to transaction fees. Moreover, this introduces heightened financial risks, particularly due to the unpredictable nature of cryptocurrencies as an investment. The over-reliance on external financial platforms erodes worker autonomy through power dynamics that lean in favor of the platforms that set the transaction rules and prices. These findings present a multifaceted perspective on deep embeddedness in platform labor, highlighting how the rewards of financial intermediation often come at a substantial cost for the workers in unstable situations, who are saddled with escalating financial risks.
Analogy-making is central to human cognition, allowing us to adapt to novel situations -- an ability that current AI systems still lack. Most analogy datasets today focus on simple analogies (e.g., word analogies); datasets including complex types of analogies are typically manually curated and very small. We believe that this holds back progress in computational analogy. In this work, we design a data generation pipeline, ParallelPARC (Parallel Paragraph Creator) leveraging state-of-the-art Large Language Models (LLMs) to create complex, paragraph-based analogies, as well as distractors, both simple and challenging. We demonstrate our pipeline and create ProPara-Logy, a dataset of analogies between scientific processes. We publish a gold-set, validated by humans, and a silver-set, generated automatically. We test LLMs' and humans' analogy recognition in binary and multiple-choice settings, and found that humans outperform the best models (~13% gap) after a light supervision. We demonstrate that our silver-set is useful for training models. Lastly, we show challenging distractors confuse LLMs, but not humans. We hope our pipeline will encourage research in this emerging field.
In this work, we present novel protocols over rings for semi-honest secure three-party computation (3-PC) and malicious four-party computation (4-PC) with one corruption. Compared to state-of-the-art protocols in the same setting, our protocols require fewer low-latency and high-bandwidth links between the parties to achieve high throughput. Our protocols also reduce the computational complexity by requiring up to 50 percent fewer basic instructions per gate. Further, our protocols achieve the currently best-known communication complexity (3, resp. 5 elements per multiplication gate) with an optional preprocessing phase to reduce the communication complexity of the online phase to 2 (resp. 3) elements per multiplication gate. In homogeneous network settings, i.e. all links between the parties share similar network bandwidth and latency, our protocols achieve up to two times higher throughput than state-of-the-art protocols. In heterogeneous network settings, i.e. all links between the parties share different network bandwidth and latency, our protocols achieve even larger performance improvements. We implemented our protocols and multiple other state-of-the-art protocols (Replicated 3-PC, Astra, Fantastic Four, Tetrad) in a novel open-source C++ framework optimized for achieving high throughput. Five out of six implemented 3-PC and 4-PC protocols achieve more than one billion 32-bit multiplication or more than 32 billion AND gates per second using our implementation in a 25 Gbit/s LAN environment. This is the highest throughput achieved in 3-PC and 4-PC so far and between two and three orders of magnitude higher than the throughput MP-SPDZ achieves in the same settings.
We introduce CyberDemo, a novel approach to robotic imitation learning that leverages simulated human demonstrations for real-world tasks. By incorporating extensive data augmentation in a simulated environment, CyberDemo outperforms traditional in-domain real-world demonstrations when transferred to the real world, handling diverse physical and visual conditions. Regardless of its affordability and convenience in data collection, CyberDemo outperforms baseline methods in terms of success rates across various tasks and exhibits generalizability with previously unseen objects. For example, it can rotate novel tetra-valve and penta-valve, despite human demonstrations only involving tri-valves. Our research demonstrates the significant potential of simulated human demonstrations for real-world dexterous manipulation tasks. More details can be found at //cyber-demo.github.io
In this work, we introduce SureFED, a novel framework for byzantine robust federated learning. Unlike many existing defense methods that rely on statistically robust quantities, making them vulnerable to stealthy and colluding attacks, SureFED establishes trust using the local information of benign clients. SureFED utilizes an uncertainty aware model evaluation and introspection to safeguard against poisoning attacks. In particular, each client independently trains a clean local model exclusively using its local dataset, acting as the reference point for evaluating model updates. SureFED leverages Bayesian models that provide model uncertainties and play a crucial role in the model evaluation process. Our framework exhibits robustness even when the majority of clients are compromised, remains agnostic to the number of malicious clients, and is well-suited for non-IID settings. We theoretically prove the robustness of our algorithm against data and model poisoning attacks in a decentralized linear regression setting. Proof-of Concept evaluations on benchmark image classification data demonstrate the superiority of SureFED over the state of the art defense methods under various colluding and non-colluding data and model poisoning attacks.
In this work, we proposed a new dynamic distributed planning approach that is able to take into account the changes that the agent introduces on his set of actions to be planned in order to take into account the changes that occur in his environment. Our approach fits into the context of distributed planning for distributed plans where each agent can produce its own plans. According to our approach the generation of the plans is based on the satisfaction of the constraints by the use of the genetic algorithms. Our approach is to generate, a new plan by each agent, whenever there is a change in its set of actions to plan. This in order to take into account the new actions introduced in its new plan. In this new plan, the agent takes, each time, as a new action set to plan all the old un-executed actions of the old plan and the new actions engendered by the changes and as a new initial state; the state in which the set of actions of the agent undergoes a change. In our work, we used a concrete case to illustrate and demonstrate the utility of our approach.
This article presents the affordances that Generative Artificial Intelligence can have in disinformation context, one of the major threats to our digitalized society. We present a research framework to generate customized agent-based social networks for disinformation simulations that would enable understanding and evaluation of the phenomena whilst discussing open challenges.
We study the problem of learning to reason in large scale knowledge graphs (KGs). More specifically, we describe a novel reinforcement learning framework for learning multi-hop relational paths: we use a policy-based agent with continuous states based on knowledge graph embeddings, which reasons in a KG vector space by sampling the most promising relation to extend its path. In contrast to prior work, our approach includes a reward function that takes the accuracy, diversity, and efficiency into consideration. Experimentally, we show that our proposed method outperforms a path-ranking based algorithm and knowledge graph embedding methods on Freebase and Never-Ending Language Learning datasets.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191