Fast PINN Eigensolvers via Biconvex Reformulationcs.AI updates on arXiv.org arXiv:2511.00792v1 Announce Type: cross
Abstract: Eigenvalue problems have a distinctive forward-inverse structure and are fundamental to characterizing a system’s thermal response, stability, and natural modes. Physics-Informed Neural Networks (PINNs) offer a mesh-free alternative for solving such problems but are often orders of magnitude slower than classical numerical schemes. In this paper, we introduce a reformulated PINN approach that casts the search for eigenpairs as a biconvex optimization problem, enabling fast and provably convergent alternating convex search (ACS) over eigenvalues and eigenfunctions using analytically optimal updates. Numerical experiments show that PINN-ACS attains high accuracy with convergence speeds up to 500$times$ faster than gradient-based PINN training. We release our codes at https://github.com/NeurIPS-ML4PS-2025/PINN_ACS_CODES.
arXiv:2511.00792v1 Announce Type: cross
Abstract: Eigenvalue problems have a distinctive forward-inverse structure and are fundamental to characterizing a system’s thermal response, stability, and natural modes. Physics-Informed Neural Networks (PINNs) offer a mesh-free alternative for solving such problems but are often orders of magnitude slower than classical numerical schemes. In this paper, we introduce a reformulated PINN approach that casts the search for eigenpairs as a biconvex optimization problem, enabling fast and provably convergent alternating convex search (ACS) over eigenvalues and eigenfunctions using analytically optimal updates. Numerical experiments show that PINN-ACS attains high accuracy with convergence speeds up to 500$times$ faster than gradient-based PINN training. We release our codes at https://github.com/NeurIPS-ML4PS-2025/PINN_ACS_CODES. Read More
Assessing LLM Reasoning Steps via Principal Knowledge Groundingcs.AI updates on arXiv.org arXiv:2511.00879v1 Announce Type: cross
Abstract: Step-by-step reasoning has become a standard approach for large language models (LLMs) to tackle complex tasks. While this paradigm has proven effective, it raises a fundamental question: How can we verify that an LLM’s reasoning is accurately grounded in knowledge? To address this question, we introduce a novel evaluation suite that systematically assesses the knowledge grounding of intermediate reasoning. Our framework comprises three key components. (1) Principal Knowledge Collection, a large-scale repository of atomic knowledge essential for reasoning. Based on the collection, we propose (2) knowledge-grounded evaluation metrics designed to measure how well models recall and apply prerequisite knowledge in reasoning. These metrics are computed by our (3) evaluator LLM, a lightweight model optimized for cost-effective and reliable metric computation. Our evaluation suite demonstrates remarkable effectiveness in identifying missing or misapplied knowledge elements, providing crucial insights for uncovering fundamental reasoning deficiencies in LLMs. Beyond evaluation, we demonstrate how these metrics can be integrated into preference optimization, showcasing further applications of knowledge-grounded evaluation.
arXiv:2511.00879v1 Announce Type: cross
Abstract: Step-by-step reasoning has become a standard approach for large language models (LLMs) to tackle complex tasks. While this paradigm has proven effective, it raises a fundamental question: How can we verify that an LLM’s reasoning is accurately grounded in knowledge? To address this question, we introduce a novel evaluation suite that systematically assesses the knowledge grounding of intermediate reasoning. Our framework comprises three key components. (1) Principal Knowledge Collection, a large-scale repository of atomic knowledge essential for reasoning. Based on the collection, we propose (2) knowledge-grounded evaluation metrics designed to measure how well models recall and apply prerequisite knowledge in reasoning. These metrics are computed by our (3) evaluator LLM, a lightweight model optimized for cost-effective and reliable metric computation. Our evaluation suite demonstrates remarkable effectiveness in identifying missing or misapplied knowledge elements, providing crucial insights for uncovering fundamental reasoning deficiencies in LLMs. Beyond evaluation, we demonstrate how these metrics can be integrated into preference optimization, showcasing further applications of knowledge-grounded evaluation. Read More
Energy-Efficient Deep Learning Without Backpropagation: A Rigorous Evaluation of Forward-Only Algorithmscs.AI updates on arXiv.org arXiv:2511.01061v1 Announce Type: cross
Abstract: The long-held assumption that backpropagation (BP) is essential for state-of-the-art performance is challenged by this work. We present rigorous, hardware-validated evidence that the Mono-Forward (MF) algorithm, a backpropagation-free method, consistently surpasses an optimally tuned BP baseline in classification accuracy on its native Multi-Layer Perceptron (MLP) architectures. This superior generalization is achieved with profound efficiency gains, including up to 41% less energy consumption and up to 34% faster training. Our analysis, which charts an evolutionary path from Geoffrey Hinton’s Forward-Forward (FF) to the Cascaded Forward (CaFo) and finally to MF, is grounded in a fair comparative framework using identical architectures and universal hyperparameter optimization. We further provide a critical re-evaluation of memory efficiency in BP-free methods, empirically demonstrating that practical overhead can offset theoretical gains. Ultimately, this work establishes MF as a practical, high-performance, and sustainable alternative to BP for MLPs.
arXiv:2511.01061v1 Announce Type: cross
Abstract: The long-held assumption that backpropagation (BP) is essential for state-of-the-art performance is challenged by this work. We present rigorous, hardware-validated evidence that the Mono-Forward (MF) algorithm, a backpropagation-free method, consistently surpasses an optimally tuned BP baseline in classification accuracy on its native Multi-Layer Perceptron (MLP) architectures. This superior generalization is achieved with profound efficiency gains, including up to 41% less energy consumption and up to 34% faster training. Our analysis, which charts an evolutionary path from Geoffrey Hinton’s Forward-Forward (FF) to the Cascaded Forward (CaFo) and finally to MF, is grounded in a fair comparative framework using identical architectures and universal hyperparameter optimization. We further provide a critical re-evaluation of memory efficiency in BP-free methods, empirically demonstrating that practical overhead can offset theoretical gains. Ultimately, this work establishes MF as a practical, high-performance, and sustainable alternative to BP for MLPs. Read More
The 5 FREE Must-Read Books for Every LLM EngineerKDnuggets Discover 5 free must-read books that cover theory, systems, linguistics, interpretability, and security side of large language models.
Discover 5 free must-read books that cover theory, systems, linguistics, interpretability, and security side of large language models. Read More
Influence-aware Causal Autoencoder Network for Node Importance Ranking in Complex Networkscs.AI updates on arXiv.org arXiv:2511.01228v1 Announce Type: cross
Abstract: Node importance ranking is a fundamental problem in graph data analysis. Existing approaches typically rely on node features derived from either traditional centrality measures or advanced graph representation learning methods, which depend directly on the target network’s topology. However, this reliance on structural information raises privacy concerns and often leads to poor generalization across different networks. In this work, we address a key question: Can we design a node importance ranking model trained exclusively on synthetic networks that is effectively appliable to real-world networks, eliminating the need to rely on the topology of target networks and improving both practicality and generalizability? We answer this question affirmatively by proposing the Influence-aware Causal Autoencoder Network (ICAN), a novel framework that leverages causal representation learning to get robust, invariant node embeddings for cross-network ranking tasks. Firstly, ICAN introduces an influence-aware causal representation learning module within an autoencoder architecture to extract node embeddings that are causally related to node importance. Moreover, we introduce a causal ranking loss and design a unified optimization framework that jointly optimizes the reconstruction and ranking objectives, enabling mutual reinforcement between node representation learning and ranking optimization. This design allows ICAN, trained on synthetic networks, to generalize effectively across diverse real-world graphs. Extensive experiments on multiple benchmark datasets demonstrate that ICAN consistently outperforms state-of-the-art baselines in terms of both ranking accuracy and generalization capability.
arXiv:2511.01228v1 Announce Type: cross
Abstract: Node importance ranking is a fundamental problem in graph data analysis. Existing approaches typically rely on node features derived from either traditional centrality measures or advanced graph representation learning methods, which depend directly on the target network’s topology. However, this reliance on structural information raises privacy concerns and often leads to poor generalization across different networks. In this work, we address a key question: Can we design a node importance ranking model trained exclusively on synthetic networks that is effectively appliable to real-world networks, eliminating the need to rely on the topology of target networks and improving both practicality and generalizability? We answer this question affirmatively by proposing the Influence-aware Causal Autoencoder Network (ICAN), a novel framework that leverages causal representation learning to get robust, invariant node embeddings for cross-network ranking tasks. Firstly, ICAN introduces an influence-aware causal representation learning module within an autoencoder architecture to extract node embeddings that are causally related to node importance. Moreover, we introduce a causal ranking loss and design a unified optimization framework that jointly optimizes the reconstruction and ranking objectives, enabling mutual reinforcement between node representation learning and ranking optimization. This design allows ICAN, trained on synthetic networks, to generalize effectively across diverse real-world graphs. Extensive experiments on multiple benchmark datasets demonstrate that ICAN consistently outperforms state-of-the-art baselines in terms of both ranking accuracy and generalization capability. Read More
Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Modelscs.AI updates on arXiv.org arXiv:2409.19667v4 Announce Type: replace-cross
Abstract: The need to analyze graphs is ubiquitous across various fields, from social networks to biological research and recommendation systems. Therefore, enabling the ability of large language models (LLMs) to process graphs is an important step toward more advanced general intelligence. However, current LLM benchmarks on graph analysis require models to directly reason over the prompts describing graph topology, and are thus limited to small graphs with only a few dozens of nodes. In contrast, human experts typically write programs based on popular libraries for task solving, and can thus handle graphs with different scales. To this end, a question naturally arises: can LLMs analyze graphs like professionals? In this paper, we introduce ProGraph, a manually crafted benchmark containing 3 categories of graph tasks. The benchmark expects solutions based on programming instead of directly reasoning over raw inputs. Our findings reveal that the performance of current LLMs is unsatisfactory, with the best model achieving only 36% accuracy. To bridge this gap, we propose LLM4Graph datasets, which include crawled documents and auto-generated codes based on 6 widely used graph libraries. By augmenting closed-source LLMs with document retrieval and fine-tuning open-source ones on the codes, we show 11-32% absolute improvements in their accuracies. Our results underscore that the capabilities of LLMs in handling structured data are still under-explored, and show the effectiveness of LLM4Graph in enhancing LLMs’ proficiency of graph analysis. The benchmark, datasets and enhanced open-source models are available at https://github.com/BUPT-GAMMA/ProGraph.
arXiv:2409.19667v4 Announce Type: replace-cross
Abstract: The need to analyze graphs is ubiquitous across various fields, from social networks to biological research and recommendation systems. Therefore, enabling the ability of large language models (LLMs) to process graphs is an important step toward more advanced general intelligence. However, current LLM benchmarks on graph analysis require models to directly reason over the prompts describing graph topology, and are thus limited to small graphs with only a few dozens of nodes. In contrast, human experts typically write programs based on popular libraries for task solving, and can thus handle graphs with different scales. To this end, a question naturally arises: can LLMs analyze graphs like professionals? In this paper, we introduce ProGraph, a manually crafted benchmark containing 3 categories of graph tasks. The benchmark expects solutions based on programming instead of directly reasoning over raw inputs. Our findings reveal that the performance of current LLMs is unsatisfactory, with the best model achieving only 36% accuracy. To bridge this gap, we propose LLM4Graph datasets, which include crawled documents and auto-generated codes based on 6 widely used graph libraries. By augmenting closed-source LLMs with document retrieval and fine-tuning open-source ones on the codes, we show 11-32% absolute improvements in their accuracies. Our results underscore that the capabilities of LLMs in handling structured data are still under-explored, and show the effectiveness of LLM4Graph in enhancing LLMs’ proficiency of graph analysis. The benchmark, datasets and enhanced open-source models are available at https://github.com/BUPT-GAMMA/ProGraph. Read More
GTAlign: Game-Theoretic Alignment of LLM Assistants for Social Welfarecs.AI updates on arXiv.org arXiv:2510.08872v3 Announce Type: replace
Abstract: Large Language Models (LLMs) have achieved remarkable progress in reasoning, yet sometimes produce responses that are suboptimal for users in tasks such as writing, information seeking, or providing practical guidance. Conventional alignment practices typically assume that maximizing model reward also maximizes user welfare, but this assumption frequently fails in practice: models may over-clarify or generate overly verbose reasoning when users prefer concise answers. Such behaviors resemble the prisoner’s dilemma, where individually rational choices lead to socially suboptimal outcomes. The fundamental challenge is the lack of a principled decision making mechanism that mutually benefits both the LLM and the user. We propose Game-Theoretic Alignment (GTAlign), an alignment framework that integrates game-theoretic decision making into both reasoning and training. During reasoning, the model explicitly treats user-LLM interaction as a strategic game: it constructs payoff matrices within its reasoning chain to estimate welfare for both itself and the user, and then selects actions that are mutually beneficial. During training, we introduce a social welfare reward that reinforces cooperative responses, aligning model behavior with socially efficient outcomes. In addition, we introduce an inference technique that leverages game-theoretic reasoning to dynamically adapt LLM’s response when pricing policies of LLM service change. Extensive experiments demonstrate that GTAlign substantially improves reasoning efficiency, answer quality, and social welfare compared to baselines across diverse tasks. The code is available at https://github.com/ulab-uiuc/GTAlign .
arXiv:2510.08872v3 Announce Type: replace
Abstract: Large Language Models (LLMs) have achieved remarkable progress in reasoning, yet sometimes produce responses that are suboptimal for users in tasks such as writing, information seeking, or providing practical guidance. Conventional alignment practices typically assume that maximizing model reward also maximizes user welfare, but this assumption frequently fails in practice: models may over-clarify or generate overly verbose reasoning when users prefer concise answers. Such behaviors resemble the prisoner’s dilemma, where individually rational choices lead to socially suboptimal outcomes. The fundamental challenge is the lack of a principled decision making mechanism that mutually benefits both the LLM and the user. We propose Game-Theoretic Alignment (GTAlign), an alignment framework that integrates game-theoretic decision making into both reasoning and training. During reasoning, the model explicitly treats user-LLM interaction as a strategic game: it constructs payoff matrices within its reasoning chain to estimate welfare for both itself and the user, and then selects actions that are mutually beneficial. During training, we introduce a social welfare reward that reinforces cooperative responses, aligning model behavior with socially efficient outcomes. In addition, we introduce an inference technique that leverages game-theoretic reasoning to dynamically adapt LLM’s response when pricing policies of LLM service change. Extensive experiments demonstrate that GTAlign substantially improves reasoning efficiency, answer quality, and social welfare compared to baselines across diverse tasks. The code is available at https://github.com/ulab-uiuc/GTAlign . Read More
DEEPAMBIGQA: Ambiguous Multi-hop Questions for Benchmarking LLM Answer Completenesscs.AI updates on arXiv.org arXiv:2511.01323v1 Announce Type: cross
Abstract: Large language models (LLMs) with integrated search tools show strong promise in open-domain question answering (QA), yet they often struggle to produce complete answer set to complex questions such as Which actor from the film Heat won at least one Academy Award?, which requires (1) distinguishing between multiple films sharing the same title and (2) reasoning across a large set of actors to gather and integrate evidence. Existing QA benchmarks rarely evaluate both challenges jointly. To address this, we introduce DeepAmbigQAGen, an automatic data generation pipeline that constructs QA tasks grounded in text corpora and linked knowledge graph, generating natural and verifiable questions that systematically embed name ambiguity and multi-step reasoning. Based on this, we build DeepAmbigQA, a dataset of 3,600 questions requiring multi-hop reasoning and half of them explicit name ambiguity resolving. Experiments reveal that, even state-of-the-art GPT-5 show incomplete answers, achieving only 0.13 exact match on ambiguous questions and 0.21 on non-ambiguous questions. These findings highlight the need for more robust QA systems aimed at information gathering and answer completeness.
arXiv:2511.01323v1 Announce Type: cross
Abstract: Large language models (LLMs) with integrated search tools show strong promise in open-domain question answering (QA), yet they often struggle to produce complete answer set to complex questions such as Which actor from the film Heat won at least one Academy Award?, which requires (1) distinguishing between multiple films sharing the same title and (2) reasoning across a large set of actors to gather and integrate evidence. Existing QA benchmarks rarely evaluate both challenges jointly. To address this, we introduce DeepAmbigQAGen, an automatic data generation pipeline that constructs QA tasks grounded in text corpora and linked knowledge graph, generating natural and verifiable questions that systematically embed name ambiguity and multi-step reasoning. Based on this, we build DeepAmbigQA, a dataset of 3,600 questions requiring multi-hop reasoning and half of them explicit name ambiguity resolving. Experiments reveal that, even state-of-the-art GPT-5 show incomplete answers, achieving only 0.13 exact match on ambiguous questions and 0.21 on non-ambiguous questions. These findings highlight the need for more robust QA systems aimed at information gathering and answer completeness. Read More
A Topology-Aware Graph Convolutional Network for Human Pose Similarity and Action Quality Assessmentcs.AI updates on arXiv.org arXiv:2511.01194v1 Announce Type: cross
Abstract: Action Quality Assessment (AQA) requires fine-grained understanding of human motion and precise evaluation of pose similarity. This paper proposes a topology-aware Graph Convolutional Network (GCN) framework, termed GCN-PSN, which models the human skeleton as a graph to learn discriminative, topology-sensitive pose embeddings. Using a Siamese architecture trained with a contrastive regression objective, our method outperforms coordinate-based baselines and achieves competitive performance on AQA-7 and FineDiving benchmarks. Experimental results and ablation studies validate the effectiveness of leveraging skeletal topology for pose similarity and action quality assessment.
arXiv:2511.01194v1 Announce Type: cross
Abstract: Action Quality Assessment (AQA) requires fine-grained understanding of human motion and precise evaluation of pose similarity. This paper proposes a topology-aware Graph Convolutional Network (GCN) framework, termed GCN-PSN, which models the human skeleton as a graph to learn discriminative, topology-sensitive pose embeddings. Using a Siamese architecture trained with a contrastive regression objective, our method outperforms coordinate-based baselines and achieves competitive performance on AQA-7 and FineDiving benchmarks. Experimental results and ablation studies validate the effectiveness of leveraging skeletal topology for pose similarity and action quality assessment. Read More
In Dialogue with Intelligence: Rethinking Large Language Models as Collective Knowledgecs.AI updates on arXiv.org arXiv:2505.22767v3 Announce Type: replace-cross
Abstract: Large Language Models (LLMs) can be understood as Collective Knowledge (CK): a condensation of human cultural and technical output, whose apparent intelligence emerges in dialogue. This perspective article, drawing on extended interaction with ChatGPT-4, postulates differential response modes that plausibly trace their origin to distinct model subnetworks. It argues that CK has no persistent internal state or “spine”: it drifts, it complies, and its behaviour is shaped by the user and by fine-tuning. It develops the notion of co-augmentation, in which human judgement and CK’s representational reach jointly produce forms of analysis that neither could generate alone. Finally, it suggests that CK offers a tractable object for neuroscience: unlike biological brains, these systems expose their architecture, training history, and activation dynamics, making the human–CK loop itself an experimental target.
arXiv:2505.22767v3 Announce Type: replace-cross
Abstract: Large Language Models (LLMs) can be understood as Collective Knowledge (CK): a condensation of human cultural and technical output, whose apparent intelligence emerges in dialogue. This perspective article, drawing on extended interaction with ChatGPT-4, postulates differential response modes that plausibly trace their origin to distinct model subnetworks. It argues that CK has no persistent internal state or “spine”: it drifts, it complies, and its behaviour is shaped by the user and by fine-tuning. It develops the notion of co-augmentation, in which human judgement and CK’s representational reach jointly produce forms of analysis that neither could generate alone. Finally, it suggests that CK offers a tractable object for neuroscience: unlike biological brains, these systems expose their architecture, training history, and activation dynamics, making the human–CK loop itself an experimental target. Read More
