Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoning

• URL: http://arxiv.org/abs/2412.05586v1
• Date: Sat, 07 Dec 2024 08:45:39 GMT
• Title: Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoning
• Authors: Michael Hersche, Giacomo Camposampiero, Roger Wattenhofer, Abu Sebastian, Abbas Rahimi,
• Abstract summary: This work compares large language models (LLMs) and neuro-symbolic approaches in solving Raven's progressive matrices (RPM) Our analysis reveals that the root cause lies in the LLM's weakness in understanding and executing arithmetic rules. We find that ARLC achieves almost perfect accuracy on the center constellation of I-RAVEN, demonstrating a high fidelity in arithmetic rules.
• Score: 20.72570252804897
• License:
• Abstract: This work compares large language models (LLMs) and neuro-symbolic approaches in solving Raven's progressive matrices (RPM), a visual abstract reasoning test that involves the understanding of mathematical rules such as progression or arithmetic addition. Providing the visual attributes directly as textual prompts, which assumes an oracle visual perception module, allows us to measure the model's abstract reasoning capability in isolation. Despite providing such compositionally structured representations from the oracle visual perception and advanced prompting techniques, both GPT-4 and Llama-3 70B cannot achieve perfect accuracy on the center constellation of the I-RAVEN dataset. Our analysis reveals that the root cause lies in the LLM's weakness in understanding and executing arithmetic rules. As a potential remedy, we analyze the Abductive Rule Learner with Context-awareness (ARLC), a neuro-symbolic approach that learns to reason with vector-symbolic architectures (VSAs). Here, concepts are represented with distributed vectors s.t. dot products between encoded vectors define a similarity kernel, and simple element-wise operations on the vectors perform addition/subtraction on the encoded values. We find that ARLC achieves almost perfect accuracy on the center constellation of I-RAVEN, demonstrating a high fidelity in arithmetic rules. To stress the length generalization capabilities of the models, we extend the RPM tests to larger matrices (3x10 instead of typical 3x3) and larger dynamic ranges of the attribute values (from 10 up to 1000). We find that the LLM's accuracy of solving arithmetic rules drops to sub-10%, especially as the dynamic range expands, while ARLC can maintain a high accuracy due to emulating symbolic computations on top of properly distributed representations. Our code is available at https://github.com/IBM/raven-large-language-models.

Related papers

• Unraveling Arithmetic in Large Language Models: The Role of Algebraic Structures [3.181878085746691]
  Large language models (LLMs) have demonstrated remarkable mathematical capabilities, largely driven by chain-of-thought (CoT) prompting. We propose that LLMs learn arithmetic by capturing algebraic structures, such as emphCommutativity and emphIdentity properties. Our findings indicate that leveraging algebraic structures can enhance the LLMs' arithmetic capabilities, offering insights into improving their arithmetic performance.
  arXiv  Detail & Related papers  (2024-11-25T10:23:11Z)
• Towards Learning Abductive Reasoning using VSA Distributed Representations [56.31867341825068]
  We introduce the Abductive Rule Learner with Context-awareness (ARLC) model. ARLC features a novel and more broadly applicable training objective for abductive reasoning. We show ARLC's robustness to post-programming training by incrementally learning from examples on top of programmed knowledge.
  arXiv  Detail & Related papers  (2024-06-27T12:05:55Z)
• LARS-VSA: A Vector Symbolic Architecture For Learning with Abstract Rules [1.3049516752695616]
  We propose a "relational bottleneck" that separates object-level features from abstract rules, allowing learning from limited amounts of data. We adapt the "relational bottleneck" strategy to a high-dimensional space, incorporating explicit vector binding operations between symbols and relational representations. Our system benefits from the low overhead of operations in hyperdimensional space, making it significantly more efficient than the state of the art when evaluated on a variety of test datasets.
  arXiv  Detail & Related papers  (2024-05-23T11:05:42Z)
• Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning [89.89857766491475]
  We propose a complex reasoning schema over KG upon large language models (LLMs) We augment the arbitrary first-order logical queries via binary tree decomposition to stimulate the reasoning capability of LLMs. Experiments across widely used datasets demonstrate that LACT has substantial improvements(brings an average +5.5% MRR score) over advanced methods.
  arXiv  Detail & Related papers  (2024-05-02T18:12:08Z)
• Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic Architectures [22.12114509953737]
  Abstract reasoning is a cornerstone of human intelligence, and replicating it with artificial intelligence (AI) presents an ongoing challenge. This study focuses on efficiently solving Raven's progressive matrices (RPM), a visual test for assessing abstract reasoning abilities. Instead of hard-coding the rule formulations associated with RPMs, our approach can learn the VSA rule formulations with just one pass through the training data.
  arXiv  Detail & Related papers  (2024-01-29T10:17:18Z)
• Semantic Graph Representation Learning for Handwritten Mathematical Expression Recognition [57.60390958736775]
  We propose a simple but efficient method to enhance semantic interaction learning (SIL) We first construct a semantic graph based on the statistical symbol co-occurrence probabilities. Then we design a semantic aware module (SAM), which projects the visual and classification feature into semantic space. Our method achieves better recognition performance than prior arts on both CROHME and HME100K datasets.
  arXiv  Detail & Related papers  (2023-08-21T06:23:41Z)
• Explaining Emergent In-Context Learning as Kernel Regression [61.57151500616111]
  Large language models (LLMs) have initiated a paradigm shift in transfer learning. In this paper, we investigate the reason why a transformer-based language model can accomplish in-context learning after pre-training. We find that during ICL, the attention and hidden features in LLMs match the behaviors of a kernel regression.
  arXiv  Detail & Related papers  (2023-05-22T06:45:02Z)
• Self-Supervised Learning Disentangled Group Representation as Feature [82.07737719232972]
  We show that existing Self-Supervised Learning (SSL) only disentangles simple augmentation features such as rotation and colorization. We propose an iterative SSL algorithm: Iterative Partition-based Invariant Risk Minimization (IP-IRM) We prove that IP-IRM converges to a fully disentangled representation and show its effectiveness on various benchmarks.
  arXiv  Detail & Related papers  (2021-10-28T16:12:33Z)
• Learning with Holographic Reduced Representations [28.462635977110413]
  Holographic Reduced Representations (HRR) are a method for performing symbolic AI on top of real-valued vectors. This paper revisits this approach to understand if it is viable for enabling a hybrid neural-symbolic approach to learning.
  arXiv  Detail & Related papers  (2021-09-05T19:37:34Z)
• FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs [53.710405006523274]
  This work focuses on the representation learning question: how can we learn such features? Under the assumption that the underlying (unknown) dynamics correspond to a low rank transition matrix, we show how the representation learning question is related to a particular non-linear matrix decomposition problem. We develop FLAMBE, which engages in exploration and representation learning for provably efficient RL in low rank transition models.
  arXiv  Detail & Related papers  (2020-06-18T19:11:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.