paper-with-me

홈 › Papers

Reasoning with Transformer-based Models: Deep Learning, but Shallow Reasoning

2021-06-22 · AKBC 2021 10 · Chadi Helwe, Chloé Clavel, Fabian M. Suchanek

Recent years have seen impressive performance of transformer-based models on different natural language processing tasks. However, it is not clear to what degree the transformers can reason on natural language. To shed light on this question, this survey paper discusses the performance of transformers on different reasoning tasks, including mathematical reasoning, commonsense reasoning, and logical reasoning. We point out successes and limitations, of both empirical and theoretical nature.

📄 PDF Abstract BibTeX

Code (1)

dig-team/failbert 공식 구현 pytorch

Tasks

Deep LearningLogical ReasoningMathematical ReasoningSurvey

Similar Papers 제목 키워드 기반

Chain-of-Thought Enhanced Shallow Transformers for Wireless Symbol Detection

2025-06-26 · Li Fan, Peng Wang, Jing Yang, Cong Shen

Transformers have shown potential in solving wireless communication problems, particularly via in-context learning (ICL), where models adapt to new tasks through prompts without requiring model updates. However, prior IC…

Computational EfficiencyIn-Context Learning

Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent

2025-08-11 · Tong Yang, Yu Huang, Yingbin Liang, Yuejie Chi arxiv

Transformers have demonstrated remarkable capabilities in multi-step reasoning tasks. However, understandings of the underlying mechanisms by which they acquire these abilities through training remain limited, particular…

Mask and Reason: Pre-Training Knowledge Graph Transformers for Complex Logical Queries

2022-08-16 · Xiao Liu, Shiyu Zhao, Kai Su, Yukuo Cen 외

Knowledge graph (KG) embeddings have been a mainstream approach for reasoning over incomplete KGs. However, limited by their inherently shallow and static architectures, they can hardly deal with the rising focus on comp…

Mixture-of-Experts

Self-Verifying Reflection Helps Transformers with CoT Reasoning

2025-10-14 · Zhongwei Yu, Wannian Xia, Xue Yan, Bo Xu 외 arxiv

Advanced large language models (LLMs) frequently reflect in reasoning chain-of-thoughts (CoTs), where they self-verify the correctness of current solutions and explore alternatives. However, given recent findings that LL…

Reinforcement Learning

Dynamic Reasoning Chains through Depth-Specialized Mixture-of-Experts in Transformer Architectures

2025-09-24 · Sampurna Roy, Ayan Sar, Anurag Kaushish, Kanav Gupta 외 arxiv

Contemporary transformer architectures apply identical processing depth to all inputs, creating inefficiencies and limiting reasoning quality. Simple factual queries are subjected to the same multilayered computation as …