paper-with-me

홈 › Papers

Implicit Reasoning in Transformers is Reasoning through Shortcuts

2025-03-10 · Tianhe Lin, Jian Xie, Siyu Yuan, Deqing Yang

Test-time compute is emerging as a new paradigm for enhancing language models' complex multi-step reasoning capabilities, as demonstrated by the success of OpenAI's o1 and o3, as well as DeepSeek's R1. Compared to explicit reasoning in test-time compute, implicit reasoning is more inference-efficient, requiring fewer generated tokens. However, why does the advanced reasoning capability fail to emerge in the implicit reasoning style? In this work, we train GPT-2 from scratch on a curated multi-step mathematical reasoning dataset and conduct analytical experiments to investigate how language models perform implicit reasoning in multi-step tasks. Our findings reveal: 1) Language models can perform step-by-step reasoning and achieve high accuracy in both in-domain and out-of-domain tests via implicit reasoning. However, this capability only emerges when trained on fixed-pattern data. 2) Conversely, implicit reasoning abilities emerging from training on unfixed-pattern data tend to overfit a specific pattern and fail to generalize further. Notably, this limitation is also observed in state-of-the-art large language models. These findings suggest that language models acquire implicit reasoning through shortcut learning, enabling strong performance on tasks with similar patterns while lacking generalization.

📄 PDF Abstract BibTeX arXiv:2503.07604

Code (1)

TianheL/LM-Implicit-Reasoning 공식 구현 pytorch

Tasks

Mathematical Reasoning

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Attention 설명 없음
Multi-Head Attention 설명 없음
Adam 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Reasoning in Transformers - Mitigating Spurious Correlations and Reasoning Shortcuts

2024-03-17 · Daniel Enström, Viktor Kjellberg, Moa Johansson

Transformer language models are neural networks used for a wide variety of tasks concerning natural language, including some that also require logical reasoning. However, a transformer model may easily learn spurious pat…

Language ModelingLanguage ModellingLogical Reasoning

Deductive Logic in Language Models: Horizontal vs Vertical Reasoning

2025-10-10 · Davide Maltoni, Matteo Ferrara arxiv

Recent language models exhibit significant logical reasoning abilities, yet the mechanisms supporting deductive inference remain poorly understood. This paper studies small transformer-based language models trained from …

Logical ReasoningDecision Making

Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

2024-05-23 · Boshi Wang, Xiang Yue, Yu Su, Huan Sun

We study whether transformers can learn to implicitly reason over parametric knowledge, a skill that even the most capable language models struggle with. Focusing on two representative reasoning types, composition and co…

Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers

2026-04-09 · Harsh Kohli, Srinivasan Parthasarathy, Huan Sun, Yuekun Yao arxiv

We study implicit reasoning, i.e. the ability to combine knowledge or rules within a single forward pass. While transformer-based large language models store substantial factual knowledge and rules, they often fail to co…

The Scaling Properties of Implicit Deductive Reasoning in Transformers

2026-05-05 · Enrico Vompa, Tanel Tammet arxiv

We investigate the scaling properties of implicit deductive reasoning over Horn clauses in depth-bounded Transformers. By systematically decorrelating provability from spurious features and enforcing algorithmic alignmen…