The Curious Case of Analogies: Investigating Analogical Reasoning in Large Language Models
Abstract
LLMs can encode and apply high-level relational concepts in analogical reasoning but face limitations, particularly when relational information is missing or when transferring to new entities.
Analogical reasoning is at the core of human cognition, serving as an important foundation for a variety of intellectual activities. While prior work has shown that LLMs can represent task patterns and surface-level concepts, it remains unclear whether these models can encode high-level relational concepts and apply them to novel situations through structured comparisons. In this work, we explore this fundamental aspect using proportional and story analogies, and identify three key findings. First, LLMs effectively encode the underlying relationships between analogous entities; both attributive and relational information propagate through mid-upper layers in correct cases, whereas reasoning failures reflect missing relational information within these layers. Second, unlike humans, LLMs often struggle not only when relational information is missing, but also when attempting to apply it to new entities. In such cases, strategically patching hidden representations at critical token positions can facilitate information transfer to a certain extent. Lastly, successful analogical reasoning in LLMs is marked by strong structural alignment between analogous situations, whereas failures often reflect degraded or misplaced alignment. Overall, our findings reveal that LLMs exhibit emerging but limited capabilities in encoding and applying high-level relational concepts, highlighting both parallels and gaps with human cognition.
Community
This paper investigates the internal mechanism of how LLMs perform analogical reasoning.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Large Language Models Do NOT Really Know What They Don't Know (2025)
- How Language Models Conflate Logical Validity with Plausibility: A Representational Analysis of Content Effects (2025)
- Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Models (2025)
- Mapping Faithful Reasoning in Language Models (2025)
- GraphGhost: Tracing Structures Behind Large Language Models (2025)
- LLMs Encode How Difficult Problems Are (2025)
- ThoughtProbe: Classifier-Guided LLM Thought Space Exploration via Probing Representations (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper