REVIEW 4 cited by
Analogical Reasoning Inside Large Language Models: Concept Vectors and the Limits of Abstraction
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Analogical reasoning relies on conceptual abstractions, but it is unclear whether Large Language Models (LLMs) harbor such internal representations. We explore distilled representations from LLM activations and find that function vectors (FVs; Todd et al., 2024) - compact representations for in-context learning (ICL) tasks - are not invariant to simple input changes (e.g., open-ended vs. multiple-choice), suggesting they capture more than pure concepts. Using representational similarity analysis (RSA), we localize a small set of attention heads that encode invariant concept vectors (CVs) for verbal concepts like "antonym". These CVs function as feature detectors that operate independently of the final output - meaning that a model may form a correct internal representation yet still produce an incorrect output. Furthermore, CVs can be used to causally guide model behaviour. However, for more abstract concepts like "previous" and "next", we do not observe invariant linear representations, a finding we link to generalizability issues LLMs display within these domains.
Forward citations
Cited by 4 Pith papers
-
Metaphor-Induced Algorithmic Steering: Cross-Domain Procedural Transfer in LLM Code Generation
Metaphorical instructions can steer LLM code generators toward correct but less efficient algorithms, and this steering is reflected in hidden-state representations.
-
Analogical Deep Research: Retrieving and Integrating Historical Analogies for Foresight Analysis
LLM deep-research agents rarely use historical analogies; a structural-decomposition plus cross-analogy-confirmation agent (CANA) sharply increases mechanism-grounded analogy claims and hidden-factor hits on the new A...
-
Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey
A survey showing that common systematic generalization benchmarks measure behavioural systematicity, not the representational systematicity that Fodor and Pylyshyn's challenge requires, and mapping them onto Hadley's ...
-
Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models?
Large reasoning models default to English or Chinese as internal 'reasoning hubs', and forcing non-hub reasoning lowers math accuracy, especially for low-resource languages, while sometimes improving safety and cultur...
Discussion (0). Continue with ORCID to comment.