The Canonical Order Problem: When Large Language Models Are Unreliable Knowledge Bases for Multi-Valued Relations
Mirrored from arXiv — NLP / Computation & Language for archival readability. Support the source by reading on the original site.
Computer Science > Computation and Language
Title:The Canonical Order Problem: When Large Language Models Are Unreliable Knowledge Bases for Multi-Valued Relations
Abstract:Large language models (LLMs) are increasingly used as knowledge bases (KBs) due to the vast amount of knowledge they acquire during pre-training. While many works focus on extracting single relational triples, most real-world relations are multi-valued and require generating sets of entities.
In this paper, we investigate how LLMs represent and generate multi-valued relations. We identify the canonical order problem: The probabilistic distributions inside LLMs organize many multi-valued relations according to a canonical ordering (e.g., alphabetical or chronological). Through mechanistic analysis, we show that set generation in LLMs can be thought of in terms of three phases: (1) retrieval of candidate entities, (2) internal sorting, and (3) selection of the next element. As a result, prompts aiming to construct KBs that deviate from this internal canonical ordering lead to a markedly reduced reliability of LLMs when aiming to generate complete sets for multi-valued relations.
| Comments: | Accepted at AKBC@EMNLP2026 |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2609.36209 [cs.CL] |
| (or arXiv:2609.36209v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2609.36209
arXiv-issued DOI via DataCite (pending registration)
|
Submission history
From: Timo Pierre Schrader [view email][v1] Mon, 28 Sep 2026 20:09:12 UTC (164 KB)
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
References & Citations
Bookmark
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
More from arXiv — NLP / Computation & Language
-
Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models
Oct 9
-
Conversational Task Disambiguation over Tabular Data: Leakage-Aware Formulation, Benchmark Suite, and Training
Oct 9
-
Language Models for Page-Level Layout Decisions in E-commerce Search
Oct 9
-
Measuring and Mitigating Solution Mode Collapse in RLVR
Oct 9
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.