Read original ↗
paperarXivTrust 82 · PrimaryPublished 1mo agoLive · 1mo ago

Grounding LLM Reasoning under Incomplete Graph Evidence

Knowledge graphs can guide large language models (LLMs) reasoning, but the graph seen by a system is usually a retrieved, linked, temporally scoped, and incomplete evidence state rather than a complete account of truth. We develop a theoretical perspective on grounding observable LLM trajectories under such incomplete graph evidence.The evidence state induces entity anchors, typed relation residuals, path energies, and support regions, while the language model supplies a prior over candidate trajectories. We show that, under open-world incompleteness, no hard rule based only on the observed st

Lineage graph

Paper → model → repo connections mined from source citations (Tier-1 exact match).

Why these links exist

Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.

Covers

newsKnowledge Distillation of Black-Box Large Language ModelsnewsKnowledge Distillation of Black-Box Large Language Models (2024)newsNew benchmark exposes reasoning gaps in top models

Has model

modelRetrace-1.5B

Related to

companyNorthwind AI

Implements (incoming)

repobenjaminzwhite/reasoning-modelsrepodouglasjordan2/c0repoJeryi-Sun/LLM-and-Lawrepowbopan/flashtracereposileod/llm-theory-of-mindrepoTencent/WeKnorarepoEricLBuehler/mistral.rsrepofrenzymath/Danusrepotirth8205/code-review-graphrepomicrosoft/interwhen

Covers (incoming)

newsBaryGraph - knowledge graph where every relationship is its own embedded document (not an edge) [R]newsCan We Understand How Large Language Models Reason? - Communications of the ACMnewsLarge language models could democratize data use—but only if the foundations are in place - World Bank BlogsnewsTowards principled knowledge editing methods for large language model reasoning

Related across the graph

repodouglasjordan2/c0newsKnowledge Distillation of Black-Box Large Language Modelsrepomicrosoft/interwhenrepoJeryi-Sun/LLM-and-Lawrepofrenzymath/DanuscompanyNorthwind AInewsLarge language models could democratize data use—but only if the foundations are in place - World Bank Blogsrepobenjaminzwhite/reasoning-modelsrepoTencent/WeKnoramodelRetrace-1.5BnewsTowards principled knowledge editing methods for large language model reasoningnewsKnowledge Distillation of Black-Box Large Language Models (2024)newsBaryGraph - knowledge graph where every relationship is its own embedded document (not an edge) [R]repoEricLBuehler/mistral.rsnewsNew benchmark exposes reasoning gaps in top modelsnewsCan We Understand How Large Language Models Reason? - Communications of the ACMreposileod/llm-theory-of-mindrepowbopan/flashtracerepotirth8205/code-review-graph

Topics

cs.CL