The results demonstrate that incremental affected-set computation—a classical technique in database materialization and ontology maintenance—can be adapted to LLM-maintained text knowledge bases, through extensions for typed provenance strength and lexical mutex conflict.
Abstract
Background: LLM-based agents are increasingly deployed not only to answer queries but to maintain persistent, evolving knowledge bases—continuously ingesting sources, revising assertions, and reconciling contradictions. After every edit, the knowledge base must be verified for internal consistency. However, naive full re-verification requires O(n²) pairwise comparisons, exceeding 90 seconds per edit step at 500-page scale and rendering it impractical for continuous maintenance.
Methods: The authors present IncrConsist, an incremental consistency maintenance framework that limits verification to a compact affected set derived from the edit's provenance-graph neighborhood. The framework formalizes five atomic edit operations (Add, Delete, Modify, Merge, Split) and three layered consistency invariants: local schema (INV1), reference chain (INV2), and mutex-based global semantic consistency (INV3). Affected-set computation integrates strength-weighted provenance BFS, keyword-Jaccard semantic expansion, and word-boundary mutex detection, thereby addressing the graph-topology gap that prevents pure graph traversal from identifying globally inconsistent assertion pairs.
Results: On a synthetic 61-page AI-course knowledge base (1,220 assertions, 908 typed provenance edges), IncrConsist achieves a 1,660× speedup over full re-verification, reduces the checked assertion count by 99.3% (an average of 10.0 nodes per step), and attains a violation recall of 0.80, compared with 0.66 for a naive 1-hop baseline. Scalability experiments across 50–500 pages confirm sub-linear time growth (3.4× for a 10× scale increase).
Conclusions: IncrConsist is the only method evaluated that detects mutex-based global semantic contradictions, a class of inconsistencies that is entirely missed by graph-traversal methods. The results demonstrate that incremental affected-set computation—a classical technique in database materialization and ontology maintenance—can be adapted to LLM-maintained text knowledge bases, through extensions for typed provenance strength and lexical mutex conflict.
Table-to-report generation refers to the task of automatically generating article-level analyt- ical reports from relational tables and is an essential capability for automated data science and decision support. Its central challenge lies in systematically discovering verifiable com- posite insights across tables, attr...
Agents build knowledge graphs as memory, and building them has become easy. Maintaining them has not. When a source is retracted, overruled, or erased, everything built on top of it (entity merges, entailed edges, community summaries) must be re-examined, and the maintainer must choose between deleting too much and too...
This work isolates the source of the loss, finding that the positional mismatch has minor effect, and independently cached artifacts retain faithful representations: reading a provided artifact stays largely accurate, and performance degrades only when the model must select among multiple artifacts.
Xing-Hao Chen, Jun-Nan Dong, Cai Ke et al.· 1 citation· ⚡1
Hardware datasheets contain engineering specifications essential for component selection, system integration, and hardware compatibility verification. However, manual inspection is tedious and error-prone because datasheets are lengthy and heterogeneous, with dense information fragmented across tables, figures, and tex...
DocuDebug, an interactive editor that reframes document verification as a software engineering task, is presented, demonstrating how structured visual diagnostics can shift AI-assisted writing from opaque global generation to systematic, user-controlled co-creation.
Hitoshi Matsuyama, Keita Higuchi· ACM Symposium on User Interf...· 0 citations
Large language model (LLM) agents have bounded context windows and therefore need external storage to retain knowledge across long interactions. Keeping that knowledge consistent requires reconciling changing facts, duplicate mentions, and competing retrieval priorities. We present Seamless, a self-maintaining knowledg...
Nikita Smirnov· IEEE Access· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.