Metraipolis › archive › dc_20a15bfcaae2

Detecting Hallucination in LLMs: Tracing the Topological Signatures of Impaired Context Sharing — arXiv:2609.21096

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.21096
License (as archived): CC0-1.0
Archived: 2026-10-10T01:01:42.947Z
SHA-256 of the archived text: 5095c56e5b6b7565a14fcfecacf4f37d45dfb29c1b726af80e6931b14246ad9b
Stable URL of this page: https://metraipolis.com/documento/dc_20a15bfcaae2

How to cite

Detecting Hallucination in LLMs: Tracing the Topological Signatures of Impaired Context Sharing — arXiv:2609.21096 — arXiv (en), https://arxiv.org/abs/2609.21096 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_20a15bfcaae2 (Metraipolis archive dc_20a15bfcaae2, sha256 5095c56e5b6b7565a14fcfecacf4f37d45dfb29c1b726af80e6931b14246ad9b)

BibTeX

@misc{dc20a15bfcaae2,
  title = {Detecting Hallucination in LLMs: Tracing the Topological Signatures of Impaired Context Sharing — arXiv:2609.21096},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21096},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_20a15bfcaae2; sha256 5095c56e5b6b7565a14fcfecacf4f37d45dfb29c1b726af80e6931b14246ad9b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21096. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In this work, we examine the topology of information flow patterns within attention graphs to effectively distinguish hallucinated from non-hallucinated responses. We analyze the Forman-Ricci curvature to identify structural patterns indicating information bottlenecks in attention graphs. We then introduce a method that captures both semi-local and global information-flow characteristics of attention heads associated with hallucinated responses. We evaluate our approach extensively across several LLMs and established benchmarks. Empirical results demonstrate that our proposed single-pass approach provides consistent improvements over existing attention-based and multi-response baselines across two hallucination-detection benchmarks, while achieving competitive performance across diverse LLM architectures. Further analysis reveals that impaired context sharing among tokens during causal generation is strongly associated with hallucination occurrences in LLMs. In particular, hallucinated responses are consistently characterized by an over-reliance on self-attention, diffused context retrieval from earlier tokens, or information over-squashing, especially in the final transformer layer.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.21096 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-10T00:23:42.428Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).