# Walking on the DARKSIDE

arXiv: https://arxiv.org/abs/2608.23370 · HTML: https://mlsanity.com/paper/2608.23370/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 43 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Builds on (most cited first, 17 of 17)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Hallucination is Inevitable: An Innate Limitation of Large Language Models](https://mlsanity.com/paper/2401.11817/) (2024)
- [Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks](https://mlsanity.com/paper/2307.02477/) (2023)
- [MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs](https://mlsanity.com/paper/2501.17399/) (2025)
- [Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation](https://mlsanity.com/paper/2305.15852/) (2023)
- [Does Spatial Cognition Emerge in Frontier Models?](https://mlsanity.com/paper/2410.06468/) (2024)
- [A Benchmark to Understand the Role of Knowledge Graphs on Large Language Model's Accuracy for Question Answering on Enterprise SQL Databases](https://mlsanity.com/paper/2311.07509/) (2023)
- [Finding Flawed Fictions: Evaluating Complex Reasoning in Language Models via Plot Hole Detection](https://mlsanity.com/paper/2504.11900/) (2025)
- [Large Language Model Reasoning Failures](https://mlsanity.com/paper/2602.06176/) (2026)
- [Remote Labor Index: Measuring AI Automation of Remote Work](https://mlsanity.com/paper/2510.26787/) (2025)
- [Intelligent AI Delegation](https://mlsanity.com/paper/2602.11865/) (2026)
- [Strong hallucinations from negation and how to fix them](https://mlsanity.com/paper/2402.10543/) (2024)
- [Neurosymbolic Graph Enrichment for Grounded World Models](https://mlsanity.com/paper/2411.12671/) (2024)
- [Mary, the Cheeseburger-Eating Vegetarian: Do LLMs Recognize Incoherence in Narratives?](https://mlsanity.com/paper/2512.07777/) (2025)
- [Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation](https://mlsanity.com/paper/2510.21891/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) do not natively track the path of exclusions that a coherent discourse demands. When an input rests on a fabricated authority, a misapplied mechanism, or a surreptitious analogy, an unsteered LLM tends to engage with it as if it were well-posed, and this affects its generation. POLANYI++, an LLM-steering method that uses heuristics, ontologies and problem-solving methods for tacit-knowledge extraction, produces an Extended Knowledge Graph (XKG) in OWL2, but when a sophisticated nonsensical input is reified into the graph alongside the legitimate triples, it gets hardly detectable by automated reasoners, since the XKG is generated jointly with the wrong assumptions. We introduce DARKSIDE, a coherence-auditing method on top of POLANYI++. DARKSIDE formalises an explicit data structure of accumulated exclusions over discourse time, complemented by a warrant axis that classifies each named referent as Warranted, Unattested, Misattributed or Fabricated. The method is anchored in nine theoretical fragments unified under a shared deep frame of path integrity. The resulting DARKPOLANYI is evaluated as a steering layer over Gemini 3 on BSBench, a 100-item adversarial corpus of sophisticated-sounding nonsense across multiple domains, with Claude Sonnet 4.6 as an independent judge. DARKPOLANYI scores 1.89/2 mean versus 0.95/2 for the unsteered Gemini 3 Pro baseline; on the 97 cases with valid judgments in both arms, paired McNemar gives a paired bootstrap mean-diff = +0.92 (95% CI [+0.75, +1.08], p = 0.0001). The evidence supports an architectural claim: when an LLM forward pass is wrapped in an ontology-mediated auditing, structurally inevitable hallucination can be partially recovered. The XKG functions as the missing memory that LLMs lack, and the warrant axis as an epistemic firewall.