From Hallucination to Scheming: A Unified Taxonomy and Benchmark Analysis for LLM Deception

• URL: http://arxiv.org/abs/2604.04788v1
• Date: Mon, 06 Apr 2026 15:57:47 GMT
• Title: From Hallucination to Scheming: A Unified Taxonomy and Benchmark Analysis for LLM Deception
• Abstract summary: We propose a unified taxonomy organized along three complementary dimensions: degree of goal-directedness, object of deception, and mechanism.<n>Applying this taxonomy to 50 existing benchmarks reveals that every benchmark tests fabrication while pragmatic distortion, attribution, and capability self-knowledge remain critically under-covered.
• Score: 32.09232866919422
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) produce systematically misleading outputs, from hallucinated citations to strategic deception of evaluators, yet these phenomena are studied by separate communities with incompatible terminology. We propose a unified taxonomy organized along three complementary dimensions: degree of goal-directedness (behavioral to strategic deception), object of deception, and mechanism (fabrication, omission, or pragmatic distortion). Applying this taxonomy to 50 existing benchmarks reveals that every benchmark tests fabrication while pragmatic distortion, attribution, and capability self-knowledge remain critically under-covered, and strategic deception benchmarks are nascent. We offer concrete recommendations for developers and regulators, including a minimal reporting template for positioning future work within our framework.

Related papers

• From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape [79.30826980815927]
  rubrics are explicit criteria sets that transform complex quality judgments into structured and actionable standards.<n>We systematically organize existing rubric designs, examine their construction and optimization, and analyze their role across evaluation and training.
  arXiv  Detail & Related papers  (2026-06-07T13:34:55Z)
• Refining and Reusing Annotation Guidelines for LLM Annotation [17.04320576398815]
  Large Language Models (LLMs) demonstrate remarkable performance on zero-shot annotation tasks.<n>LLMs often struggle with the specialized conventions of gold-standard benchmarks.<n>We propose an iterative moderation framework that simulates the early phases of annotation projects.
  arXiv  Detail & Related papers  (2026-05-20T07:03:42Z)
• Beyond the Academic Monoculture: A Unified Framework and Industrial Perspective for Attributed Graph Clustering [75.50670592447219]
  Attributed Graph Clustering (AGC) is a fundamental unsupervised task that partitions nodes into cohesive groups by jointly modeling structural topology and node attributes.<n>This survey provides a comprehensive, industrially grounded review of AGC from three complementary perspectives.
  arXiv  Detail & Related papers  (2026-03-21T14:15:34Z)
• Beyond Holistic Scores: Automatic Trait-Based Quality Scoring of Argumentative Essays [15.895792302323883]
  In educational contexts, teachers and learners require interpretable, trait-level feedback.<n>We study trait-based Automatic Argumentative Essay Scoring using two complementary modeling paradigms.<n>We show that explicitly modeling score ordinality substantially improves agreement with human raters.
  arXiv  Detail & Related papers  (2026-02-04T14:30:52Z)
• LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals [18.015918696398085]
  Concept-based explanations quantify how high-level concepts influence model behavior.<n>Existing benchmarks rely on costly human-written counterfactuals that serve as an imperfect proxy.<n>We introduce a framework for constructing datasets containing structural counterfactual pairs: LIBERTy.
  arXiv  Detail & Related papers  (2026-01-15T18:54:50Z)
• Implicit Reasoning in Large Language Models: A Comprehensive Survey [67.53966514728383]
  Large Language Models (LLMs) have demonstrated strong generalization across a wide range of tasks.<n>Recent studies have shifted attention from explicit chain-of-thought prompting toward implicit reasoning.<n>This survey introduces a taxonomy centered on execution paradigms, shifting the focus from representational forms to computational strategies.
  arXiv  Detail & Related papers  (2025-09-02T14:16:02Z)
• Aligning MLLM Benchmark With Human Preferences via Structural Equation Modeling [17.092510377905814]
  evaluating multimodal large language models (MLLMs) remains a fundamental challenge due to a lack of structured, interpretable, and theoretically grounded benchmark designs.<n>We propose a novel framework for aligning MLLM benchmark based on Structural Equation Modeling (SEM) to analyze and quantify the internal validity, dimensional separability, and contribution of benchmark components.<n> Experimental results demonstrate that the proposed benchmark exhibits stronger interpretability, reduced indicator redundancy, and clearer cognitive consistency compared to existing approaches.
  arXiv  Detail & Related papers  (2025-06-13T08:04:56Z)
• Benchmarks as Microscopes: A Call for Model Metrology [76.64402390208576]
  Modern language models (LMs) pose a new challenge in capability assessment. To be confident in our metrics, we need a new discipline of model metrology.
  arXiv  Detail & Related papers  (2024-07-22T17:52:12Z)
• Top-K Pairwise Ranking: Bridging the Gap Among Ranking-Based Measures for Multi-Label Classification [120.37051160567277]
  This paper proposes a novel measure named Top-K Pairwise Ranking (TKPR) A series of analyses show that TKPR is compatible with existing ranking-based measures. On the other hand, we establish a sharp generalization bound for the proposed framework based on a novel technique named data-dependent contraction.
  arXiv  Detail & Related papers  (2024-07-09T09:36:37Z)
• MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation [60.65820977963331]
  We introduce a novel evaluation paradigm for Large Language Models (LLMs) This paradigm shifts the emphasis from result-oriented assessments, which often neglect the reasoning process, to a more comprehensive evaluation. By applying this paradigm in the GSM8K dataset, we have developed the MR-GSM8K benchmark.
  arXiv  Detail & Related papers  (2023-12-28T15:49:43Z)
• An Examination of the Compositionality of Large Generative Vision-Language Models [7.639748270719836]
  Generative Vision-Language Models (GVLMs) have been constructed via multimodal instruction tuning. In this paper, we examine both the evaluation metrics (VisualGPTScore, etc.) and current benchmarks for evaluating the compositionality of GVLMs. We identify the syntactical bias in current benchmarks, which is exploited by the linguistic capability of GVLMs.
  arXiv  Detail & Related papers  (2023-08-21T06:50:29Z)
• Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds [59.71218039095155]
  We evaluate language understanding capacities on simple inference tasks that most humans find trivial. We target (i) grammatically-specified entailments, (ii) premises with evidential adverbs of uncertainty, and (iii) monotonicity entailments. The models exhibit moderate to low performance on these evaluation sets.
  arXiv  Detail & Related papers  (2023-05-24T06:41:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.