Constrained Paraphrase Consistency for LLM Hallucination Detection

• URL: http://arxiv.org/abs/2606.08158v1
• Date: Sat, 06 Jun 2026 13:14:10 GMT
• Title: Constrained Paraphrase Consistency for LLM Hallucination Detection
• Abstract summary: Large language models (LLMs) can generate factually inconsistent claims, motivating accurate and scalable hallucination detectors.<n>We propose Consistency-Constrained Hallucination Detector (CCHD), which formulates training as a constrained optimization problem.
• Score: 11.075787335043238
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) can generate factually inconsistent claims, motivating accurate and scalable hallucination detectors. Prior work largely enlarges training sets via synthesis or new annotations, introducing increasing cost and potential bias while underusing the consistency implied by semantically equivalent paraphrases. We propose Consistency-Constrained Hallucination Detector (CCHD), which formulates training as a constrained optimization problem. The standard cross-entropy on original document-claim pairs is complemented by (i) paraphrase-consistency constraints bounding divergence across paraphrased views, and (ii) label-preservation constraints tying paraphrases to ground truth. We solve the problem by gradient descent-ascent over model parameters and per-view Lagrange multipliers, adding only a few scalar dual variables and no inference-time overhead. With DeBERTa and Flan-T5 backbones, CCHD consistently outperforms strong baselines (FactCG, MiniCheck, and AlignScore) on standard factuality benchmarks, demonstrating its superiority on hallucination detection.

Related papers

• C$^{2}$R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders [56.67585330425431]
  Sparse Autoencoders (SAEs) are widely used to interpret large language models by decomposing activations into sparse, human-understandable features.<n>These issues stem from inconsistent latent assignment across samples.<n>We introduce C$2$R, which penalizes the co-activation of directionally similar latents.
  arXiv  Detail & Related papers  (2026-06-29T17:45:31Z)
• Hacking Generative Perplexity: Why Unconditional Text Evaluation Needs Distributional Metrics [49.443264461057645]
  Diffusion and continuous flow-based language models have emerged as the leading non-autoregressive alternatives to language modeling.<n>Progress in both paradigms is overwhelmingly tracked by generative perplexity (gen-PPL): the per-token negative log-likelihood of samples under a frozen autoregressive (AR) scorer.<n>We argue that this metric is unsound. By construction, gen-PPL measures only predictability under the scoring AR, not grammaticality or semantic coherence.
  arXiv  Detail & Related papers  (2026-06-07T02:35:56Z)
• Chain-based Adaptive Reconfiguration Over Lattices for Hallucination Reduction [0.0]
  CAROL is a probabilistic framework for test-time hallucination reduction in large language models.<n>CAROL defines a semantic uncertainty measure based on the consistency between generated responses and a trusted context.<n>CAROL unifies hallucination detection and mitigation within a single framework.
  arXiv  Detail & Related papers  (2026-05-26T21:28:51Z)
• A Multimodal Dataset for Visually Grounded Ambiguity in Machine Translation [53.06004926782424]
  We present VIDA (Visually-Dependent Ambiguity), a dataset of 2,500 carefully curated instances in which resolving an annotated source span requires visual evidence.<n>We also propose Disambiguation-Centric Metrics that use an LLM-as-a-judge classifier to verify whether annotated ambiguous expressions are resolved correctly at the span level.
  arXiv  Detail & Related papers  (2026-05-03T19:55:06Z)
• HTDC: Hesitation-Triggered Differential Calibration for Mitigating Hallucination in Large Vision-Language Models [0.7252027234425333]
  Hesitation-Triggered Differential inference (HTDC) is a training-free decoding framework that preserves standard full-branch inference.<n>Hesitation-Triggered Differential inference consistently reduces hallucinations while maintaining strong task accuracy.
  arXiv  Detail & Related papers  (2026-04-13T22:47:27Z)
• Neural Uncertainty Principle: A Unified View of Adversarial Fragility and LLM Hallucination [60.197429875410286]
  Adversarial vulnerability in vision and hallucination in large language models are conventionally viewed as separate problems.<n>Formalizing a Neural Uncertainty Principle (NUP) under a loss-induced state, we find that in near-bound regimes, further compression must be accompanied by increased sensitivity dispersion.<n>In vision, masking highly coupled components improves robustness without costly adversarial training.<n>In language, the same prefill-stage probe detects hallucination risk before generating any answer tokens.
  arXiv  Detail & Related papers  (2026-03-20T02:07:10Z)
• Seeing Through the Chain: Mitigate Hallucination in Multimodal Reasoning Models via CoT Compression and Contrastive Preference Optimization [78.94590726578014]
  multimodal reasoning models (MLRMs) remain prone to hallucinations, and effective solutions are still underexplored.<n>We propose C3PO, a training-based mitigation framework comprising textbfCompression and textbfPreference textbfOptimization.
  arXiv  Detail & Related papers  (2026-02-03T11:00:55Z)
• HADSF: Aspect Aware Semantic Control for Explainable Recommendation [4.75127493865044]
  Recent advances in large language models (LLMs) promise more effective information extraction for recommender systems.<n>We propose a two-stage approach that induces a compact, corpus-level aspect vocabulary via adaptive selection and then performs vocabulary-guided, explicitly constrained extraction of structured aspect-opinion triples.<n> Experiments on approximately 3 million reviews spanning 1.5B-70B parameters show that, when integrated into standard rating predictors, HADSF yields consistent reductions in prediction error.
  arXiv  Detail & Related papers  (2025-10-30T20:49:33Z)
• Mitigating Multimodal Hallucinations via Gradient-based Self-Reflection [49.26064449816502]
  We propose a Gradient-based Influence-Aware Constrained Decoding (GACD) method to address text-visual bias and co-occurrence bias.<n>GACD effectively reduces hallucinations and improves the visual grounding of MLLM outputs.
  arXiv  Detail & Related papers  (2025-09-03T08:13:52Z)
• Verify when Uncertain: Beyond Self-Consistency in Black Box Hallucination Detection [25.176984317213858]
  Large Language Models (LLMs) suffer from hallucination problems, which hinder their reliability in sensitive applications.<n>We propose a budget-friendly, two-stage detection algorithm that calls the verifier model only for a subset of cases.
  arXiv  Detail & Related papers  (2025-02-20T21:06:08Z)

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.