LLM-CAS: Dynamic Neuron Perturbation for Real-Time Hallucination Correction

• URL: http://arxiv.org/abs/2512.18623v1
• Date: Sun, 21 Dec 2025 06:54:34 GMT
• Title: LLM-CAS: Dynamic Neuron Perturbation for Real-Time Hallucination Correction
• Authors: Jensen Zhang, Ningyuan Liu, Yijia Fan, Zihao Huang, Qinglin Zeng, Kaitong Cai, Jian Wang, Keze Wang,
• Abstract summary: Large language models (LLMs) often generate hallucinated content that lacks factual or contextual grounding.<n>We propose LLM-CAS, a framework that formulates real-time correction as a hierarchical reinforcement learning problem.
• Score: 11.5874975353231
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) often generate hallucinated content that lacks factual or contextual grounding, limiting their reliability in critical applications. Existing approaches such as supervised fine-tuning and reinforcement learning from human feedback are data intensive and computationally expensive, while static parameter editing methods struggle with context dependent errors and catastrophic forgetting. We propose LLM-CAS, a framework that formulates real-time hallucination correction as a hierarchical reinforcement learning problem. LLM-CAS trains an agent to learn a policy that dynamically selects temporary neuron perturbations during inference based on the current context. Unlike prior dynamic approaches that rely on heuristic or predefined adjustments, this policy driven mechanism enables adaptive and fine grained correction without permanent parameter modification. Experiments across multiple language models demonstrate that LLM-CAS consistently improves factual accuracy, achieving gains of 10.98 percentage points on StoryCloze, 2.71 points on TriviaQA, and 2.06 points on the MC1 score of TruthfulQA. These results outperform both static editing methods such as ITI and CAA and the dynamic SADI framework. Overall, LLM-CAS provides an efficient and context aware solution for improving the reliability of LLMs, with promising potential for future multimodal extensions.

Related papers

• Identifying and Transferring Reasoning-Critical Neurons: Improving LLM Inference Reliability via Activation Steering [50.63386303357225]
  We propose AdaRAS, a lightweight test-time framework that improves reasoning reliability by selectively intervening on neuron activations.<n>AdaRAS identifies Reasoning-Critical Neurons (RCNs) via a polarity-aware mean-difference criterion and adaptively steers their activations during inference.<n> Experiments on 10 mathematics and coding benchmarks demonstrate consistent improvements, including over 13% gains on AIME-24 and AIME-25.
  arXiv  Detail & Related papers  (2026-01-27T17:53:01Z)
• Problems With Large Language Models for Learner Modelling: Why LLMs Alone Fall Short for Responsible Tutoring in K--12 Education [4.658972861389497]
  The rapid rise of large language model (LLM)-based tutors in K--12 education has fostered a misconception that generative models can replace traditional learner modelling for adaptive instruction.<n>This study synthesises evidence on limitations of LLM-based tutors and empirically investigates one critical issue: the accuracy, reliability, and temporal coherence of assessing learners' evolving knowledge over time.
  arXiv  Detail & Related papers  (2025-12-28T18:26:22Z)
• Beyond Static LLM Policies: Imitation-Enhanced Reinforcement Learning for Recommendation [23.945049006150555]
  Large language models (LLMs) have become critical tools for enhancing user engagement by delivering personalized content across diverse digital platforms.<n>Direct deployment of LLMs as primary recommendation policies presents notable challenges, including persistent latency issues.<n>This paper proposes a novel offline reinforcement learning framework that leverages imitation learning from LLM-generated trajectories.
  arXiv  Detail & Related papers  (2025-10-15T07:28:29Z)
• HCRMP: A LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving [4.340881027724334]
  Large Language Models (LLMs) with Reinforcement Learning (RL) can enhance autonomous driving (AD) performance in complex scenarios.<n> Evaluations show that state-of-the-art LLM indicates a non-hallucination rate of only approximately 57.95% when assessed on essential driving-related tasks.<n>This paper argues that maintaining relative independence between the LLM and the RL is vital for solving the hallucinations problem.
  arXiv  Detail & Related papers  (2025-05-21T17:47:24Z)
• LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization [59.75242204923353]
  We introduce LLM-Lasso, a framework that leverages large language models (LLMs) to guide feature selection in Lasso regression.<n>LLMs generate penalty factors for each feature, which are converted into weights for the Lasso penalty using a simple, tunable model.<n>Features identified as more relevant by the LLM receive lower penalties, increasing their likelihood of being retained in the final model.
  arXiv  Detail & Related papers  (2025-02-15T02:55:22Z)
• Adaptive Distraction: Probing LLM Contextual Robustness with Automated Tree Search [76.54475437069395]
  Large Language Models (LLMs) often struggle to maintain their original performance when faced with semantically coherent but task-irrelevant contextual information.<n>We propose a dynamic distraction generation framework based on tree search, where the generation process is guided by model behavior.
  arXiv  Detail & Related papers  (2025-02-03T18:43:36Z)
• Iter-AHMCL: Alleviate Hallucination for Large Language Model via Iterative Model-level Contrastive Learning [16.883679810267342]
  Iterative Model-level Contrastive Learning (Iter-AHMCL) to address hallucination. This paper introduces a novel approach called Iterative Model-level Contrastive Learning (Iter-AHMCL) to address hallucination.
  arXiv  Detail & Related papers  (2024-10-16T00:15:40Z)
• CoMMIT: Coordinated Multimodal Instruction Tuning [90.1532838391285]
  Multimodal large language models (MLLMs) generally involve cooperative learning between a backbone LLM and a feature encoder of non-text input modalities.<n>In this paper, we analyze the MLLM instruction tuning from both theoretical and empirical perspectives.<n>We propose a Multimodal Balance Coefficient that enables quantitative measurement of the balance of learning.
  arXiv  Detail & Related papers  (2024-07-29T23:18:55Z)
• Course-Correction: Safety Alignment Using Synthetic Preferences [17.897817682322053]
  We introduce the textscC$2$-Eval benchmark for quantitative assessment and analyze 10 popular language models. Using an automated pipeline, we create textscC$2$-Syn, a synthetic dataset with 750K pairwise preferences. Experiments on 2 LLMs, textscLlama2-Chat 7B and textscQwen2 7B, show that our method effectively enhances course-correction skills without affecting general performance.
  arXiv  Detail & Related papers  (2024-07-23T16:54:28Z)
• Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing [63.20133320524577]
  We show that editing a small subset of parameters can effectively modulate specific behaviors of large language models (LLMs)<n>Our approach achieves reductions of up to 90.0% in toxicity on the RealToxicityPrompts dataset and 49.2% on ToxiGen.
  arXiv  Detail & Related papers  (2024-07-11T17:52:03Z)
• Temporal Scaling Law for Large Language Models [70.74571133406958]
  We propose the novel concept of Temporal Scaling Law, studying how the test loss of an LLM evolves as the training steps scale up.<n>In contrast to modeling the test loss as a whole in a coarse-grained manner, we break it down and dive into the fine-grained test loss of each token position.<n>We derive the much more precise temporal scaling law by studying the temporal patterns of the parameters in the dynamic hyperbolic-law.
  arXiv  Detail & Related papers  (2024-04-27T05:49:11Z)
• ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks [91.55895047448249]
  This paper presents ReEval, an LLM-based framework using prompt chaining to perturb the original evidence for generating new test cases. We implement ReEval using ChatGPT and evaluate the resulting variants of two popular open-domain QA datasets. Our generated data is human-readable and useful to trigger hallucination in large language models.
  arXiv  Detail & Related papers  (2023-10-19T06:37:32Z)

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.