paper-with-me

Papers

Beyond "Hallucinations": A Framework for Stable Human-AI Reasoning

2025-10-16 · Rikard Rosenbacke, Carl Rosenbacke, Victor Rosenbacke, Martin McKee arxiv

As large language models (LLMs) become integrated into everyday and high-stakes decision-making, they inherit the ambiguity and biases of human language. While they produce fluent and coherent outputs, they rely on statistical pattern prediction rather than grounded reasoning, creating a risk of outputs that are plausible but incorrect. This paper argues that these failures are not only technical but cognitive. LLMs reproduce associative patterns similar to intuitive human reasoning, amplifying systematic misinterpretations when combined with human users. To analyse this, we introduce the Rose-Frame, a cognitive-epistemological framework for diagnosing breakdowns in human-AI interaction. The framework identifies three recurrent traps: (i) map vs territory, distinguishing representations from reality; (ii) intuition vs reason, separating fast associative judgments from reflective reasoning; and (iii) conflict vs confirmation, examining whether ideas are critically tested or mutually reinforced. These mechanisms can compound into epistemic drift when human and model reasoning interact. We show how these failures emerge in practice and propose human-side interventions, including interpretive cues, reflective prompts, and structured disagreement, to stabilise reasoning. Rather than modifying models, the framework focuses on governing interaction. The central claim is that fluency can create an illusion of understanding. Aligning AI therefore requires not only technical improvements but structures that enable reflective and falsifiable human oversight.

📄 PDF Abstract BibTeX arXiv:2510.14665

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability

2026-03-11 · Xinyan Jiang, Ninghao Liu, Di Wang, Lijie Hu arxiv

Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning. We introduce TRACED, a framework that assesses reasoning quality through theoretically grounded geometric k…

Thinking, Faithful and Stable: Mitigating Hallucinations in LLMs

2025-11-19 · Chelsea Zou, Yiheng Yao, Basant Khalil arxiv

This project develops a self correcting framework for large language models (LLMs) that detects and mitigates hallucinations during multi-step reasoning. Rather than relying solely on final answer correctness, our approa…

Reinforcement Learning

Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation

2026-01-06 · Qianchi Zhang, Hainan Zhang, Liang Pang, Hongwei Zheng 외 arxiv

Retrieval-Augmented Generation (RAG) has become a key paradigm for reducing factual hallucinations in Large Language Models (LLMs), yet little is known about how the order of retrieved documents affects model behavior. W…

Difference Feedback: Generating Multimodal Process-Level Supervision for VLM Reinforcement Learning

2026-03-29 · Feiding, Yongkang Zhang, Yuhao Liao, Zijian Zeng 외 arxiv

Vision--language models (VLMs) are increasingly aligned via Group Relative Policy Optimization (GRPO)-style training. However, relying solely on terminal outcome rewards yields sparse credit assignment in multi-step reas…

Reinforcement LearningMultimodal Reasoning

Reducing Tool Hallucination via Reliability Alignment

2024-12-05 · Hongshen Xu, Su Zhu, Zihan Wang, Hang Zheng 외

Large Language Models (LLMs) have extended their capabilities beyond language generation to interact with external systems through tool calling, offering powerful potential for real-world applications. However, the pheno…

HallucinationText Generation