Look Within, Why LLMs Hallucinate: A Causal Perspective
Fuente:
arXiv
Guardado en:
| Autores principales: | Li, He, Chi, Haoang, Liu, Mingyu, Yang, Wenjing |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?
por: Chi, Haoang, et al.
Publicado: (2025)
por: Chi, Haoang, et al.
Publicado: (2025)
A Closer Look into LLMs for Table Understanding
por: Wang, Jia, et al.
Publicado: (2026)
por: Wang, Jia, et al.
Publicado: (2026)
Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations
por: Li, Shanghao, et al.
Publicado: (2026)
por: Li, Shanghao, et al.
Publicado: (2026)
Why LLMs Fail at Causal Discovery and How Interventional Agents Escape
por: Roy, Amartya, et al.
Publicado: (2026)
por: Roy, Amartya, et al.
Publicado: (2026)
Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure
por: Li, Zirui, et al.
Publicado: (2026)
por: Li, Zirui, et al.
Publicado: (2026)
A Cause-Effect Look at Alleviating Hallucination of Knowledge-grounded Dialogue Generation
por: Yu, Jifan, et al.
Publicado: (2024)
por: Yu, Jifan, et al.
Publicado: (2024)
LLMs Are Prone to Fallacies in Causal Inference
por: Joshi, Nitish, et al.
Publicado: (2024)
por: Joshi, Nitish, et al.
Publicado: (2024)
A Geometric Taxonomy of Hallucinations in LLMs
por: Marín, Javier
Publicado: (2026)
por: Marín, Javier
Publicado: (2026)
Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective
por: Kang, Yipeng, et al.
Publicado: (2024)
por: Kang, Yipeng, et al.
Publicado: (2024)
When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs
por: Sun, Zhongxiang, et al.
Publicado: (2026)
por: Sun, Zhongxiang, et al.
Publicado: (2026)
Hallucinate Less by Thinking More: Aspect-Based Causal Abstention for Large Language Models
por: Nguyen, Vy, et al.
Publicado: (2025)
por: Nguyen, Vy, et al.
Publicado: (2025)
Probing LLM Hallucination from Within: Perturbation-Driven Approach via Internal Knowledge
por: Lee, Seongmin, et al.
Publicado: (2024)
por: Lee, Seongmin, et al.
Publicado: (2024)
An Audit on the Perspectives and Challenges of Hallucinations in NLP
por: Venkit, Pranav Narayanan, et al.
Publicado: (2024)
por: Venkit, Pranav Narayanan, et al.
Publicado: (2024)
Hallucination Detection with the Internal Layers of LLMs
por: Preiß, Martin
Publicado: (2025)
por: Preiß, Martin
Publicado: (2025)
COPO: Causal-Oriented Policy Optimization for Hallucinations of MLLMs
por: Guo, Peizheng, et al.
Publicado: (2025)
por: Guo, Peizheng, et al.
Publicado: (2025)
Triggering Hallucinations in LLMs: A Quantitative Study of Prompt-Induced Hallucination in Large Language Models
por: Sato, Makoto
Publicado: (2025)
por: Sato, Makoto
Publicado: (2025)
Why are LLMs' abilities emergent?
por: Havlík, Vladimír
Publicado: (2025)
por: Havlík, Vladimír
Publicado: (2025)
Transformer-Based Spatial-Temporal Counterfactual Outcomes Estimation
por: Li, He, et al.
Publicado: (2025)
por: Li, He, et al.
Publicado: (2025)
Hallucination is Inevitable for LLMs with the Open World Assumption
por: Xu, Bowen
Publicado: (2025)
por: Xu, Bowen
Publicado: (2025)
The Two Sides of the Coin: Hallucination Generation and Detection with LLMs as Evaluators for LLMs
por: Bui, Anh Thu Maria, et al.
Publicado: (2024)
por: Bui, Anh Thu Maria, et al.
Publicado: (2024)
Hallucination Detection and Hallucination Mitigation: An Investigation
por: Luo, Junliang, et al.
Publicado: (2024)
por: Luo, Junliang, et al.
Publicado: (2024)
FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs
por: Bao, Forrest Sheng, et al.
Publicado: (2024)
por: Bao, Forrest Sheng, et al.
Publicado: (2024)
In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation
por: Chen, Shiqi, et al.
Publicado: (2024)
por: Chen, Shiqi, et al.
Publicado: (2024)
How Much Do LLMs Hallucinate across Languages? On Realistic Multilingual Estimation of LLM Hallucination
por: Islam, Saad Obaid ul, et al.
Publicado: (2025)
por: Islam, Saad Obaid ul, et al.
Publicado: (2025)
SINdex: Semantic INconsistency Index for Hallucination Detection in LLMs
por: Abdaljalil, Samir, et al.
Publicado: (2025)
por: Abdaljalil, Samir, et al.
Publicado: (2025)
Hallucination Detection in LLMs with Topological Divergence on Attention Graphs
por: Bazarova, Alexandra, et al.
Publicado: (2025)
por: Bazarova, Alexandra, et al.
Publicado: (2025)
Can Hallucinations Help? Boosting LLMs for Drug Discovery
por: Yuan, Shuzhou, et al.
Publicado: (2025)
por: Yuan, Shuzhou, et al.
Publicado: (2025)
Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems
por: Li, Yihan, et al.
Publicado: (2025)
por: Li, Yihan, et al.
Publicado: (2025)
A Novel Approach to Eliminating Hallucinations in Large Language Model-Assisted Causal Discovery
por: Sng, Grace, et al.
Publicado: (2024)
por: Sng, Grace, et al.
Publicado: (2024)
TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization
por: Tang, Liyan, et al.
Publicado: (2024)
por: Tang, Liyan, et al.
Publicado: (2024)
Why LVLMs Are More Prone to Hallucinations in Longer Responses: The Role of Context
por: Zheng, Ge, et al.
Publicado: (2025)
por: Zheng, Ge, et al.
Publicado: (2025)
Is LLMs Hallucination Usable? LLM-based Negative Reasoning for Fake News Detection
por: Zhang, Chaowei, et al.
Publicado: (2025)
por: Zhang, Chaowei, et al.
Publicado: (2025)
Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations
por: Tomani, Christian, et al.
Publicado: (2024)
por: Tomani, Christian, et al.
Publicado: (2024)
Mitigating Hallucinations in Large Language Models via Causal Reasoning
por: Li, Yuangang, et al.
Publicado: (2025)
por: Li, Yuangang, et al.
Publicado: (2025)
Can LLMs Detect Intrinsic Hallucinations in Paraphrasing and Machine Translation?
por: Gogoulou, Evangelia, et al.
Publicado: (2025)
por: Gogoulou, Evangelia, et al.
Publicado: (2025)
Graphing the Truth: Structured Visualizations for Automated Hallucination Detection in LLMs
por: Agrawal, Tanmay
Publicado: (2025)
por: Agrawal, Tanmay
Publicado: (2025)
Latent Causal Probing: A Formal Perspective on Probing with Causal Models of Data
por: Jin, Charles, et al.
Publicado: (2024)
por: Jin, Charles, et al.
Publicado: (2024)
Why Retrieval-Augmented Generation Fails: A Graph Perspective
por: Guo, Kai, et al.
Publicado: (2026)
por: Guo, Kai, et al.
Publicado: (2026)
Test-time Scaling of LLMs: A Survey from A Subproblem Structure Perspective
por: Yang, Zhuoyi, et al.
Publicado: (2025)
por: Yang, Zhuoyi, et al.
Publicado: (2025)
H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs
por: Gao, Cheng, et al.
Publicado: (2025)
por: Gao, Cheng, et al.
Publicado: (2025)
Ejemplares similares
-
Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?
por: Chi, Haoang, et al.
Publicado: (2025) -
A Closer Look into LLMs for Table Understanding
por: Wang, Jia, et al.
Publicado: (2026) -
Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations
por: Li, Shanghao, et al.
Publicado: (2026) -
Why LLMs Fail at Causal Discovery and How Interventional Agents Escape
por: Roy, Amartya, et al.
Publicado: (2026) -
Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure
por: Li, Zirui, et al.
Publicado: (2026)