Imagen de Portada

Anchored Confabulation: Partial Evidence Non-Monotonically Amplifies Confident Hallucination in LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Lathkar, Ashish Balkishan
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Critical Confabulation: Can LLMs Hallucinate for Social Good?
por: Sui, Peiqi, et al.
Publicado: (2025)

Confabulation: The Surprising Value of Large Language Model Hallucinations
por: Sui, Peiqi, et al.
Publicado: (2024)

Synthetic Fluency: Hallucinations, Confabulations, and the Creation of Irish Words in LLM-Generated Translations
por: Castilho, Sheila, et al.
Publicado: (2025)

Confabulations from ACL Publications (CAP): A Dataset for Scientific Hallucination Detection
por: Gamba, Federica, et al.
Publicado: (2025)

Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models
por: Zhou, Tianyi, et al.
Publicado: (2025)

Predictable Confabulations: Factual Recall by LLMs Scales with Model Size and Topic Frequency
por: Smith, Matthew L., et al.
Publicado: (2026)

Can Hallucinations Help? Boosting LLMs for Drug Discovery
por: Yuan, Shuzhou, et al.
Publicado: (2025)

ReFACT: A Benchmark for Scientific Confabulation Detection with Positional Error Annotations
por: Wang, Yindong, et al.
Publicado: (2025)

When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language Models
por: Park, Jungwon, et al.
Publicado: (2026)

Lowest Span Confidence: A Zero-Shot Metric for Efficient and Black-Box Hallucination Detection in LLMs
por: Qiao, Yitong, et al.
Publicado: (2026)

DECK: A Consistency x Confidence Taxonomy of LLM Hallucinations
por: Chauhan, Mohit Singh
Publicado: (2026)

Anchors in the Machine: Behavioral and Attributional Evidence of Anchoring Bias in LLMs
por: Valencia-Clavijo, Felipe
Publicado: (2025)

Taming Object Hallucinations with Verified Atomic Confidence Estimation
por: Liu, Jiarui, et al.
Publicado: (2025)

On Verbalized Confidence Scores for LLMs
por: Yang, Daniel, et al.
Publicado: (2024)

Persona Inconstancy in Multi-Agent LLM Collaboration: Conformity, Confabulation, and Impersonation
por: Baltaji, Razan, et al.
Publicado: (2024)

Do Hallucination Neurons Generalize? Evidence from Cross-Domain Transfer in LLMs
por: Vaddi, Snehit, et al.
Publicado: (2026)

The First Token Knows: Single-Decode Confidence for Hallucination Detection
por: Gabriel, Mina
Publicado: (2026)

More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
por: Liu, Chengzhi, et al.
Publicado: (2025)

Sentence-Anchored Gist Compression for Long-Context LLMs
por: Tarasov, Dmitrii, et al.
Publicado: (2025)

Can LLMs Detect Their Own Hallucinations?
por: Kadotani, Sora, et al.
Publicado: (2025)

Shared Imagination: LLMs Hallucinate Alike
por: Zhou, Yilun, et al.
Publicado: (2024)

Hard Non-Monotonic Attention for Character-Level Transduction
por: Wu, Shijie, et al.
Publicado: (2018)

Multicalibration for Confidence Scoring in LLMs
por: Detommaso, Gianluca, et al.
Publicado: (2024)

Confidence Estimation for LLMs in Multi-turn Interactions
por: Zhang, Caiqi, et al.
Publicado: (2026)

On the Robustness of Verbal Confidence of LLMs in Adversarial Attacks
por: Obadinma, Stephen, et al.
Publicado: (2025)

I-CALM: Incentivizing Confidence-Aware Abstention for LLM Hallucination Mitigation
por: Zong, Haotian, et al.
Publicado: (2026)

Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
por: Xiong, Miao, et al.
Publicado: (2023)

Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning
por: Liao, Yiming, et al.
Publicado: (2026)

From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data
por: Sadi, Md. Rejaul Korim Sadi, et al.
Publicado: (2026)

Attend to Evidence: Evidence-Anchored Spatial Attention Supervision for Multimodal RLVR
por: Hu, Ruina, et al.
Publicado: (2026)

Probabilistic Guarantees for Reducing Contextual Hallucinations in LLMs
por: Rautenberg, Nils, et al.
Publicado: (2026)

Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs
por: Phillips, Edward, et al.
Publicado: (2025)

How Non-Linguistic Is the Indus Sign System? A Synthetic-Baseline Scorecard
por: Nair, Ashish
Publicado: (2026)

Popular LLMs Amplify Race and Gender Disparities in Human Mobility
por: Wu, Xinhua, et al.
Publicado: (2024)

Confidence Estimation in Automatic Short Answer Grading with LLMs
por: Cong, Longwei, et al.
Publicado: (2026)

Supervised Optimism Correction: Be Confident When LLMs Are Sure
por: Zhang, Junjie, et al.
Publicado: (2025)

When to Trust LLMs: Aligning Confidence with Response Quality
por: Tao, Shuchang, et al.
Publicado: (2024)

Confidence Improves Self-Consistency in LLMs
por: Taubenfeld, Amir, et al.
Publicado: (2025)

Facet-Level Tracing of Evidence Uncertainty and Hallucination in RAG
por: Elchafei, Passant, et al.
Publicado: (2026)

Detecting Contextual Hallucinations in LLMs with Frequency-Aware Attention
por: Qi, Siya, et al.
Publicado: (2026)