Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Lathkar, Ashish Balkishan
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Critical Confabulation: Can LLMs Hallucinate for Social Good?
par: Sui, Peiqi, et autres
Publié: (2025)

Confabulation: The Surprising Value of Large Language Model Hallucinations
par: Sui, Peiqi, et autres
Publié: (2024)

Synthetic Fluency: Hallucinations, Confabulations, and the Creation of Irish Words in LLM-Generated Translations
par: Castilho, Sheila, et autres
Publié: (2025)

Confabulations from ACL Publications (CAP): A Dataset for Scientific Hallucination Detection
par: Gamba, Federica, et autres
Publié: (2025)

Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models
par: Zhou, Tianyi, et autres
Publié: (2025)

Predictable Confabulations: Factual Recall by LLMs Scales with Model Size and Topic Frequency
par: Smith, Matthew L., et autres
Publié: (2026)

Can Hallucinations Help? Boosting LLMs for Drug Discovery
par: Yuan, Shuzhou, et autres
Publié: (2025)

ReFACT: A Benchmark for Scientific Confabulation Detection with Positional Error Annotations
par: Wang, Yindong, et autres
Publié: (2025)

When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language Models
par: Park, Jungwon, et autres
Publié: (2026)

Lowest Span Confidence: A Zero-Shot Metric for Efficient and Black-Box Hallucination Detection in LLMs
par: Qiao, Yitong, et autres
Publié: (2026)

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

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

Taming Object Hallucinations with Verified Atomic Confidence Estimation
par: Liu, Jiarui, et autres
Publié: (2025)

On Verbalized Confidence Scores for LLMs
par: Yang, Daniel, et autres
Publié: (2024)

Persona Inconstancy in Multi-Agent LLM Collaboration: Conformity, Confabulation, and Impersonation
par: Baltaji, Razan, et autres
Publié: (2024)

Do Hallucination Neurons Generalize? Evidence from Cross-Domain Transfer in LLMs
par: Vaddi, Snehit, et autres
Publié: (2026)

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

More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
par: Liu, Chengzhi, et autres
Publié: (2025)

Sentence-Anchored Gist Compression for Long-Context LLMs
par: Tarasov, Dmitrii, et autres
Publié: (2025)

Can LLMs Detect Their Own Hallucinations?
par: Kadotani, Sora, et autres
Publié: (2025)

Shared Imagination: LLMs Hallucinate Alike
par: Zhou, Yilun, et autres
Publié: (2024)

Hard Non-Monotonic Attention for Character-Level Transduction
par: Wu, Shijie, et autres
Publié: (2018)

Multicalibration for Confidence Scoring in LLMs
par: Detommaso, Gianluca, et autres
Publié: (2024)

Confidence Estimation for LLMs in Multi-turn Interactions
par: Zhang, Caiqi, et autres
Publié: (2026)

On the Robustness of Verbal Confidence of LLMs in Adversarial Attacks
par: Obadinma, Stephen, et autres
Publié: (2025)

I-CALM: Incentivizing Confidence-Aware Abstention for LLM Hallucination Mitigation
par: Zong, Haotian, et autres
Publié: (2026)

Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
par: Xiong, Miao, et autres
Publié: (2023)

Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning
par: Liao, Yiming, et autres
Publié: (2026)

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

Attend to Evidence: Evidence-Anchored Spatial Attention Supervision for Multimodal RLVR
par: Hu, Ruina, et autres
Publié: (2026)

Probabilistic Guarantees for Reducing Contextual Hallucinations in LLMs
par: Rautenberg, Nils, et autres
Publié: (2026)

Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs
par: Phillips, Edward, et autres
Publié: (2025)

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

Popular LLMs Amplify Race and Gender Disparities in Human Mobility
par: Wu, Xinhua, et autres
Publié: (2024)

Confidence Estimation in Automatic Short Answer Grading with LLMs
par: Cong, Longwei, et autres
Publié: (2026)

Supervised Optimism Correction: Be Confident When LLMs Are Sure
par: Zhang, Junjie, et autres
Publié: (2025)

When to Trust LLMs: Aligning Confidence with Response Quality
par: Tao, Shuchang, et autres
Publié: (2024)

Confidence Improves Self-Consistency in LLMs
par: Taubenfeld, Amir, et autres
Publié: (2025)

Facet-Level Tracing of Evidence Uncertainty and Hallucination in RAG
par: Elchafei, Passant, et autres
Publié: (2026)

Detecting Contextual Hallucinations in LLMs with Frequency-Aware Attention
par: Qi, Siya, et autres
Publié: (2026)