Cover Image

Second Guess: Detecting Uncertainty Through Abstention and Answer Stability in Small Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Aravindan, Ashwath Vaithinathan, Kejriwal, Mayank
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Fragile Thoughts: How Large Language Models Handle Chain-of-Thought Perturbations
by: Aravindan, Ashwath Vaithinathan, et al.
Published: (2026)

Code-Driven Planning in Grid Worlds with Large Language Models
by: Aravindan, Ashwath Vaithinathan, et al.
Published: (2025)

Rewarding Intellectual Humility Learning When Not To Answer In Large Language Models
by: Jha, Abha, et al.
Published: (2026)

An Evaluation of Estimative Uncertainty in Large Language Models
by: Tang, Zhisheng, et al.
Published: (2024)

Defining and Evaluating Decision and Composite Risk in Language Models Applied to Natural Language Inference
by: Shen, Ke, et al.
Published: (2024)

HALO: An Ontology for Representing and Categorizing Hallucinations in Large Language Models
by: Nananukul, Navapat, et al.
Published: (2023)

Humanlike Cognitive Patterns as Emergent Phenomena in Large Language Models
by: Tang, Zhisheng, et al.
Published: (2024)

Navigating Semantic Relations: Challenges for Language Models in Abstract Common-Sense Reasoning
by: Gawin, Cole, et al.
Published: (2025)

SelECT-SQL: Self-correcting ensemble Chain-of-Thought for Text-to-SQL
by: Shen, Ke, et al.
Published: (2024)

GRASP: A Grid-Based Benchmark for Evaluating Commonsense Spatial Reasoning
by: Tang, Zhisheng, et al.
Published: (2024)

Answer, Refuse, or Guess? Investigating Risk-Aware Decision Making in Language Models
by: Wu, Cheng-Kuang, et al.
Published: (2025)

Is persona enough for personality? Using ChatGPT to reconstruct an agent's latent personality from simple descriptions
by: Ji, Yongyi, et al.
Published: (2024)

Knowing When Not to Answer: Abstention-Aware Scientific Reasoning
by: Abdaljalil, Samir, et al.
Published: (2026)

Backdoor Defense in Diffusion Models via Spatial Attention Unlearning
by: Jha, Abha, et al.
Published: (2025)

Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations
by: Tomani, Christian, et al.
Published: (2024)

Enhancing Answer Reliability Through Inter-Model Consensus of Large Language Models
by: Amiri-Margavi, Alireza, et al.
Published: (2024)

Energy Landscapes Enable Reliable Abstention in Retrieval-Augmented Large Language Models for Healthcare
by: Shankar, Ravi, et al.
Published: (2025)

Hallucinate Less by Thinking More: Aspect-Based Causal Abstention for Large Language Models
by: Nguyen, Vy, et al.
Published: (2025)

GuessingGame: Measuring the Informativeness of Open-Ended Questions in Large Language Models
by: Hutson, Dylan, et al.
Published: (2025)

Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models
by: Chen, Yuyan, et al.
Published: (2024)

Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability
by: Aravindan, Ashwath Vaithinathan, et al.
Published: (2025)

Hallucination Detection with Small Language Models
by: Cheung, Ming
Published: (2025)

Knowledge Graph Guided Evaluation of Abstention Techniques
by: Vasisht, Kinshuk, et al.
Published: (2024)

An Analysis of Artificial Intelligence Adoption in NIH-Funded Research
by: Nananukul, Navapat, et al.
Published: (2026)

HALT-RAG: A Task-Adaptable Framework for Hallucination Detection with Calibrated NLI Ensembles and Abstention
by: Goswami, Saumya, et al.
Published: (2025)

Prompt Sensitivity and Answer Consistency of Small Open-Source Language Models for Clinical Question Answering in Low-Resource Healthcare
by: Hariprasad, Shravani
Published: (2026)

Sadeed: Advancing Arabic Diacritization Through Small Language Model
by: Aldallal, Zeina, et al.
Published: (2025)

Uncertainty Quantification in Large Language Models Through Convex Hull Analysis
by: Catak, Ferhat Ozgur, et al.
Published: (2024)

Diffusion Language Models Know the Answer Before Decoding
by: Li, Pengxiang, et al.
Published: (2025)

Answering the Unanswerable Is to Err Knowingly: Analyzing and Mitigating Abstention Failures in Large Reasoning Models
by: Liu, Yi, et al.
Published: (2025)

Cross-lingual Editing in Multilingual Language Models
by: Beniwal, Himanshu, et al.
Published: (2024)

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

CausalAbstain: Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstention
by: Sun, Yuxi, et al.
Published: (2025)

Language Modeling and Understanding Through Paraphrase Generation and Detection
by: Wahle, Jan Philip
Published: (2026)

Evaluation Methodology for Large Language Models for Multilingual Document Question and Answer
by: Kahana, Adar, et al.
Published: (2024)

Keep Guessing? When Considering Inference Scaling, Mind the Baselines
by: Yona, Gal, et al.
Published: (2024)

Sacred or Synthetic? Evaluating LLM Reliability and Abstention for Religious Questions
by: Atif, Farah, et al.
Published: (2025)

From Attribution to Abstention: Training-Free Attention-Based Auditing for Clinical Summarization
by: Yan, Qianqi, et al.
Published: (2026)

Improving Phishing Email Detection Performance of Small Large Language Models
by: Lin, Zijie, et al.
Published: (2025)

Mitigating LLM Hallucinations via Conformal Abstention
by: Yadkori, Yasin Abbasi, et al.
Published: (2024)