Cover Image

Cost-Saving LLM Cascades with Early Abstention

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zellinger, Michael J., Liu, Rex, Thomson, Matt
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Rational Tuning of LLM Cascades via Probabilistic Modeling
by: Zellinger, Michael J., et al.
Published: (2025)

Economic Evaluation of LLMs
by: Zellinger, Michael J., et al.
Published: (2025)

Efficiently Deploying LLMs with Controlled Risk
by: Zellinger, Michael J., et al.
Published: (2024)

Fail Fast, or Ask: Mitigating the Deficiencies of Reasoning LLMs with Human-in-the-Loop Systems Engineering
by: Zellinger, Michael J., et al.
Published: (2025)

Herd: Using multiple, smaller LLMs to match the performances of proprietary, large LLMs via an intelligent composer
by: Hari, Surya Narayanan, et al.
Published: (2023)

Improving LLM Reliability through Hybrid Abstention and Adaptive Detection
by: Sharma, Ankit, et al.
Published: (2026)

CascadeDebate: Multi-Agent Deliberation for Cost-Aware LLM Cascades
by: Chang, Raeyoung, et al.
Published: (2026)

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

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

AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions
by: Kirichenko, Polina, et al.
Published: (2025)

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

Reliable Text-to-SQL with Adaptive Abstention
by: Chen, Kaiwen, et al.
Published: (2025)

Learning with Noisy Labels by Adaptive Gradient-Based Outlier Removal
by: Sedova, Anastasiia, et al.
Published: (2023)

Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs
by: Gourabathina, Abinitha, et al.
Published: (2026)

Auditable Decision Models with Learned Abstention and Real-Time Steering
by: Chandrasekaran, Sankaranarayanan Palamadai
Published: (2026)

Counterfactual Reasoning with Knowledge Graph Embeddings
by: Zellinger, Lena, et al.
Published: (2024)

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

Bounded-Abstention Pairwise Learning to Rank
by: Ferrara, Antonio, et al.
Published: (2025)

Leveraging Open-Source Large Language Models for encoding Social Determinants of Health using an Intelligent Router
by: Goel, Akul, et al.
Published: (2024)

What's the Magic Word? A Control Theory of LLM Prompting
by: Bhargava, Aman, et al.
Published: (2023)

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

Task Abstention for Large Language Models in Code Generation
by: Zhou, Yanke, et al.
Published: (2026)

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

TIAR: Trajectory-Informed Advantage Reweighting for LLM Abstention Learning
by: Pan, Muyu, et al.
Published: (2026)

To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models
by: Hedström, Anna, et al.
Published: (2025)

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

Prompt Baking
by: Bhargava, Aman, et al.
Published: (2024)

SEAT: Sparse Entity-Aware Tuning for Knowledge Adaptation while Preserving Epistemic Abstention
by: Shen, William F., et al.
Published: (2025)

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

Learning When Not to Learn: Risk-Sensitive Abstention in Bandits with Unbounded Rewards
by: Liaw, Sarah, et al.
Published: (2025)

COEF-VQ: Cost-Efficient Video Quality Understanding through a Cascaded Multimodal LLM Framework
by: Dong, Xin, et al.
Published: (2024)

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

Explicit Abstention Knobs for Predictable Reliability in Video Question Answering
by: Ortiz, Jorge
Published: (2025)

Cascaded Language Models for Cost-effective Human-AI Decision-Making
by: Fanconi, Claudio, et al.
Published: (2025)

Generalizing Abstention for Noise-Robust Learning in Medical Image Segmentation
by: Moustafa, Wesam, et al.
Published: (2026)

ClinDet-Bench: Beyond Abstention, Evaluating Judgment Determinability of LLMs in Clinical Decision-Making
by: Watanabe, Yusuke, et al.
Published: (2026)

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)

Second Guess: Detecting Uncertainty Through Abstention and Answer Stability in Small Language Models
by: Aravindan, Ashwath Vaithinathan, et al.
Published: (2026)

Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL
by: Zhai, Skylar, et al.
Published: (2026)