Copertina

A Simple Ensemble Strategy for LLM Inference: Towards More Stable Text Classification

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Niimi, Junichiro
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Stable LLM Ensemble: Interaction between Example Representativeness and Diversity
di: Niimi, Junichiro
Pubblicazione: (2025)

Reference Points in LLM Sentiment Analysis: The Role of Structured Context
di: Niimi, Junichiro
Pubblicazione: (2025)

Hierarchical Memorization in Large Language Models: Evidence from Citation Generation
di: Niimi, Junichiro
Pubblicazione: (2025)

Hallucinations in Bibliographic Recommendation: Citation Frequency as a Proxy for Training Data Redundancy
di: Niimi, Junichiro
Pubblicazione: (2025)

Distortion Instead of Hallucination: The Effect of Reasoning Under Strict Constraints
di: Niimi, Junichiro
Pubblicazione: (2026)

The Mouth is Not the Brain: Bridging Energy-Based World Models and Language Generation
di: Niimi, Junichiro
Pubblicazione: (2026)

Three-in-One World Model: Energy-Based Consistency, Prediction, and Counterfactual Inference for Marketing Intervention
di: Niimi, Junichiro
Pubblicazione: (2026)

When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling
di: Yun, Heecheol, et al.
Pubblicazione: (2025)

Dynamic Sentiment Analysis with Local Large Language Models using Majority Voting: A Study on Factors Affecting Restaurant Evaluation
di: Niimi, Junichiro
Pubblicazione: (2024)

NYT-Connections: A Deceptively Simple Text Classification Task that Stumps System-1 Thinkers
di: Lopez, Angel Yahir Loredo, et al.
Pubblicazione: (2024)

Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling
di: Yu, Yao-Ching, et al.
Pubblicazione: (2024)

MedRECT: A Medical Reasoning Benchmark for Error Correction in Clinical Texts
di: Iwase, Naoto, et al.
Pubblicazione: (2025)

Inference-Time Selective Debiasing to Enhance Fairness in Text Classification Models
di: Kuzmin, Gleb, et al.
Pubblicazione: (2024)

Large Language Models Are Still Misled by Simple Bias Ensembles
di: Sun, Zhouhao, et al.
Pubblicazione: (2025)

MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents
di: Tan, Haoran, et al.
Pubblicazione: (2025)

CAST: Achieving Stable LLM-based Text Analysis for Data Analytics
di: Xie, Jinxiang, et al.
Pubblicazione: (2026)

Simple Hack for Transformers against Heavy Long-Text Classification on a Time- and Memory-Limited GPU Service
di: Mutasodirin, Mirza Alim, et al.
Pubblicazione: (2024)

PLEX: Perturbation-free Local Explanations for LLM-Based Text Classification
di: Rahulamathavan, Yogachandran, et al.
Pubblicazione: (2025)

That's So FETCH: Fashioning Ensemble Techniques for LLM Classification in Civil Legal Intake and Referral
di: Steenhuis, Quinten
Pubblicazione: (2025)

Ensemble Bayesian Inference: Leveraging Small Language Models to Achieve LLM-level Accuracy in Profile Matching Tasks
di: Sato, Haru-Tada, et al.
Pubblicazione: (2025)

Parameterized Synthetic Text Generation with SimpleStories
di: Finke, Lennart, et al.
Pubblicazione: (2025)

Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems
di: Chen, Lingjiao, et al.
Pubblicazione: (2024)

Towards Reliable Detection of LLM-Generated Texts: A Comprehensive Evaluation Framework with CUDRT
di: Tao, Zhen, et al.
Pubblicazione: (2024)

CoCoP: Enhancing Text Classification with LLM through Code Completion Prompt
di: Mohajeri, Mohammad Mahdi, et al.
Pubblicazione: (2024)

Towards Intelligent Legal Document Analysis: CNN-Driven Classification of Case Law Texts
di: Hossain, Moinul, et al.
Pubblicazione: (2026)

SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation
di: Liu, Xiaoze, et al.
Pubblicazione: (2024)

Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
di: Al-Tawaha, Ahmad, et al.
Pubblicazione: (2026)

Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM
di: Zhang, Ruohong, et al.
Pubblicazione: (2023)

Don't Just Demo, Teach Me the Principles: A Principle-Based Multi-Agent Prompting Strategy for Text Classification
di: Wei, Peipei, et al.
Pubblicazione: (2025)

Adverb Is the Key: Simple Text Data Augmentation with Adverb Deletion
di: Choi, Juhwan, et al.
Pubblicazione: (2024)

Language Model Meets Prototypes: Towards Interpretable Text Classification Models through Prototypical Networks
di: Wen, Ximing
Pubblicazione: (2024)

Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL
di: Yao, Zhewei, et al.
Pubblicazione: (2025)

Multi-Modal Vision vs. Text-Based Parsing: Benchmarking LLM Strategies for Invoice Processing
di: Berghaus, David, et al.
Pubblicazione: (2025)

Harnessing Consistency for Robust Test-Time LLM Ensemble
di: Zeng, Zhichen, et al.
Pubblicazione: (2025)

MGSM-Pro: A Simple Strategy for Robust Multilingual Mathematical Reasoning Evaluation
di: Xu, Tianyi, et al.
Pubblicazione: (2026)

Annotation Guidelines-Based Knowledge Augmentation: Towards Enhancing Large Language Models for Educational Text Classification
di: Liu, Shiqi, et al.
Pubblicazione: (2024)

Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds
di: Basmov, Victoria, et al.
Pubblicazione: (2023)

Political Leaning and Politicalness Classification of Texts
di: Volf, Matous, et al.
Pubblicazione: (2025)

A Simple and Effective $L_2$ Norm-Based Strategy for KV Cache Compression
di: Devoto, Alessio, et al.
Pubblicazione: (2024)

Drift No More? Context Equilibria in Multi-Turn LLM Interactions
di: Dongre, Vardhan, et al.
Pubblicazione: (2025)