Image de couverture de livre

Representation Consistency for Accurate and Coherent LLM Answer Aggregation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jiang, Junqi, Bewley, Tom, Amoukou, Salim I., Leofante, Francesco, Rago, Antonio, Mishra, Saumitra, Toni, Francesca
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Synthesising Counterfactual Explanations via Label-Conditional Gaussian Mixture Variational Autoencoders
par: Jiang, Junqi, et autres
Publié: (2025)

Recourse under Model Multiplicity via Argumentative Ensembling (Technical Report)
par: Jiang, Junqi, et autres
Publié: (2023)

Robust Counterfactual Explanations in Machine Learning: A Survey
par: Jiang, Junqi, et autres
Publié: (2024)

Interval Abstractions for Robust Counterfactual Explanations
par: Jiang, Junqi, et autres
Publié: (2024)

Argumentative Ensembling for Robust Recourse under Model Multiplicity
par: Jiang, Junqi, et autres
Publié: (2025)

To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models
par: Hedström, Anna, et autres
Publié: (2025)

ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values
par: Bewley, Tom, et autres
Publié: (2026)

Entropic Projection Alignment: Estimating, Explaining, and Improving Model Performance Under Distribution Shift
par: Amoukou, Salim I., et autres
Publié: (2026)

Provably Robust and Plausible Counterfactual Explanations for Neural Networks via Robust Optimisation
par: Jiang, Junqi, et autres
Publié: (2023)

Sequential Harmful Shift Detection Without Labels
par: Amoukou, Salim I., et autres
Publié: (2024)

Interpreting Language Reward Models via Contrastive Explanations
par: Jiang, Junqi, et autres
Publié: (2024)

Counterfactual Metarules for Local and Global Recourse
par: Bewley, Tom, et autres
Publié: (2024)

RobustX: Robust Counterfactual Explanations Made Easy
par: Jiang, Junqi, et autres
Publié: (2025)

Local and Regional Counterfactual Rules: Summarized and Robust Recourses
par: Amoukou, Salim I., et autres
Publié: (2022)

Regional Explanations: Bridging Local and Global Variable Importance
par: Amoukou, Salim I., et autres
Publié: (2026)

Human-LLM Hybrid Text Answer Aggregation for Crowd Annotations
par: Li, Jiyi
Publié: (2024)

MArgE: Meshing Argumentative Evidence from Multiple Large Language Models for Justifiable Claim Verification
par: Ng, Ming Pok, et autres
Publié: (2025)

Improving LLM Final Representations with Inter-Layer Geometry
par: Ulanovski, Tom, et autres
Publié: (2026)

InterrogateLLM: Zero-Resource Hallucination Detection in LLM-Generated Answers
par: Yehuda, Yakir, et autres
Publié: (2024)

SkillAggregation: Reference-free LLM-Dependent Aggregation
par: Sun, Guangzhi, et autres
Publié: (2024)

Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems
par: Agrawal, Aakriti, et autres
Publié: (2025)

Can Large Language Models perform Relation-based Argument Mining?
par: Gorur, Deniz, et autres
Publié: (2024)

Domaino1s: Guiding LLM Reasoning for Explainable Answers in High-Stakes Domains
par: Chu, Xu, et autres
Publié: (2025)

Quantifying Prediction Consistency Under Fine-Tuning Multiplicity in Tabular LLMs
par: Hamman, Faisal, et autres
Publié: (2024)

MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning
par: Modoranu, Ionut-Vlad, et autres
Publié: (2026)

Explainable Prediction of the Mechanical Properties of Composites with CNNs
par: Raaghav, Varun, et autres
Publié: (2025)

Measuring and Reducing LLM Hallucination without Gold-Standard Answers
par: Wei, Jiaheng, et autres
Publié: (2024)

Out-of-Distribution Detection using Counterfactual Distance
par: Stoica, Maria, et autres
Publié: (2025)

Probing the Limits of the Lie Detector Approach to LLM Deception
par: Berger, Tom-Felix
Publié: (2026)

CLAA: Cross-Layer Attention Aggregation for Accelerating LLM Prefill
par: McDanel, Bradley, et autres
Publié: (2026)

Argumentatively Coherent Judgmental Forecasting
par: Gorur, Deniz, et autres
Publié: (2025)

LLM Circuit Analyses Are Consistent Across Training and Scale
par: Tigges, Curt, et autres
Publié: (2024)

Multilingual Non-Factoid Question Answering with Answer Paragraph Selection
par: Mishra, Ritwik, et autres
Publié: (2024)

Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction
par: Kim, Jang-Hyun, et autres
Publié: (2026)

nanoLM: an Affordable LLM Pre-training Benchmark via Accurate Loss Prediction across Scales
par: Yao, Yiqun, et autres
Publié: (2023)

The Vulnerability of Language Model Benchmarks: Do They Accurately Reflect True LLM Performance?
par: Banerjee, Sourav, et autres
Publié: (2024)

Reliability-Aware Adaptive Self-Consistency for Efficient Sampling in LLM Reasoning
par: Kim, Junseok, et autres
Publié: (2026)

CORAL: Learning Consistent Representations across Multi-step Training with Lighter Speculative Drafter
par: Weng, Yepeng, et autres
Publié: (2025)

Accurate and Diverse LLM Mathematical Reasoning via Automated PRM-Guided GFlowNets
par: Younsi, Adam, et autres
Publié: (2025)

On the Robustness of Answer Formats in Medical Reasoning Models
par: Taveekitworachai, Pittawat, et autres
Publié: (2025)