Buchumschlag

Multidimensional Consistency Improves Reasoning in Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Lai, Huiyuan, Zhang, Xiao, Nissim, Malvina
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models
von: Lai, Huiyuan, et al.
Veröffentlicht: (2024)

TACLer: Tailored Curriculum Reinforcement Learning for Efficient Reasoning
von: Lai, Huiyuan, et al.
Veröffentlicht: (2026)

IT5: Text-to-text Pretraining for Italian Language Understanding and Generation
von: Sarti, Gabriele, et al.
Veröffentlicht: (2022)

Puzzled By ChatGPT? No more! A Jigsaw Puzzle to Promote AI Literacy and Awareness
von: Padovani, Francesca, et al.
Veröffentlicht: (2026)

Multi-property Steering of Large Language Models with Dynamic Activation Composition
von: Scalena, Daniel, et al.
Veröffentlicht: (2024)

Fine-tuning with HED-IT: The impact of human post-editing for dialogical language models
von: Occhipinti, Daniela, et al.
Veröffentlicht: (2024)

Can Model Uncertainty Function as a Proxy for Multiple-Choice Question Item Difficulty?
von: Zotos, Leonidas, et al.
Veröffentlicht: (2024)

Are You Doubtful? Oh, It Might Be Difficult Then! Exploring the Use of Model Uncertainty for Question Difficulty Estimation
von: Zotos, Leonidas, et al.
Veröffentlicht: (2024)

Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses
von: Sarti, Gabriele, et al.
Veröffentlicht: (2024)

When Harry Meets Superman: The Role of The Interlocutor in Persona-Based Dialogue Generation
von: Occhipinti, Daniela, et al.
Veröffentlicht: (2025)

Choosy Babies Need One Coach: Inducing Mode-Seeking Behavior in BabyLlama with Reverse KL Divergence
von: Shi, Shaozhen, et al.
Veröffentlicht: (2024)

OntoURL: A Benchmark for Evaluating Large Language Models on Symbolic Ontological Understanding, Reasoning and Learning
von: Zhang, Xiao, et al.
Veröffentlicht: (2025)

Practising responsibility: Ethics in NLP as a hands-on course
von: Nissim, Malvina, et al.
Veröffentlicht: (2025)

A gentle push funziona benissimo: making instructed models in Italian via contrastive activation steering
von: Scalena, Daniel, et al.
Veröffentlicht: (2024)

The Role of the Availability Heuristic in Multiple-Choice Answering Behaviour
von: Zotos, Leonidas, et al.
Veröffentlicht: (2026)

Steering Large Language Models for Machine Translation Personalization
von: Scalena, Daniel, et al.
Veröffentlicht: (2025)

Unsupervised Word-level Quality Estimation for Machine Translation Through the Lens of Annotators (Dis)agreement
von: Sarti, Gabriele, et al.
Veröffentlicht: (2025)

Quantifying the Plausibility of Context Reliance in Neural Machine Translation
von: Sarti, Gabriele, et al.
Veröffentlicht: (2023)

ARGUS: Seeing the Influence of Narrative Features on Persuasion in Argumentative Texts
von: Nabhani, Sara, et al.
Veröffentlicht: (2026)

QE4PE: Word-level Quality Estimation for Human Post-Editing
von: Sarti, Gabriele, et al.
Veröffentlicht: (2025)

Not All Votes Count! Programs as Verifiers Improve Self-Consistency of Language Models for Math Reasoning
von: Toh, Vernon Y. H., et al.
Veröffentlicht: (2024)

Calibrating Reasoning in Language Models with Internal Consistency
von: Xie, Zhihui, et al.
Veröffentlicht: (2024)

DCR-Consistency: Divide-Conquer-Reasoning for Consistency Evaluation and Improvement of Large Language Models
von: Cui, Wendi, et al.
Veröffentlicht: (2024)

Cross-lingual Self-Consistency for Multilingual Reasoning with Language Models
von: Elhady, Ahmed, et al.
Veröffentlicht: (2026)

Improving Data and Reward Design for Scientific Reasoning in Large Language Models
von: Chen, Zijie, et al.
Veröffentlicht: (2026)

Improving the Robustness of Large Language Models via Consistency Alignment
von: Zhao, Yukun, et al.
Veröffentlicht: (2024)

Hallucination Detection via Internal States and Structured Reasoning Consistency in Large Language Models
von: Song, Yusheng, et al.
Veröffentlicht: (2025)

Exploring and Evaluating Multimodal Knowledge Reasoning Consistency of Multimodal Large Language Models
von: Jia, Boyu, et al.
Veröffentlicht: (2025)

Refining Answer Distributions for Improved Large Language Model Reasoning
von: Pal, Soumyasundar, et al.
Veröffentlicht: (2024)

NLP Methods May Actually Be Better Than Professors at Estimating Question Difficulty
von: Zotos, Leonidas, et al.
Veröffentlicht: (2025)

ToW: Thoughts of Words Improve Reasoning in Large Language Models
von: Xu, Zhikun, et al.
Veröffentlicht: (2024)

Evaluating Consistency and Reasoning Capabilities of Large Language Models
von: Saxena, Yash, et al.
Veröffentlicht: (2024)

TextReasoningBench: Does Reasoning Really Improve Text Classification in Large Language Models?
von: Guo, Xinyu, et al.
Veröffentlicht: (2026)

CROPE: Evaluating In-Context Adaptation of Vision and Language Models to Culture-Specific Concepts
von: Nikandrou, Malvina, et al.
Veröffentlicht: (2024)

LexChain: Modeling Legal Reasoning Chains for Chinese Tort Case Analysis
von: Xie, Huiyuan, et al.
Veröffentlicht: (2025)

SarcasmMiner: A Dual-Track Post-Training Framework for Robust Audio-Visual Sarcasm Reasoning
von: Li, Zhu, et al.
Veröffentlicht: (2026)

Semantic Self-Consistency: Enhancing Language Model Reasoning via Semantic Weighting
von: Knappe, Tim, et al.
Veröffentlicht: (2024)

Towards Logically Consistent Language Models via Probabilistic Reasoning
von: Calanzone, Diego, et al.
Veröffentlicht: (2024)

Improving Parametric Knowledge Access in Reasoning Language Models
von: Ma, Melody, et al.
Veröffentlicht: (2026)

Re-Reading Improves Reasoning in Large Language Models
von: Xu, Xiaohan, et al.
Veröffentlicht: (2023)