Cover Image

Class Distillation with Mahalanobis Contrast: An Efficient Training Paradigm for Pragmatic Language Understanding Tasks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Chenlu, Lyu, Weimin, Banerjee, Ritwik
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Paying Attention to Deflections: Mining Pragmatic Nuances for Whataboutism Detection in Online Discourse
by: Phi, Khiem, et al.
Published: (2024)

A Longitudinal, Multinational, and Multilingual Corpus of News Coverage of the Russo-Ukrainian War
by: Mohanty, Dikshya, et al.
Published: (2026)

PUB: A Pragmatics Understanding Benchmark for Assessing LLMs' Pragmatics Capabilities
by: Sravanthi, Settaluri Lakshmi, et al.
Published: (2024)

Beyond Understanding: Evaluating the Pragmatic Gap in LLMs' Cultural Processing of Figurative Language
by: Attia, Mena, et al.
Published: (2025)

Understand the Implication: Learning to Think for Pragmatic Understanding
by: Sravanthi, Settaluri Lakshmi, et al.
Published: (2025)

Understanding Understanding: A Pragmatic Framework Motivated by Large Language Models
by: Leyton-Brown, Kevin, et al.
Published: (2024)

Are Multimodal Large Language Models Pragmatically Competent Listeners in Simple Reference Resolution Tasks?
by: Junker, Simeon, et al.
Published: (2025)

Towards Better Understanding of Contrastive Sentence Representation Learning: A Unified Paradigm for Gradient
by: Li, Mingxin, et al.
Published: (2024)

Training Task Experts through Retrieval Based Distillation
by: Ge, Jiaxin, et al.
Published: (2024)

Do Language Models Understand the Cognitive Tasks Given to Them? Investigations with the N-Back Paradigm
by: Hu, Xiaoyang, et al.
Published: (2024)

Pragmatic Theories Enhance Understanding of Implied Meanings in LLMs
by: Sato, Takuma, et al.
Published: (2025)

The Pragmatic Mind of Machines: Tracing the Emergence of Pragmatic Competence in Large Language Models
by: Yu, Kefan, et al.
Published: (2025)

BadCLM: Backdoor Attack in Clinical Language Models for Electronic Health Records
by: Lyu, Weimin, et al.
Published: (2024)

Developing a Pragmatic Benchmark for Assessing Korean Legal Language Understanding in Large Language Models
by: Kim, Yeeun, et al.
Published: (2024)

Distillation versus Contrastive Learning: How to Train Your Rerankers
by: Xu, Zhichao, et al.
Published: (2025)

NLoRA: Nyström-Initiated Low-Rank Adaptation for Large Language Models
by: Guo, Chenlu, et al.
Published: (2025)

VLCD: Vision-Language Contrastive Distillation for Accurate and Efficient Automatic Placenta Analysis
by: Mehta, Manas, et al.
Published: (2025)

DistilQwen2.5: Industrial Practices of Training Distilled Open Lightweight Language Models
by: Wang, Chengyu, et al.
Published: (2025)

A Training-Free Regeneration Paradigm: Contrastive Reflection Memory Guided Self-Verification and Self-Improvement
by: Li, Yuran, et al.
Published: (2026)

Leveraging Large Language Models for Enhanced NLP Task Performance through Knowledge Distillation and Optimized Training Strategies
by: Huang, Yining, et al.
Published: (2024)

Sensivity of LLMs' Explanations to the Training Randomness:Context, Class & Task Dependencies
by: Loncour, Romain, et al.
Published: (2026)

Contrastive Learning in Distilled Models
by: Lim, Valerie, et al.
Published: (2024)

Pragmatic Competence Evaluation of Large Language Models for the Korean Language
by: Park, Dojun, et al.
Published: (2024)

QCRD: Quality-guided Contrastive Rationale Distillation for Large Language Models
by: Wang, Wei, et al.
Published: (2024)

Distilling Instruction-following Abilities of Large Language Models with Task-aware Curriculum Planning
by: Yue, Yuanhao, et al.
Published: (2024)

A Dual-Task Paradigm to Investigate Sentence Comprehension Strategies in Language Models
by: Emura, Rei, et al.
Published: (2026)

Efficient End-to-End Visual Document Understanding with Rationale Distillation
by: Zhu, Wang, et al.
Published: (2023)

Language Model Training Paradigms for Clinical Feature Embeddings
by: Hu, Yurong, et al.
Published: (2023)

Distilling Fine-grained Sentiment Understanding from Large Language Models
by: Zhang, Yice, et al.
Published: (2024)

A Learning Rate Path Switching Training Paradigm for Version Updates of Large Language Models
by: Wang, Zhihao, et al.
Published: (2024)

Unsupervised Out-of-Distribution Dialect Detection with Mahalanobis Distance
by: Das, Sourya Dipta, et al.
Published: (2023)

CHBench: A Chinese Dataset for Evaluating Health in Large Language Models
by: Guo, Chenlu, et al.
Published: (2024)

Evolutionary Contrastive Distillation for Language Model Alignment
by: Katz-Samuels, Julian, et al.
Published: (2024)

Long-context Non-factoid Question Answering in Indic Languages
by: Mishra, Ritwik, et al.
Published: (2025)

Task-Agnostic Detector for Insertion-Based Backdoor Attacks
by: Lyu, Weimin, et al.
Published: (2024)

AFD-SLU: Adaptive Feature Distillation for Spoken Language Understanding
by: Xie, Yan, et al.
Published: (2025)

Language Models are Bounded Pragmatic Speakers: Understanding RLHF from a Bayesian Cognitive Modeling Perspective
by: Nguyen, Khanh
Published: (2023)

From Correction to Mastery: Reinforced Distillation of Large Language Model Agents
by: Lyu, Yuanjie, et al.
Published: (2025)

LittiChoQA: Literary Texts in Indic Languages Chosen for Question Answering
by: Khandelwal, Aarya, et al.
Published: (2026)

DDK: Distilling Domain Knowledge for Efficient Large Language Models
by: Liu, Jiaheng, et al.
Published: (2024)