Cover Image

The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nguyen, Phuc Minh, La, Chinh D., Nguyen, Duy M. H., Chawla, Nitesh V., Nguyen, Binh T., Doan, Khoa D.
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PRISM: A Multi-Dimensional Benchmark for Evaluating LLM Peer Reviewers
by: Loc, Ngoc Phan Phuoc, et al.
Published: (2026)

Class-Aware Contrastive Optimization for Imbalanced Text Classification
by: Khvatskii, Grigorii, et al.
Published: (2024)

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching
by: Nguyen, Truong, et al.
Published: (2026)

Distributional Surgery for Language Model Activations
by: Nguyen, Bao, et al.
Published: (2025)

ViX-Ray: A Vietnamese Chest X-Ray Dataset for Vision-Language Models
by: Nguyen, Duy Vu Minh, et al.
Published: (2026)

Human-Guided Reasoning with Large Language Models for Vietnamese Speech Emotion Recognition
by: Nguyen, Truc, et al.
Published: (2026)

Venomancer: Towards Imperceptible and Target-on-Demand Backdoor Attacks in Federated Learning
by: Nguyen, Son, et al.
Published: (2024)

Swift Cross-Dataset Pruning: Enhancing Fine-Tuning Efficiency in Natural Language Understanding
by: Nguyen, Binh-Nguyen, et al.
Published: (2025)

The Abstraction Gap in Vision-Language Causal Reasoning
by: Hoang, Chinh, et al.
Published: (2026)

VisTA: Vision-Text Alignment Model with Contrastive Learning using Multimodal Data for Evidence-Driven, Reliable, and Explainable Alzheimer's Disease Diagnosis
by: Can, Duy-Cat, et al.
Published: (2025)

KGAlign: Joint Semantic-Structural Knowledge Encoding for Multimodal Fake News Detection
by: La, Tuan-Vinh, et al.
Published: (2025)

Overcoming Catastrophic Forgetting in Federated Class-Incremental Learning via Federated Global Twin Generator
by: Nguyen, Thinh, et al.
Published: (2024)

ViCocktail: Automated Multi-Modal Data Collection for Vietnamese Audio-Visual Speech Recognition
by: Nguyen, Thai-Binh, et al.
Published: (2025)

Unveiling Concept Attribution in Diffusion Models
by: Nguyen, Quang H., et al.
Published: (2024)

READ: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling
by: Nguyen, Thong, et al.
Published: (2023)

REMEMBER: Retrieval-based Explainable Multimodal Evidence-guided Modeling for Brain Evaluation and Reasoning in Zero- and Few-shot Neurodegenerative Diagnosis
by: Can, Duy-Cat, et al.
Published: (2025)

DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding
by: Nguyen, Thong, et al.
Published: (2023)

Retrospective Feature Estimation for Continual Learning
by: Nguyen, Nghia D., et al.
Published: (2024)

FLAT: Latent-Driven Arbitrary-Target Backdoor Attacks in Federated Learning
by: Nguyen, Tuan, et al.
Published: (2025)

SparseSAM: Structured Sparsification of Activations in Segment Anything Models
by: Tran, Hoai-Chau, et al.
Published: (2026)

OpenEvents V1: Large-Scale Benchmark Dataset for Multimodal Event Grounding
by: Nguyen, Hieu, et al.
Published: (2025)

MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning
by: Nguyen, Thong, et al.
Published: (2024)

ViConBERT: Context-Gloss Aligned Vietnamese Word Embedding for Polysemous and Sense-Aware Representations
by: Huynh, Khang T., et al.
Published: (2025)

SignBart -- New approach with the skeleton sequence for Isolated Sign language Recognition
by: Nguyen, Tinh, et al.
Published: (2025)

The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation
by: Nguyen, Thanh-Danh, et al.
Published: (2023)

HA-RDet: Hybrid Anchor Rotation Detector for Oriented Object Detection
by: Nguyen, Phuc D. A.
Published: (2024)

Fusionista2.0: Efficiency Retrieval System for Large-Scale Datasets
by: Le, Huy M., et al.
Published: (2025)

Non-Cooperative Backdoor Attacks in Federated Learning: A New Threat Landscape
by: Nguyen, Tuan, et al.
Published: (2024)

VLegal-Bench: Cognitively Grounded Benchmark for Vietnamese Legal Reasoning of Large Language Models
by: Dong, Nguyen Tien, et al.
Published: (2025)

Link prediction Graph Neural Networks for structure recognition of Handwritten Mathematical Expressions
by: Nguyen, Cuong Tuan, et al.
Published: (2025)

ViSpeechFormer: A Phonemic Approach for Vietnamese Automatic Speech Recognition
by: Nguyen, Khoa Anh, et al.
Published: (2026)

Span Modeling for Idiomaticity and Figurative Language Detection with Span Contrastive Loss
by: Matheny, Blake, et al.
Published: (2026)

Detecting Omissions in Geographic Maps through Computer Vision
by: Nguyen, Phuc D. A., et al.
Published: (2024)

Do Multimodal Large Language Models Understand Welding?
by: Khvatskii, Grigorii, et al.
Published: (2025)

Accelerating Conditional Prompt Learning via Masked Image Modeling for Vision-Language Models
by: Bui, Phuoc-Nguyen, et al.
Published: (2025)

CutPaste&Find: Efficient Multimodal Hallucination Detector with Visual-aid Knowledge Base
by: Nguyen, Cong-Duy, et al.
Published: (2025)

Linguistically Informed Multimodal Fusion for Vietnamese Scene-Text Image Captioning: Dataset, Graph Framework, and Phonological Attention
by: Nguyen, Nhi Ngoc-Yen, et al.
Published: (2026)

Fooling the Textual Fooler via Randomizing Latent Representations
by: Hoang, Duy C., et al.
Published: (2023)

Enhancing Entity Aware Machine Translation with Multi-task Learning
by: Trieu, An, et al.
Published: (2025)

Tracing the Evolution of Word Embedding Techniques in Natural Language Processing
by: Nguyen, Minh Anh, et al.
Published: (2026)