Cover Image

Can Safety Emerge from Weak Supervision? A Systematic Analysis of Small Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Saha, Punyajoy, Halder, Sudipta, Mondal, Debjyoti, Panda, Subhadarshi
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SmoGVLM: A Small, Graph-enhanced Vision-Language Model
by: Mondal, Debjyoti, et al.
Published: (2026)

KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning
by: Mondal, Debjyoti, et al.
Published: (2024)

Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models
by: Zhou, Zhanhui, et al.
Published: (2024)

Semi-Supervised Learning for Large Language Models Safety and Content Moderation
by: Dinuta, Eduard Stefan, et al.
Published: (2025)

PARAMANU-GANITA: Can Small Math Language Models Rival with Large Language Models on Mathematical Reasoning?
by: Niyogi, Mitodru, et al.
Published: (2024)

Knowledge-based Consistency Testing of Large Language Models
by: Rajan, Sai Sathiesh, et al.
Published: (2024)

Can Small-Scale Data Poisoning Exacerbate Dialect-Linked Biases in Large Language Models?
by: Abbas, Chaymaa, et al.
Published: (2025)

Deception Abilities Emerged in Large Language Models
by: Hagendorff, Thilo
Published: (2023)

Leviathan: Decoupling Input and Output Representations in Language Models
by: Batley, Reza T., et al.
Published: (2026)

Weakly Supervised Veracity Classification with LLM-Predicted Credibility Signals
by: Leite, João A., et al.
Published: (2023)

Reducing Large Language Model Bias with Emphasis on 'Restricted Industries': Automated Dataset Augmentation and Prejudice Quantification
by: Mondal, Devam, et al.
Published: (2024)

Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
by: Chen, Zixiang, et al.
Published: (2024)

When Attention Sink Emerges in Language Models: An Empirical View
by: Gu, Xiangming, et al.
Published: (2024)

Stacking Small Language Models for Generalizability
by: Liang, Laurence
Published: (2024)

All Language Models Large and Small
by: Chen, Zhixun, et al.
Published: (2024)

SteeringSafety: A Systematic Safety Evaluation Framework of Representation Steering in LLMs
by: Siu, Vincent, et al.
Published: (2025)

How Do Latent Reasoning Methods Perform Under Weak and Strong Supervision?
by: Cui, Yingqian, et al.
Published: (2026)

Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?
by: Kang, Deokhyung, et al.
Published: (2025)

Systematic Outliers in Large Language Models
by: An, Yongqi, et al.
Published: (2025)

Can Language Models Discover Scaling Laws?
by: Lin, Haowei, et al.
Published: (2025)

Can Large Language Models Reason and Plan?
by: Kambhampati, Subbarao
Published: (2024)

Language Models Can Predict Their Own Behavior
by: Ashok, Dhananjay, et al.
Published: (2025)

Kakugo: Distillation of Low-Resource Languages into Small Language Models
by: Devine, Peter, et al.
Published: (2026)

Small Language Models: Survey, Measurements, and Insights
by: Lu, Zhenyan, et al.
Published: (2024)

Towards Reasoning Ability of Small Language Models
by: Srivastava, Gaurav, et al.
Published: (2025)

Squat: Quant Small Language Models on the Edge
by: Shen, Xuan, et al.
Published: (2024)

Are Small Language Models Ready to Compete with Large Language Models for Practical Applications?
by: Sinha, Neelabh, et al.
Published: (2024)

Discovering Latent Knowledge in Language Models Without Supervision
by: Burns, Collin, et al.
Published: (2022)

Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents
by: Kim, Suji, et al.
Published: (2026)

Escaping Collapse: The Strength of Weak Data for Large Language Model Training
by: Amin, Kareem, et al.
Published: (2025)

Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision
by: Ye, Yaowen, et al.
Published: (2025)

Lightweight Safety Classification Using Pruned Language Models
by: Sawtell, Mason, et al.
Published: (2024)

Large Language Models for Cancer Communication: Evaluating Linguistic Quality, Safety, and Accessibility in Generative AI
by: Saha, Agnik, et al.
Published: (2025)

Aligning Large Language Models via Fine-grained Supervision
by: Xu, Dehong, et al.
Published: (2024)

Improving Large Language Model Safety with Contrastive Representation Learning
by: Simko, Samuel, et al.
Published: (2025)

Adversarial Reinforcement Learning for Large Language Model Agent Safety
by: Wang, Zizhao, et al.
Published: (2025)

Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing
by: Tran, Thien Q., et al.
Published: (2025)

Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models
by: Liu, Qin, et al.
Published: (2024)

Can Large Language Models Understand Intermediate Representations in Compilers?
by: Jiang, Hailong, et al.
Published: (2025)

Can Large Language Models Infer Causation from Correlation?
by: Jin, Zhijing, et al.
Published: (2023)