Cover Image

UnsafeChain: Enhancing Reasoning Model Safety via Hard Cases

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tomar, Raj Vardhan, Nakov, Preslav, Wang, Yuxia
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

How Does Prefix Matter in Reasoning Model Tuning?
by: Tomar, Raj Vardhan, et al.
Published: (2026)

Rethinking STS and NLI in Large Language Models
by: Wang, Yuxia, et al.
Published: (2023)

MuDRiC: Multi-Dialect Reasoning for Arabic Commonsense Validation
by: Elozeiri, Kareem, et al.
Published: (2025)

Can Machines Resonate with Humans? Evaluating the Emotional and Empathic Comprehension of LMs
by: Manzoor, Muhammad Arslan, et al.
Published: (2024)

HALF: Harm-Aware LLM Fairness Evaluation Aligned with Deployment
by: Mekky, Ali, et al.
Published: (2025)

Arabic Dataset for LLM Safeguard Evaluation
by: Ashraf, Yasser, et al.
Published: (2024)

Large Language Models are Few-Shot Training Example Generators: A Case Study in Fallacy Recognition
by: Alhindi, Tariq, et al.
Published: (2023)

ConspirED: A Dataset for Cognitive Traits of Conspiracy Theories and Large Language Model Safety
by: Bates, Luke, et al.
Published: (2025)

Instruction Tuning on Public Government and Cultural Data for Low-Resource Language: a Case Study in Kazakh
by: Laiyk, Nurkhan, et al.
Published: (2025)

A Survey of Confidence Estimation and Calibration in Large Language Models
by: Geng, Jiahui, et al.
Published: (2023)

Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models
by: Gao, Lang, et al.
Published: (2024)

DUAL-Bench: Measuring Over-Refusal and Robustness in Vision-Language Models
by: Ren, Kaixuan, et al.
Published: (2025)

OpenFactCheck: Building, Benchmarking Customized Fact-Checking Systems and Evaluating the Factuality of Claims and LLMs
by: Wang, Yuxia, et al.
Published: (2024)

Adapting Fake News Detection to the Era of Large Language Models
by: Su, Jinyan, et al.
Published: (2023)

Co-FactChecker: A Framework for Human-AI Collaborative Claim Verification Using Large Reasoning Models
by: Sahnan, Dhruv, et al.
Published: (2026)

Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs
by: Su, Jinyan, et al.
Published: (2025)

CoDet-M4: Detecting Machine-Generated Code in Multi-Lingual, Multi-Generator and Multi-Domain Settings
by: Orel, Daniil, et al.
Published: (2025)

Factuality of Large Language Models: A Survey
by: Wang, Yuxia, et al.
Published: (2024)

MemeMQA: Multimodal Question Answering for Memes via Rationale-Based Inferencing
by: Agarwal, Siddhant, et al.
Published: (2024)

Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore's Low-Resource Languages
by: Hu, Yujia, et al.
Published: (2025)

UNCERTAINTY-LINE: Length-Invariant Estimation of Uncertainty for Large Language Models
by: Vashurin, Roman, et al.
Published: (2025)

A Chinese Dataset for Evaluating the Safeguards in Large Language Models
by: Wang, Yuxia, et al.
Published: (2024)

From Chaos to Clarity: Claim Normalization to Empower Fact-Checking
by: Sundriyal, Megha, et al.
Published: (2023)

TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning
by: Lu, Xinyuan, et al.
Published: (2024)

Exploring Language Model Generalization in Low-Resource Extractive QA
by: Sengupta, Saptarshi, et al.
Published: (2024)

Multimodal Large Language Models to Support Real-World Fact-Checking
by: Geng, Jiahui, et al.
Published: (2024)

OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs
by: Iqbal, Hasan, et al.
Published: (2024)

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities
by: Geng, Jiahui, et al.
Published: (2025)

Missci: Reconstructing Fallacies in Misrepresented Science
by: Glockner, Max, et al.
Published: (2024)

Grounding Fallacies Misrepresenting Scientific Publications in Evidence
by: Glockner, Max, et al.
Published: (2024)

FMI_SU_Yotkova_Kastreva at SemEval-2026 Task 13: Lightweight Detection of LLM-Generated Code via Stylometric Signals
by: Yotkova, Elitsa, et al.
Published: (2026)

Qorgau: Evaluating LLM Safety in Kazakh-Russian Bilingual Contexts
by: Goloburda, Maiya, et al.
Published: (2025)

A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models
by: Geng, Jiahui, et al.
Published: (2025)

Adaptive Conformal Prediction for Improving Factuality of Generations by Large Language Models
by: Rubashevskii, Aleksandr, et al.
Published: (2026)

DP-Fusion: Token-Level Differentially Private Inference for Large Language Models
by: Thareja, Rushil, et al.
Published: (2025)

Loki: An Open-Source Tool for Fact Verification
by: Li, Haonan, et al.
Published: (2024)

Beyond "Not Novel Enough": Enriching Scholarly Critique with LLM-Assisted Feedback
by: Afzal, Osama Mohammed, et al.
Published: (2025)

Generating Zero-shot Abstractive Explanations for Rumour Verification
by: Bilal, Iman Munire, et al.
Published: (2024)

A Template Is All You Meme
by: Bates, Luke, et al.
Published: (2023)

On a Novel Application of Wasserstein-Procrustes for Unsupervised Cross-Lingual Learning
by: Ramírez, Guillem, et al.
Published: (2020)