Copertina

NJUST-KMG at TRAC-2024 Tasks 1 and 2: Offline Harm Potential Identification

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Jingyuan, Xu, Shengdong, Yang, Yang
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

LegalLens Shared Task 2024: Legal Violation Identification in Unstructured Text
di: Hagag, Ben, et al.
Pubblicazione: (2024)

Investigating and Alleviating Harm Amplification in LLM Interactions
di: Guo, Ruohao, et al.
Pubblicazione: (2026)

MULTISCRIPT: Multimodal Script Learning for Supporting Open Domain Everyday Tasks
di: Qi, Jingyuan, et al.
Pubblicazione: (2023)

Data Contamination Report from the 2024 CONDA Shared Task
di: Sainz, Oscar, et al.
Pubblicazione: (2024)

From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards
di: Chehbouni, Khaoula, et al.
Pubblicazione: (2024)

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
di: Andriushchenko, Maksym, et al.
Pubblicazione: (2024)

Task Vector Geometry Underlies Dual Modes of Task Inference in Transformers
di: Yan, Hao, et al.
Pubblicazione: (2026)

Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model
di: Hong, Yuzhong, et al.
Pubblicazione: (2024)

Offline Reinforcement Learning for LLM Multi-Step Reasoning
di: Wang, Huaijie, et al.
Pubblicazione: (2024)

Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content
di: Stepanov, Ihor, et al.
Pubblicazione: (2026)

The Solution for The PST-KDD-2024 OAG-Challenge
di: Zhong, Shupeng, et al.
Pubblicazione: (2024)

SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests
di: Pandey, Punya Syon, et al.
Pubblicazione: (2025)

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders
di: Wang, Shun, et al.
Pubblicazione: (2025)

Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning
di: Feng, Weitao, et al.
Pubblicazione: (2025)

When 2D Tasks Meet 1D Serialization: On Serialization Friction in Structured Tasks
di: Lo, Chung-Hsiang, et al.
Pubblicazione: (2026)

Representation Noising: A Defence Mechanism Against Harmful Finetuning
di: Rosati, Domenic, et al.
Pubblicazione: (2024)

Disentangling Task Conflicts in Multi-Task LoRA via Orthogonal Gradient Projection
di: Yang, Ziyu, et al.
Pubblicazione: (2026)

Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts
di: Pang, Jing-Cheng, et al.
Pubblicazione: (2024)

OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models
di: Wu, Junda, et al.
Pubblicazione: (2024)

RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents
di: Zhu, Jialiang, et al.
Pubblicazione: (2026)

DISA: Offline Importance Sampling for Distribution-Matching LLM-RL
di: Wang, Shaobo, et al.
Pubblicazione: (2026)

NeuroLoRA: Context-Aware Neuromodulation for Parameter-Efficient Multi-Task Adaptation
di: Yang, Yuxin, et al.
Pubblicazione: (2026)

A Baseline for Self-state Identification and Classification in Mental Health Data: CLPsych 2025 Task
di: Kim, Laerdon
Pubblicazione: (2025)

Harder Tasks Need More Experts: Dynamic Routing in MoE Models
di: Huang, Quzhe, et al.
Pubblicazione: (2024)

Learning Task Representations from In-Context Learning
di: Saglam, Baturay, et al.
Pubblicazione: (2025)

HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models
di: Lee, Seanie, et al.
Pubblicazione: (2024)

Which LLMs are Difficult to Detect? A Detailed Analysis of Potential Factors Contributing to Difficulties in LLM Text Detection
di: Thorat, Shantanu, et al.
Pubblicazione: (2024)

PCL-Reasoner-V1.5: Advancing Math Reasoning with Offline Reinforcement Learning
di: Lu, Yao, et al.
Pubblicazione: (2026)

Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization
di: Mukherjee, Subhojyoti, et al.
Pubblicazione: (2025)

Offline Preference Optimization via Maximum Marginal Likelihood Estimation
di: Najafi, Saeed, et al.
Pubblicazione: (2025)

Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale datasets for Responsible LLMs
di: Mendu, Sai Krishna, et al.
Pubblicazione: (2025)

MALTO at SemEval-2024 Task 6: Leveraging Synthetic Data for LLM Hallucination Detection
di: Borra, Federico, et al.
Pubblicazione: (2024)

Frustratingly Easy Task-aware Pruning for Large Language Models
di: Tian, Yuanhe, et al.
Pubblicazione: (2025)

PIE: Performance Interval Estimation for Free-Form Generation Tasks
di: Hsu, Chi-Yang, et al.
Pubblicazione: (2025)

SIG: Speaker Identification in Literature via Prompt-Based Generation
di: Su, Zhenlin, et al.
Pubblicazione: (2023)

Offline Exploration-Aware Fine-Tuning for Long-Chain Mathematical Reasoning
di: Mu, Yongyu, et al.
Pubblicazione: (2026)

FLARE: Task-agnostic embedding model evaluation through a normalization process
di: Jiang, Jingzhou, et al.
Pubblicazione: (2026)

Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack
di: Huang, Tiansheng, et al.
Pubblicazione: (2024)

HarmPot: An Annotation Framework for Evaluating Offline Harm Potential of Social Media Text
di: Kumar, Ritesh, et al.
Pubblicazione: (2024)

LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
di: Pan, Zhuoshi, et al.
Pubblicazione: (2024)