Copertina

Evaluating Defences against Unsafe Feedback in RLHF

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Rosati, Domenic, Edkins, Giles, Raj, Harsh, Atanasov, David, Majumdar, Subhabrata, Rajendran, Janarthanan, Rudzicz, Frank, Sajjad, Hassan
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

Limits of Convergence-Rate Control for Open-Weight Safety
di: Rosati, Domenic, et al.
Pubblicazione: (2026)

Semantic Consistency for Assuring Reliability of Large Language Models
di: Raj, Harsh, et al.
Pubblicazione: (2023)

Improving Consistency in Large Language Models through Chain of Guidance
di: Raj, Harsh, et al.
Pubblicazione: (2025)

Immunization against harmful fine-tuning attacks
di: Rosati, Domenic, et al.
Pubblicazione: (2024)

Resolving Lexical Bias in Model Editing
di: Rizwan, Hammad, et al.
Pubblicazione: (2024)

RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
di: Lee, Harrison, et al.
Pubblicazione: (2023)

Consistency in Language Models: Current Landscape, Challenges, and Future Directions
di: Novikova, Jekaterina, et al.
Pubblicazione: (2025)

LLM Library Learning Fails: A LEGO-Prover Case Study
di: Berlot-Attwell, Ian, et al.
Pubblicazione: (2025)

Dependency Parsing is More Parameter-Efficient with Normalization
di: Gajo, Paolo, et al.
Pubblicazione: (2025)

Long-form evaluation of model editing
di: Rosati, Domenic, et al.
Pubblicazione: (2024)

LLMs Underperform Graph-Based Parsers on Supervised Relation Extraction for Complex Graphs
di: Gajo, Paolo, et al.
Pubblicazione: (2026)

Localized LoRA: A Structured Low-Rank Approximation for Efficient Fine-Tuning
di: Barazandeh, Babak, et al.
Pubblicazione: (2025)

Library Learning Doesn't: The Curious Case of the Single-Use "Library"
di: Berlot-Attwell, Ian, et al.
Pubblicazione: (2024)

Learning and Forgetting Unsafe Examples in Large Language Models
di: Zhao, Jiachen, et al.
Pubblicazione: (2023)

How to Evaluate Reward Models for RLHF
di: Frick, Evan, et al.
Pubblicazione: (2024)

Interpreting the Effects of Quantization on LLMs
di: Singh, Manpreet, et al.
Pubblicazione: (2025)

Quantifying the Capabilities of LLMs across Scale and Precision
di: Badshah, Sher, et al.
Pubblicazione: (2024)

Plug and Play with Prompts: A Prompt Tuning Approach for Controlling Text Generation
di: Ajwani, Rohan Deepak, et al.
Pubblicazione: (2024)

CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbacks
di: Wang, Hao, et al.
Pubblicazione: (2026)

RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs
di: Chaudhari, Shreyas, et al.
Pubblicazione: (2024)

RLHF Workflow: From Reward Modeling to Online RLHF
di: Dong, Hanze, et al.
Pubblicazione: (2024)

Failure Modes of Maximum Entropy RLHF
di: Çağatan, Ömer Veysel, et al.
Pubblicazione: (2025)

OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework
di: Hu, Jian, et al.
Pubblicazione: (2024)

Mastering Memory Tasks with World Models
di: Samsami, Mohammad Reza, et al.
Pubblicazione: (2024)

Intelligent Switching for Reset-Free RL
di: Patil, Darshan, et al.
Pubblicazione: (2024)

LLMGuard: Guarding Against Unsafe LLM Behavior
di: Goyal, Shubh, et al.
Pubblicazione: (2024)

Solving the Inverse Alignment Problem for Efficient RLHF
di: Krishna, Shambhavi, et al.
Pubblicazione: (2024)

Hierarchical Latent Structures in Data Generation Process Unify Mechanistic Phenomena across Scale
di: Rohweder, Jonas, et al.
Pubblicazione: (2026)

RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking
di: Jiang, Yifan, et al.
Pubblicazione: (2024)

Group Robust Preference Optimization in Reward-free RLHF
di: Ramesh, Shyam Sundhar, et al.
Pubblicazione: (2024)

Why Is RLHF Alignment Shallow? A Gradient Analysis
di: Young, Robin
Pubblicazione: (2026)

RLHF and IIA: Perverse Incentives
di: Xu, Wanqiao, et al.
Pubblicazione: (2023)

Reward-Robust RLHF in LLMs
di: Yan, Yuzi, et al.
Pubblicazione: (2024)

Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery
di: Yu, Xuemin, et al.
Pubblicazione: (2026)

Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs
di: Si, Wai Man, et al.
Pubblicazione: (2026)

A Long Way to Go: Investigating Length Correlations in RLHF
di: Singhal, Prasann, et al.
Pubblicazione: (2023)

Reward Model Overoptimisation in Iterated RLHF
di: Wolf, Lorenz, et al.
Pubblicazione: (2025)

Dataset Reset Policy Optimization for RLHF
di: Chang, Jonathan D., et al.
Pubblicazione: (2024)

Measuring memorization in RLHF for code completion
di: Pappu, Aneesh, et al.
Pubblicazione: (2024)