Skip to content
Papers.

LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet research paper by Scale AI, 2024

Scale AI · Aug 27, 2024 · Foundation models 2 years ago

Read on arXiv

What it shows

Multi-turn human jailbreaks reveal significant vulnerabilities in large language model defenses, achieving high attack success rates and exposing flaws in machine unlearning mechanisms.

Hugging Face's summary; not yet checked by hand.

More from Scale AI

All 25
PaperCitations
Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent FailuresContinual Search improves automated root-cause attribution in long agent execution traces by iteratively prompting diagnosis until unresolved evidence is found.Agents and evaluation · Sep 20262 weeks ago-
SteerDuplex: Steerable Duplex Speech Dialogue ModelsA full-duplex speech model that follows spoken instructions on tone, persona, pace and voice, with a benchmark of 390 prompts to test it.Multimodal and robotics · Sep 20262 weeks ago-
Studying Without a Syllabus: Task-Agnostic Environment PreprocessingAn agent can explore unfamiliar environments without task-specific guidance to build reusable artifacts that reduce later inference costs, though larger study budgets do not always improve results.Agents and evaluation · Sep 20262 weeks ago-
HarnessOpt-Bench: Evaluating LLMs at Harness OptimizationHarnessOpt-Bench measures how well frontier LLMs iteratively improve agent harnesses under constrained evaluation budgets, revealing substantial variation across models and tasks.Agents and evaluation · Aug 20267 weeks ago-
Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent FailuresAn interaction-centric taxonomy localizes agent failures to specific component interactions to guide targeted repairs across diverse architectures.Agents and evaluation · Jul 20268 weeks ago-
SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding SessionsSWE-Interact presents a testbed that evaluates coding agents in realistic multi-turn, user-driven software engineering scenarios, revealing significant gaps between single-turn performance and interactive task completion.Agents and evaluation · Jun 20262 months ago-
Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVRPOW3R is a policy-aware framework for reinforcement learning with rubric-based rewards that adapts criterion weights during training to improve policy optimization while preserving human-defined criteria importance.Training and scaling · May 20264 months ago-
Reward Hacking in Rubric-Based Reinforcement LearningResearch examines reward hacking in rubric-based reinforcement learning, identifying verifier failure and rubric-design limitations as key sources of divergence between training and evaluation metrics.Reasoning · May 20264 months ago-

Other foundation models papers

Topic
PaperCitations
BERT: Pre-training of Deep Bidirectional Transformers for Language UnderstandingPre-training a Transformer to fill in masked words, then fine-tuning it, beat task-specific models across language understanding tests.Google · Oct 20187 years ago121k
Language Models are Few-Shot LearnersGPT-3, a 175B-parameter model, does new tasks from a few examples in the prompt, with no fine-tuning.OpenAI · May 20206 years ago63.7k
GPT-4 Technical ReportA multimodal model that passes a simulated bar exam with a score around the top 10% of test takers.OpenAI · Mar 20233 years ago27.3k
LLaMA: Open and Efficient Foundation Language ModelsOpen models from 7B to 65B trained only on public data; the 13B model beats GPT-3 on most benchmarks.Meta · Feb 20233 years ago21.7k
The Llama 3 Herd of ModelsOpen models up to 405B parameters that match leading closed models on many tasks.Meta · Jul 20242 years ago18.9k
Qwen3 Technical ReportQwen3, a unified series of large language models, integrates thinking and non-thinking modes, reduces computational resources, and achieves state-of-the-art performance across various tasks and languages.Alibaba (Qwen) · May 2025 · Unverified1 year ago8,100
About this paper
Authors
Nathaniel Li, Ziwen Han, Ian Steneker and 6 more
arXiv
2408.15221 · PDF
Citations
Not counted yet · Semantic Scholar
Upvotes
0 · Hugging Face
Lab
Scale AI · on Companies · on Acquisitions

Changes

What changed
New paperAdded to the listSep 26, 2026today

New papers by email

Monday afternoons, only in weeks with new papers from the labs.

Double opt-in. Unsubscribe any time.