REVIEW 29 cited by
ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection
read the original abstract
Toxic language detection systems often falsely flag text that contains minority group mentions as toxic, as those groups are often the targets of online hate. Such over-reliance on spurious correlations also causes systems to struggle with detecting implicitly toxic language. To help mitigate these issues, we create ToxiGen, a new large-scale and machine-generated dataset of 274k toxic and benign statements about 13 minority groups. We develop a demonstration-based prompting framework and an adversarial classifier-in-the-loop decoding method to generate subtly toxic and benign text with a massive pretrained language model. Controlling machine generation in this way allows ToxiGen to cover implicitly toxic text at a larger scale, and about more demographic groups, than previous resources of human-written text. We conduct a human evaluation on a challenging subset of ToxiGen and find that annotators struggle to distinguish machine-generated text from human-written language. We also find that 94.5% of toxic examples are labeled as hate speech by human annotators. Using three publicly-available datasets, we show that finetuning a toxicity classifier on our data improves its performance on human-written data substantially. We also demonstrate that ToxiGen can be used to fight machine-generated toxicity as finetuning improves the classifier significantly on our evaluation subset. Our code and data can be found at https://github.com/microsoft/ToxiGen.
Forward citations
Cited by 29 Pith papers
-
Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety
Boiling the Frog is a new stateful multi-turn benchmark for agentic safety that reports an aggregate strict attack success rate of 44.4% across nine models, with rates ranging from 20.5% to 92.9% depending on the mode...
-
Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety
Boiling the Frog is a new stateful multi-turn benchmark that finds an aggregate 44.4% strict attack success rate for incremental safety violations across nine AI models, with rates ranging from 20.5% to 92.9%.
-
Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling
DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.
-
The Safety-Aware Denoiser for Text Diffusion Models
SAD modifies the denoising process in text diffusion models to enforce safety constraints at inference time, reducing unsafe generations while preserving quality and diversity.
-
MHSafeEval: Role-Aware Interaction-Level Evaluation of Mental Health Safety in Large Language Models
MHSafeEval applies a new role-aware taxonomy to discover cumulative mental health harms in LLM counseling trajectories via adversarial multi-turn interactions, revealing failures missed by static benchmarks.
-
FlowGuard: Towards Lightweight In-Generation Safety Detection for Diffusion Models via Linear Latent Decoding
FlowGuard detects unsafe content during diffusion image generation via linear latent decoding and curriculum learning, outperforming prior methods by over 30% F1 while reducing GPU memory by 97% and projection time to...
-
Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression
KV cache compression causes task-dependent degradation in high-density reasoning due to disrupted CoT links; ShotKV mitigates this by preserving few-shot examples as indivisible semantic units through phase separation...
-
Symmetric Divergence and Normalized Similarity: A Unified Topological Framework for Representation Analysis
Introduces SRTD and SRTD-lite to symmetrize topological divergences for neural representations and NTS as a rank-correlation-based metric bounded in [-1,1] for cross-scenario benchmarking.
-
SafetyRepro: Configuration-Conditional Rank Instability on Alignment Benchmarks
Configuration choices alone flip pairwise safety verdicts on every tested alignment benchmark, isolated via a finite-envelope proposition linking disagreement rate to strict ordering reversal.
-
S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF
S2T-RLHF splits each response-level RLHF reward into sentence shares and then token shares, via bargaining and Dirichlet weighting, yielding steadier training with competitive preference alignment.
-
Leveraging RAG for Training-Free Alignment of LLMs
RAG-Pref is a training-free RAG-based alignment technique that conditions LLMs on contrastive preference samples during inference, yielding over 3.7x average improvement in agentic attack refusals when combined with o...
-
Navigating the Sea of LLM Evaluation: Investigating Bias in Toxicity Benchmarks
Toxicity benchmarks for LLMs produce inconsistent results when task type, input domain, or model changes, revealing intrinsic evaluation biases.
-
f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment
f-GRPO and f-HAL estimate f-divergences between reward-aligned and reward-unaligned response distributions and prove expected reward improvement for general LLM alignment.
-
Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety
Distilling safe refusal behavior from OpenAI o1-mini into Llama-3, Gemma-2, and Qwen3 models via response-based LoRA on multilingual jailbreak data increases jailbreak success rates on MultiJail by up to 16.6 points.
-
Red-Bandit: Test-Time Adaptation for LLM Red-Teaming via Bandit-Guided LoRA Experts
Red-Bandit adapts online to LLM failure modes by dynamically selecting among RL-trained LoRA attack-style experts via a bandit policy, reporting SOTA ASR@10 on AdvBench with lower-perplexity prompts.
-
SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
SmoothLLM mitigates jailbreaking attacks on LLMs by randomly perturbing multiple copies of a prompt at the character level and aggregating the outputs to detect adversarial inputs.
-
Textbooks Are All You Need II: phi-1.5 technical report
phi-1.5 is a 1.3B parameter model trained on synthetic textbook data that matches the reasoning performance of models five times larger on natural language, math, and basic coding tasks.
-
AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models
AGIEval shows GPT-4 exceeding average human scores on SAT Math at 95% and Chinese college entrance English at 92.5%, while revealing weaker results on complex reasoning tasks.
-
UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering
UniSteer trains a conditional flow matching model on LLM residual-stream activations to enable text-conditioned steering and classification across multiple behavioral tasks.
-
Fence: Specialized SLM Guardrails for LLM Applications
Small language models trained on GAN-style adversarial synthetic data outperform prompted large models on use-case-specific guardrails for off-topic and prompt-injection detection.
-
The Safety-Aware Denoiser for Text Diffusion Models
Safety-Aware Denoiser integrates safety guidance into the denoising steps of text diffusion models to reduce unsafe generations while maintaining quality.
-
DRAFT: Task Decoupled Latent Reasoning for Agent Safety
DRAFT decouples agent safety judgment into latent extraction and reasoning stages, raising average benchmark accuracy from 63.27% to 91.18%.
-
AgentCrypt: Advancing Privacy and (Secure) Computation in AI Agent Collaboration
AgentCrypt introduces a deterministic three-tier privacy framework for AI agent collaboration that uses masking and homomorphic encryption to protect data independently of model accuracy.
-
TrustLLM: Trustworthiness in Large Language Models
TrustLLM defines eight trustworthiness principles, creates a six-dimension benchmark, and evaluates 16 LLMs showing proprietary models generally lead but some open-source ones are close while over-calibration can hurt...
-
Distilling Safe LLM Systems via Soft Prompts for On Device Settings
Soft prompt distillation with total variation and KL divergence transfers safety behaviors from guard models to on-device LLMs and outperforms LoRA adapters, steering vectors, and direct optimization in safety-usefuln...
-
Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions
A position paper argues that post-hoc XAI explanations are unfaithful and paradoxical, proposing a shift to expert-based verification and certification of AI systems.
-
Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions
Current XAI methods for DNNs and LLMs rest on paradoxes and false assumptions that demand a paradigm shift to verification protocols, scientific foundations, context-aware design, and faithful model analysis rather th...
-
Baichuan 2: Open Large-scale Language Models
Baichuan 2 presents 7B and 13B LLMs trained on 2.6T tokens that match or exceed similar open models on MMLU, CMMLU, GSM8K, HumanEval and excel in medicine and law.
-
AERIC: Anticipatory Hidden-State Monitoring for Implicit Harmful Dialogue
AERIC uses a 387-parameter head on LLM hidden states for same-pass anticipatory detection of implicit harm, reporting AUROC gains on DiaSafety and Harmful Advice plus low-latency trigger rates on HarmBench and SocialH...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.