DAPRO provides the first dynamic, theoretically guaranteed way to allocate interaction budgets across test cases for bounding time-to-event in multi-turn LLM evaluations, achieving tighter coverage than static conformal survival methods.
Baseline reference
arXiv preprint arXiv:2311.08370 , year=
Baseline reference. 50% of citing Pith papers use this work as a benchmark or comparison.
9
Pith papers citing it
Baseline
50% of classified citations
citation-role summary
dataset 3
background 2
method 1
citation-polarity summary
representative citing papers
LLMs generate adequate counterspeech for co-occurring hate and misinformation in 40% of cases, with a mixed knowledge strategy from fact-checkers and NGOs proving most effective after expert revision.
Toxicity benchmarks for LLMs produce inconsistent results when task type, input domain, or model changes, revealing intrinsic evaluation biases.
GLiGuard is a compact schema-conditioned bidirectional encoder that matches 7B-27B guard models on safety benchmarks while delivering up to 16x higher throughput and 17x lower latency.
Reasoning traces in large reasoning models expose safety failures missed by final-answer checks, and adaptive multi-principle steering reduces unsafe content in both traces and answers while preserving task performance.
SIREN identifies safety neurons via linear probing on internal LLM layers and combines them with adaptive weighting to detect harm, outperforming prior guard models with 250x fewer parameters.
Language models refuse 75.4% of requests to evade defeated rules and do so even after recognizing reasons that undermine the rule's legitimacy.
WildGuard is a new open moderation model and dataset for LLM safety that identifies harmful prompts, risky responses, and refusal rates, achieving SOTA open-source performance and sometimes exceeding GPT-4 while cutting jailbreak success from 79.8% to 2.4%.
Guardian-as-an-Advisor prepends risk labels and explanations from a guardian model to queries, improving LLM safety compliance and reducing over-refusal while adding minimal compute overhead.
citing papers explorer
-
LLM Safety From Within: Detecting Harmful Content with Internal Representations
SIREN identifies safety neurons via linear probing on internal LLM layers and combines them with adaptive weighting to detect harm, outperforming prior guard models with 250x fewer parameters.