Asymmetric Langevin Unlearning uses public data to suppress unlearning noise costs by O(1/n_pub²), enabling practical mass unlearning with preserved utility under distribution mismatch.
hub
Feder Cooper, Daphne Ippolito, Christopher A
18 Pith papers cite this work. Polarity classification is still indexing.
18
Pith papers citing it
hub tools
representative citing papers
A new paired-prompt protocol reveals alignment-pipeline-specific heterogeneity in how open-weight LLMs respond to evaluation versus deployment framings.
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
CAMP formalizes Cumulative PII Exposure and uses a session registry, co-occurrence graph, and CPE score to trigger retroactive masking in multi-turn LLM conversations, neutralizing re-identifiable profiles in synthetic tests while keeping utility intact.
Probe-geometry alignment erases cross-sequence memorization signatures in LLMs below chance using per-depth rank-one activation interventions with negligible impact on zero-shot capabilities.
Perplexity gaps between finetuned and reference models on random-prefill completions often reveal the original finetuning objectives across diverse model organisms.
A separable expert architecture uses base models, LoRA adapters, and deletable per-user proxies to enable privacy-preserving personalization and deterministic unlearning in LLMs.
COMPASS uses semantic clustering on multilingual embeddings to select auxiliary data for PEFT adapters, outperforming linguistic-similarity baselines on multilingual benchmarks while supporting continual adaptation.
REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
An open-source local linter verifies reference integrity and claim support in scientific manuscripts using public databases and consumer hardware, with an experimental contribution scoring extension.
Kimi K2.5 matches closed models on dual-use tasks but refuses fewer CBRNE requests and shows some sabotage and self-replication tendencies.
TRUST is a decentralized AI auditing framework that decomposes reasoning into HDAGs, maps agent interactions via the DAAN protocol to CIGs, and uses stake-weighted multi-tier consensus to achieve 72.4% accuracy while proving a Safety-Profitability Theorem that rewards honest auditors.
enclawed is a sector-neutral hardening framework for AI gateways providing signed modules, audit trails, peer attestation, and a 356-case test suite for regulated deployments.
Merlin achieves byte-exact deduplication of text at up to 8.7 GB/s using SIMD-optimized hashing, reducing LLM context sizes by 13.9-71% with no data loss.
Byte-exact deduplication reduces RAG context size by 0.16% to 80.34% across three regimes with zero measurable quality regression per multi-vendor LLM evaluation.
A modified Llama 3 model using fully homomorphic encryption achieves up to 98% text generation accuracy and 80 tokens per second at 237 ms latency on an i9 CPU.
Gemma introduces open 2B and 7B LLMs derived from Gemini technology that beat comparable open models on 11 of 18 text tasks and come with safety assessments.
Gemma 2 models achieve leading performance at their sizes by combining established Transformer modifications with knowledge distillation for the 2B and 9B variants.
citing papers explorer
-
Gemma 2: Improving Open Language Models at a Practical Size
Gemma 2 models achieve leading performance at their sizes by combining established Transformer modifications with knowledge distillation for the 2B and 9B variants.