{"total":18,"items":[{"citing_arxiv_id":"2605.11170","ref_index":211,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data","primary_cat":"cs.LG","submitted_at":"2026-05-11T19:28:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09990","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference","primary_cat":"cs.CL","submitted_at":"2026-05-11T05:06:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09611","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Byte-Exact Deduplication in Retrieval-Augmented Generation: A Three-Regime Empirical Analysis Across Public Benchmarks","primary_cat":"cs.CL","submitted_at":"2026-05-10T15:48:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06327","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity","primary_cat":"cs.CL","submitted_at":"2026-05-07T14:23:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A new paired-prompt protocol reveals alignment-pipeline-specific heterogeneity in how open-weight LLMs respond to evaluation versus deployment framings.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.01699","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance","primary_cat":"cs.LG","submitted_at":"2026-05-03T03:44:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00994","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Model Organisms Are Leaky: Perplexity Differencing Often Reveals Finetuning Objectives","primary_cat":"cs.CL","submitted_at":"2026-05-01T18:00:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Perplexity gaps between finetuned and reference models on random-prefill completions often reveal the original finetuning objectives across diverse model organisms.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.27132","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TRUST: A Framework for Decentralized AI Service v.0.1","primary_cat":"cs.AI","submitted_at":"2026-04-29T19:32:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23338","ref_index":68,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework","primary_cat":"cs.CR","submitted_at":"2026-04-25T14:57:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21571","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User Proxies","primary_cat":"cs.AI","submitted_at":"2026-04-23T11:51:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A separable expert architecture uses base models, LoRA adapters, and deletable per-user proxies to enable privacy-preserving personalization and deterministic unlearning in LLMs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.20720","ref_index":48,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling","primary_cat":"cs.LG","submitted_at":"2026-04-22T16:07:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17396","ref_index":91,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Representation-Guided Parameter-Efficient LLM Unlearning","primary_cat":"cs.CL","submitted_at":"2026-04-19T11:59:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.16838","ref_index":32,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"enclawed: A Configurable, Sector-Neutral Hardening Framework for Single-User AI Assistant Gateways","primary_cat":"cs.CR","submitted_at":"2026-04-18T05:10:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.16521","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CAMP: Cumulative Agentic Masking and Pruning for Privacy Protection in Multi-Turn LLM Conversations","primary_cat":"cs.CR","submitted_at":"2026-04-16T03:44:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.12168","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Fully Homomorphic Encryption on Llama 3 model for privacy preserving LLM inference","primary_cat":"cs.CR","submitted_at":"2026-04-14T00:54:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08501","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"sciwrite-lint: Verification Infrastructure for the Age of Science Vibe-Writing","primary_cat":"cs.DL","submitted_at":"2026-04-09T17:46:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.03121","ref_index":96,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"An Independent Safety Evaluation of Kimi K2.5","primary_cat":"cs.CR","submitted_at":"2026-04-03T15:45:35+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Kimi K2.5 matches closed models on dual-use tasks but refuses fewer CBRNE requests and shows some sabotage and self-replication tendencies.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2408.00118","ref_index":62,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Gemma 2: Improving Open Language Models at a Practical Size","primary_cat":"cs.CL","submitted_at":"2024-07-31T19:13:07+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Gemma 2 models achieve leading performance at their sizes by combining established Transformer modifications with knowledge distillation for the 2B and 9B variants.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2403.08295","ref_index":59,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Gemma: Open Models Based on Gemini Research and Technology","primary_cat":"cs.CL","submitted_at":"2024-03-13T06:59:16+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":4.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}