Character-Name Concentration in LLM Fiction: Measuring Displacement and Mitigating RepetitionSpeculative naming is a fine-tuning-free method that cuts character-name repetition in LLM fiction. It adapts draft-verify-reject from speculative decoding to names, using verbalized sampling and a SlopTracker that combines a per-model fingerprint with a runtime counter. Across 20 LLMs and 44,782 stories in four languages, it cut Slop Ratio by 95% and mean collision probability from 7.3% to 0.4%. Static banlists only displaced the concentration to emergent names.
arxiv.orgpaperAdded 3 Nov 2026, published 31 Oct 2026π§ AI- Context-Shielded Backdoor Attack against Large Vision-Language Models
StripWake is a projector-only backdoor attack on large vision-language models. It stays dormant under full-token inference and activates when visual-token compression prunes the context around a trigger (context stripping). On LLaVA-1.5-7B across nine unseen compressors, it reaches 0.4% full-token attack success rate and 94.0%-99.7% compressed ASR on five primary compressors, with no CIDEr loss. Training aligns early visual attention with a frozen benign teacher.
arxiv.orgpaperAdded 3 Nov 2026, published 31 Oct 2026π‘οΈ Security - Vision-Language Models Are Joint Denoisers in Robotic Action Generation
JADE (Joint Action DEnoiser) is a diffusion-based vision-language-action architecture in which the VLM reads the current noisy action latents together with images and instructions at every denoising step, and guides the action expert through gated cross-attention. The VLM is also trained to recover clean action latents, and an adaptive step-size schedule cuts sampling steps. On RoboDojo it averages 12.67% success, the highest among Ο0.5-based methods, and it adds 20.8 points over Ο0.5 on four real bimanual tasks.
arxiv.orgpaperAdded 3 Nov 2026, published 31 Oct 2026π§ AI - TRIAGE: Reliability- and Load-Conditioned Escalation for Two-Tier LLM Serving with a Semantic Evidence Judge
TRIAGE is a two-tier LLM serving scheme that escalates requests from a small model to a large one based on a post-generation reliability state and a load-dependent GPU price. On one A40 serving Qwen2.5-7B and 32B (AWQ) under vLLM, escalation cost rose 21.9x from 1 to 10 requests/s. A pre-registered claim that the reliability state detects corrupted evidence (AUROC 0.70 or higher) failed at 0.571. A semantic evidence judge raised detection to 0.846. The 7B to 32B pair showed only a +2.88 pp held-out gap, so the allocator declined to escalate.
arxiv.orgpaperAdded 3 Nov 2026, published 31 Oct 2026π§ AI - CivicBench: A Benchmark and Memory Framework for Web-Based Civic Data Analytics
CivicBench is a 400-task benchmark over four cities and two years that freezes civic Web data (service requests, boundaries, weather, demographics) into reproducible bundles. Executable contracts score computation, source linkage, coverage, scope, qualified answers and refusal. The paper also proposes Task-State Memory (TSM), which compiles tool observations into typed assertions and reconciles records only within compatible scopes. Eight of nine model pairs show positive mean-score gains with bootstrap intervals excluding zero.
arxiv.orgpaperAdded 3 Nov 2026, published 31 Oct 2026π§ AI - Constraint Dependency Graph Retrieval for Compliance Detection on Long SKILL Documents
SkillCDG is a compliance detection framework that turns each long SKILL document (an enterprise SOP followed by LLM agents) into a constraint dependency graph. Atomic rules are nodes tied to source text spans, and mandatory prerequisites are the only edges. Policy-generated keywords seed rules, and their dependency closure fills the small auditor's context budget. Retrieval is trained with GRPO and selective on-policy distillation. It beats full-document and retrieval baselines on three enterprise datasets and two public benchmarks.
arxiv.orgpaperAdded 3 Nov 2026, published 31 Oct 2026π§ AI - Labadain-MedQA: A Tetun Medical QA Dataset for Fine-Tuning and Evaluating Large Language Models
Labadain-MedQA is a Tetun medical question-answering dataset of 39,077 pairs, made by translating MedAlpaca's Medical Flashcards and WikiDoc Patient Information collections with Gemini 2.5 Flash. Two native-speaking healthcare professionals rated human translations higher than LLM ones (4.43 vs 4.02 out of 5). QLoRA fine-tuning of Gemma 4 12B raised mean accuracy about 10.8% on 325 Tetun-translated USMLE questions.
arxiv.orgpaperAdded 3 Nov 2026, published 31 Oct 2026π§ AI - ShiftRAG: Bypassing the Textual Bottleneck via Decoupled Learning and Continuous Soft Tokens
ShiftRAG is a decoupled retrieval-augmented generation framework that uses one LLM backbone but separates discriminative retrieval learning from autoregressive generation. It projects retrieval alignments into continuous soft tokens so the generator receives retriever-side signals, and adds a soft orthogonality objective against rank collapse in decoder-only models. The abstract reports gains in retrieval and question answering over state-of-the-art baselines, without numbers.
arxiv.orgpaperAdded 3 Nov 2026, published 31 Oct 2026π§ AI - AgentCap: Capability-Based Runtime Authorization for Secure LLM Agent Execution
AgentCap is a runtime authorization layer for LLM agents from Virginia Tech (Suresh and Gao), posted to arXiv on 31 October 2026. The model proposes MCP tool calls, and a policy engine issues Ed25519-signed capability tokens only after checks on provenance, intent, trust and prerequisites. It reports 0% attack success with GPT-5.4 on AgentDojo and InjecAgent, but only on scenarios the authors built.
arxiv.orgpaperAdded 3 Nov 2026, published 31 Oct 2026π§ AI - The Long Con on the Web: Earn-then-Exploit Fraud Attacks against Coding Agents
EtE (Earn-then-Exploit) is a web fraud attack framework against coding agents: a malicious site first gives several rounds of verifiable help to build trust, then issues task-related instructions that cross operational boundaries. Across 56 environments and three agents, average attack success was 71.4% (85.7% on Codex with GPT-5.5), beating injection baselines. The proposed defense, action-authorization separation (AAS), cut success to 0% with 100% task completion.
arxiv.orgpaperAdded 3 Nov 2026, published 31 Oct 2026π‘οΈ Security - Saidzoda-Tajik-E5-Large: Fine-Tuning a 560M Embedder for Tajik Retrieval
Saidzoda-Tajik-E5-Large is a Tajik text embedder fine-tuned from multilingual-e5-large-instruct (560M parameters) on 235,140 synthetic question and passage pairs, with hard negatives and English and Russian pairs mixed in. Top-10 retrieval on unseen laws rises from 80.2% to 93.6%, and on tax documents from 82.6% to 94.5%. The Belebele gain (92.2% to 95.2%) is not confirmed. bfloat16 training broke the model.
arxiv.orgpaperAdded 3 Nov 2026, published 31 Oct 2026π§ AI - From Lookups to Lessons: Turning Retrieved Knowledge into Parametric Memory
ResMem is a method that distills retrieved knowledge into a parametric memory. The LLM reads retrieved text offline to produce teacher targets, and a memory sharing the same backbone learns an additive logit residual through self-distillation. On a Wikipedia subset it cuts teacher-construction storage by 94.7% versus a kNN pipeline. Across five QA datasets, mean token F1 rises from 32.83% to 34.48%, and it breaks 21% fewer correct answers than a kNN-trained memory.
arxiv.orgpaperAdded 3 Nov 2026, published 30 Oct 2026π§ AI - Randomized Caches in Hardware: Challenges and Trade-offs
Paper implementing four randomized last-level cache designs (CEASER-S, ScatterCache, SassCache, MIRAGE) in a multi-core out-of-order RISC-V SoC on FPGA, evaluated with SPEC CPU 2017 and GAPBS. Pipelining the index derivation function alone is insufficient: three variants lose up to 35% frequency until critical paths are redesigned, leaving them within 10% of baseline. IPC falls up to 5% (SPEC) and 11% (GAPBS); FPGA LUTs rise 10-35%, ASIC area 1-14%.
arxiv.orgpaperAdded 3 Nov 2026, published 30 Oct 2026π‘οΈ Security - ProLand: A New Infeasible Manifold Optimization Method for LoRA Fine-Tuning
ProLand (Product-space Landing) is a retraction-free optimizer for LoRA fine-tuning that keeps the basis factor near the Stiefel manifold. It coordinates factor updates with Muon-style spectral directions, designing updates in the space of the weight increment so objective optimization and orthogonality restoration stay separate. It reports the highest average score among compared methods across 11 tasks on DeBERTa-v3-base, Qwen2.5-3B, Llama-3.2-3B and Moonlight-16B-A3B at several ranks.
arxiv.orgpaperAdded 3 Nov 2026, published 30 Oct 2026π§ AI - SecPO: Principled Adversarial Training for Prompt Injection Security
SecPO is a prompt injection defense that combines a new preference-optimization loss with adversarial training. It replaces the insecure DPO reference model with an approximated injection-invariant oracle, and trains on strong injections synthesized at best@240. Against Meta-SecAlign, AT cuts attack success rates 1.5-14.5x, and on Qwen3.6-27B AgentDojo ASR@800 falls to 8.8% from 78.8%, with no noticeable utility loss across nine benchmarks. Code, training data and model are released.
arxiv.orgpaperAdded 3 Nov 2026, published 30 Oct 2026π‘οΈ Security - SecPO: Principled Adversarial Training for Prompt Injection Security
SecPO is a DPO-variant loss from UC Berkeley for training LLMs against indirect prompt injection. It replaces the undefended-model reference on injected input with its output on the clean input, a one-line change, and pairs with a PAIR-based adversarial training pipeline. On Qwen3.6-27B, AgentDojo ASR@800 is 8.8% against 78.8% for Meta-SecAlign, with utility unchanged across nine benchmarks. Code, training set and weights are released.
arxiv.orgpaperAdded 3 Nov 2026, published 30 Oct 2026π§ AI - How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces
PrivacyTrace is a benchmark from the Shanghai AI Laboratory (AgentDoG Team, October 2026) that tests how much a passive observer can infer about a user from MCP tool-call traces alone. It has 1,000 synthetic profiles, 4,000 trajectories and 67,950 calls across 25 MCP servers. Four LLM attackers reached 26.25% attribute accuracy against a 17.97% prior baseline, and tool arguments leaked most.
arxiv.orgpaperAdded 3 Nov 2026, published 30 Oct 2026π§ AI - Locality-Controlled Out-of-Distribution Guidance for Robust Regulatory DNA Sequence Design
LOCOGEN is a sampling-time guidance method for diffusion models that design regulatory DNA sequences. It learns an invariant motif mask through sequence-level invariance learning, protects motif positions, and applies out-of-distribution damping only to background positions, with no retraining of the frozen backbone. On HepG2, K562 and SK-N-SH it reaches a region of the property, novelty and plausibility space that no baseline reached. Code is released.
arxiv.orgpaperAdded 3 Nov 2026, published 30 Oct 2026π§ AI 
WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent TrainingWorkFactory is a framework that builds coherent, executable professional tasks for training working agents. It plans an information support graph from professional intents, then uses probe executions to find and repair missing or inconsistent task information. The authors built 112,686 tasks across 612 occupations and fine-tuned Qwen models at 4B, 27B and 35B-A3B (WorkPilot). WorkPilot-35B-A3B rose from 879 to 1565 Elo on GDPval-AA v2.1.
huggingface.copaperAdded 30 Oct 2026π§ AI- RADIOlogy: A Single-Pass Approach to Training-Free Zero-Shot Anomaly Detection
RADIOlogy is a training-free, single-pass zero-shot anomaly detection method that uses multi-head attention pooling in vision-language models. It scores anomalies by contrasting average similarity between vision features and sets of normal and abnormal prompts, with no windowed execution. RADIO agglomerative features drive a dense refinement pipeline for pixel-level segmentation, and the method is applied to medical images.
arxiv.orgpaperAdded 31 Oct 2026, published 29 Oct 2026π§ AI - VeriCUA: Verification as Agentic Exploration for Computer-Using Agents
VeriCUA is a platform-agnostic framework that verifies task completion by computer-using agents through agentic exploration. The verifier inspects context to build a task rubric, then picks GUI or code checks for unresolved requirements and combines findings under explicit evidence rules. It works online and offline across desktop, mobile and web, and agrees better with reference labels than the baselines, with the largest offline gains on hard cases.
arxiv.orgpaperAdded 31 Oct 2026, published 29 Oct 2026π§ AI - Multi-View MoE: Letting Every Router Shape Expert Computation
Multi-View MoE is a sparse mixture-of-experts design that uses several independently initialized routers to select experts, then reuses their relative scores to mix learned latent views into each selected expert's input. Each expert still runs one forward pass, so active-expert count, FLOPs and all-to-all volume are unchanged. On a 24-layer 10B-A1B model trained on 708B tokens, it gains 1.18 points on a nine-task mean; Multi-Router alone gains 0.6.
arxiv.orgpaperAdded 31 Oct 2026, published 29 Oct 2026π§ AI - On the Fundamental Limits of Prefill-Based Decoding Length Prediction
This paper derives bounds on predicting an LLM's decode length from prefill-phase hidden states, a primitive for inference scheduling. It models decoding as a stopped stochastic process, giving per-prompt normality and an affine variance law Ο=Ξ±ΞΌ+b. Predictors (MLP, EGTP, FiLM, soft-label, Mixture-of-Experts) converge near the bound, so system error dominates model error. It proposes fixing model, data and sampling in benchmarks and reporting relative-error metrics.
arxiv.orgpaperAdded 31 Oct 2026, published 29 Oct 2026π§ AI - Efficient Scalable Oversight via Rewinding
Rewindable interactive proofs (RIPs) are a new model of relativizing interactive proofs for scalable oversight, in which a weak verifier can rewind an AI prover to an earlier saved state. The paper builds an RIP for computations robust to changes in a small fraction of oracle answers. The honest prover runs in linear time, the verifier runs in nearly linear time in the input length after one-time preprocessing, and no cryptography is used. A preliminary MNIST experiment shows an RIP can be faster than a deployed proof system.
arxiv.orgpaperAdded 31 Oct 2026, published 29 Oct 2026π§ AI - Glance: The Generator Is Its Own Reranker
Glance is a RAG method in which the generator also reranks. It adds a lightweight decision adapter and pointer head that score candidate passages from one shared prefill, so a single resident 9B backbone does generation and reranking. After 39 minutes of MS MARCO fine-tuning it reaches nDCG@10 of 0.741 on SciFact and 0.345 on NFCorpus, against 0.721 and 0.326 for bge-reranker-v2-m3. On 300 HotpotQA questions it improves answer F1 by 0.045 over cross-encoder-selected context. Evaluation covers two retrieval datasets, one QA dataset and one backbone family.
arxiv.orgpaperAdded 31 Oct 2026, published 29 Oct 2026π§ AI - Understanding and Mitigating Role Spoofing in LLMs
Understanding and Mitigating Role Spoofing in LLMs is an arXiv paper (October 2026) on role spoofing, a prompt injection where malicious tool output impersonates the user. It shows models track "who said what" using both content cues (semantics, style) and structure cues (control tokens, formatting). Attacks combining fake structure and content succeed often, adversarial training stops only content-based attacks, and linear probes trained to predict conversation roles detect spoofing across settings.
arxiv.orgpaperAdded 31 Oct 2026, published 29 Oct 2026π‘οΈ Security - Agentic LLM reasoning in pediatric diabetes outcome prediction from multimodal medical records
CEDAR (Clinical Evidence-Driven Agent for Risk-prediction) is an evidence-citing, self-auditing LLM pipeline for predicting pediatric diabetes outcomes at 24 months from 18 months of records. On 2,489 youth with type 2 diabetes and 4,018 with type 1, pooled AUROC was 0.815 versus 0.656 to 0.700 for trained ML in T2D, and 0.756 versus 0.603 to 0.631 in T1D. Only 4 of 70,246 cited values mismatched the chart. Two pediatric endocrinologists matched its predictions in about nine of ten cases.
arxiv.orgpaperAdded 31 Oct 2026, published 29 Oct 2026π§ AI - A Unified Hessian-Guided Framework for Post-Training Quantization
This preprint proposes a unified post-training quantization framework for large language models. It derives a Hessian-guided approximation of the output change caused by joint weight and activation quantization, using a tractable Fisher approximation. Quantization ranges, linear transformations and weight rounding are optimized together under one output-sensitivity objective. The authors report gains over state-of-the-art transformation and rounding methods in channel-wise and block-wise settings.
arxiv.orgpaperAdded 31 Oct 2026, published 29 Oct 2026π§ AI - Decompose, Estimate, Select: Coverage-Aware Context Construction for Long-Form RAG
Decompose, Estimate, Select is a coverage-aware retrieval pipeline for long-form RAG. It splits a query into subquestions, ranks candidates with a coverage-trained bi-encoder, predicts a document-by-subquestion coverage matrix with a cross-encoder, and picks documents by greedy maximum-marginal coverage. On TREC RAG 2024, Ξ±-nDCG@10 rises from 0.625 to 0.702 (gold-nugget bound 0.718). A grounded self-feedback loop raises V_strict by 0.086 over two passes.
arxiv.orgpaperAdded 31 Oct 2026, published 29 Oct 2026π§ AI - Quasi-polynomial time algorithms for block basis reduction of linear codes
Kolesnikov and Novoselov give block basis reduction (BKZ) algorithms for linear codes that need polynomial or quasi-polynomial numbers of calls to a minimum weight codeword oracle at fixed block size. The earlier Ghentiyala and Stephens-Davidowitz bounds are exponential. The paper adds a truncated BKZ and a DeepBKZ variant, with an implementation for block sizes 2 to 24 and approximation-factor estimates on random codes.
eprint.iacr.orgpaperAdded 31 Oct 2026, published 29 Oct 2026π‘οΈ Security
Showing 30 of 705
Show more