Knowledge catalogue
arXiv:2610.16312v1 Announce Type: new Abstract: Explicit reasoning in large language models (LLMs) is often associated with reliability, yet it can still pose risks when a model infers harmful goals u
arXiv:2606.22953v2 Announce Type: replace Abstract: Context managers summarize or evict old messages so agents can operate beyond a finite window. This creates a reliability problem: removing history
arXiv:2609.32817v2 Announce Type: replace Abstract: Clinical Large Language Models (LLMs) achieve strong medical-exam accuracy; however, a correct answer does not guarantee that the explanation names
arXiv:2511.21752v3 Announce Type: replace-cross Abstract: Prompt injection can cause large language models (LLMs) to deviate from their intended tasks by following instructions embedded in untrusted i
arXiv:2610.19349v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) provides no reward-relative learning signal when all rollouts receive identical rewards. In long-horizon tas
arXiv:2610.14334v1 Announce Type: new Abstract: In Model Context Protocol (MCP) systems, LLMs select tools from metadata rather than from their implementations. Names and descriptions summarize what a
arXiv:2610.17528v1 Announce Type: cross Abstract: Training recipes are tuned by hand for one model, cluster and workload, and every new model, accelerator, framework version or dataset means tuning ag
arXiv:2610.17576v1 Announce Type: cross Abstract: Answering questions from radiology reports involves two decisions: whether the report contains an answer and which span gives it. A false answer prese
arXiv:2610.14277v1 Announce Type: cross Abstract: Tensor parallelism ends every layer with an all-reduce that sits between two dependent matrix multiplications, so its cost cannot be hidden and grows
arXiv:2601.06157v2 Announce Type: replace Abstract: Alignment in large language models (LLMs) is still largely static: after training, the policy is frozen. DPO, GRPO methods typically imprint one beh
arXiv:2610.17734v1 Announce Type: new Abstract: Exploration bounds learning efficiency in reinforcement learning with verifiable rewards (RLVR). Current methods explore mostly through independent samp
arXiv:2610.14550v1 Announce Type: cross Abstract: Dynamic Product Advertising (DPA) retrieval systems are a core component of modern e-commerce advertising; however, their evaluation remains challengi
arXiv:2610.15205v1 Announce Type: cross Abstract: Efficient task scheduling in heterogeneous computing systems remains a fundamental challenge in embedded and high-level synthesis flows. This paper pr
arXiv:2604.02341v2 Announce Type: replace Abstract: Mathematical reasoning in large language models has improved substantially with reinforcement learning using verifiable rewards, where final answers
arXiv:2602.21189v3 Announce Type: replace Abstract: Pass@k is a widely used performance metric for verifiable large language model tasks, including mathematical reasoning, code generation, and short-a
arXiv:2610.14043v1 Announce Type: cross Abstract: Frontier language models reliably refuse to explain how to cause physical harm. We ask whether this refusal survives when the same models control a ro
arXiv:2605.06046v2 Announce Type: replace Abstract: Auto-regressive token generation in large language models is memory-bound because it requires 'attending to' key and value tensors (KV cache) of all
arXiv:2610.15514v1 Announce Type: new Abstract: Structured pruning reduces the inference cost of large language models (LLMs) by permanently removing neurons and weight rows, yielding dense, hardware-
I wanted to find where the recognizable assistant style (em dashes, 'it's not X, it's Y', lists of three, buzzwords) lives in a model and which training stage installs it. Where it lives: in Qwen3-4B-
arXiv:2610.16152v1 Announce Type: new Abstract: Although post-training significantly enhances model performance, the use of massive undisclosed data raises concerns about benchmark contamination and c
arXiv:2610.15336v1 Announce Type: new Abstract: Influence functions enable principled data selection for large language models (e.g., identifying influential training samples for model editing, debugg
arXiv:2510.10998v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly under scrutiny for perpetuating identity-based discrimination in high-stakes domains such as hir
arXiv:2610.13335v1 Announce Type: new Abstract: Tool-using agents increasingly require a common substrate for building, training, evaluating, distilling, and maintaining agentic systems, yet existing
arXiv:2610.12837v1 Announce Type: cross Abstract: Knowledge distillation aims to train a smaller student model to mimic a larger teacher model for resource-constrained environments. However, the proce
arXiv:2610.12610v1 Announce Type: cross Abstract: Ethnic and cultural identities rarely align with political borders, a tension made sharper by migration and long-standing cross-border ties. Communiti
arXiv:2610.13755v1 Announce Type: cross Abstract: Training long-horizon language model agents requires assigning credit to intermediate decisions from sparse terminal feedback. Within a finite group o
arXiv:2610.12855v1 Announce Type: new Abstract: On-Policy Self-distillation is a self-improvement paradigm that enables large language models (LLMs) to improve their capabilities by leveraging the sam
arXiv:2610.12865v1 Announce Type: new Abstract: Existing convergence guarantees for non-log-concave sampling with stochastic gradient Langevin Monte Carlo (SG-LMC) typically assume globally Lipschitz
On October 11 2026 François Chollet announced that he has been experimenting with large‑language‑model post‑training techniques using KerasHub, JAX, and TPUs. He indicated that portions of his work ma
arXiv:2610.12360v1 Announce Type: new Abstract: When retrieved evidence contradicts an agent's prior beliefs, does it revise its answer, acknowledge uncertainty, or persist with an incorrect conclusio
arXiv:2610.11300v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for automated code generation, but generated programs can appear syntactically plausible while stil
arXiv:2610.11447v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as coding agents that edit files, run builds and tests, inspect execution results, and repair s
arXiv:2610.12106v1 Announce Type: cross Abstract: Watermarking large language models is popular for tracing chatbot and agentic outputs, yet detectors remain unreleased since exposing them could let a
arXiv:2610.11539v1 Announce Type: cross Abstract: As leading LLMs improve on capability evaluations, their limitations in producing creative outputs on design tasks remain insufficiently characterised
arXiv:2610.11373v1 Announce Type: cross Abstract: Continual learning remains challenging for large language models, which must enable models to acquire new skills and knowledge without degrading exist
arXiv:2610.11005v1 Announce Type: new Abstract: Safety-aligned language models often refuse a harmful request stated directly but answer the same request inside a role-play or narrative wrapper. We me
arXiv:2505.24282v2 Announce Type: replace Abstract: Language-driven action localization in videos requires not only semantic alignment between language query and video segment, but also prediction of
arXiv:2610.11586v1 Announce Type: new Abstract: Existing evaluation methods for healthcare LLMs primarily assess factual correctness,safety, and fluency, while providing limited insight into whether g
arXiv:2610.11573v1 Announce Type: new Abstract: The memory capabilities of Large Language Models (LLMs) have garnered increasing attention recently. Despite great success achieved, existing retrieval-
arXiv:2610.12124v1 Announce Type: new Abstract: The evolution of Large Language Model agents from single-task execution to long-term autonomous operation highlights the critical challenge of transform
arXiv:2610.12313v1 Announce Type: new Abstract: Large language model compliance systems are deployed on the assumption that a verdict depends on the regulatory rule it is given. We test this directly
arXiv:2610.11226v1 Announce Type: new Abstract: Weight-only post-training quantization (PTQ) relies heavily on reconstruction loss minimization to preserve model quality at low precision. We show that
arXiv:2610.11008v1 Announce Type: cross Abstract: Language-model agents favor their own group because they have watched their members favor each other. The group label alone does little once the decis
arXiv:2610.10085v1 Announce Type: new Abstract: Post-training tensor-network compression replaces Transformer linear layers with Tensor Train (TT) or Tree Tensor Network (TTN) operators, but standard
arXiv:2610.09219v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) treats all constraint violations equally: a 1 budget overshoot and a 1,000 overshoot induce the same training sig
arXiv:2610.09597v1 Announce Type: new Abstract: Asynchronous RL accelerates large language model post-training by decoupling rollout generation from optimization, but trains on stale trajectories. Exi
arXiv:2610.09212v1 Announce Type: new Abstract: The best two-bit weight quantizers for large language models, such as QTIP and Proteus, rotate each weight matrix by a random orthogonal transform, whic
arXiv:2609.35308v2 Announce Type: replace Abstract: Large language models treat conversation history as unverified context, so false premises injected into prior turns can be adopted as fact, a failur
arXiv:2610.09412v1 Announce Type: cross Abstract: Retrieval diversification is widely available in retrieval-augmented generation (RAG) frameworks, yet prior studies disagree on whether it improves re
arXiv:2610.08959v1 Announce Type: new Abstract: On-policy distillation post-trains large language model agents by supplying dense, step-level guidance from a teacher policy when the reinforcement-lear
arXiv:2610.10232v1 Announce Type: new Abstract: Large language models (LLMs) have already been shown to match or exceed human experts in persuasion. While their persuasive capabilities hold promise fo
arXiv:2610.06647v2 Announce Type: replace Abstract: Reinforcement learning has greatly advanced the capabilities of large language models, but its memory demands remain a barrier to broader adoption.
arXiv:2610.09063v1 Announce Type: cross Abstract: Multi-label topic assignment for user-generated content (UGC) -- including product reviews and buyer-seller conversations -- poses unique scalability
arXiv:2610.09660v1 Announce Type: new Abstract: Automatic Short Answer Scoring (ASAS) requires models that can score student responses against question-specific criteria while remaining efficient and
arXiv:2610.07457v1 Announce Type: cross Abstract: Fine-grained mixed-precision quantization promises efficient large language model inference, but local precision choices can conflict with regular GPU
arXiv:2610.07023v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable capabilities but remain vulnerable to jailbreak attacks that elicit harmful or unsafe outputs. Exi
arXiv:2610.07535v1 Announce Type: cross Abstract: Multi-agent simulations with large language models (LLMs) often operate networks of agents with a single base model. This overlooks the inter-model ef
arXiv:2610.07518v1 Announce Type: cross Abstract: Safety auditing of post-trained large language models typically relies on model behavior, requiring model execution and depending on the coverage of a
arXiv:2610.08055v1 Announce Type: new Abstract: Automatic assessment of communication quality in dyadic counseling conversations is bottlenecked by data: expert-rated corpora are small and expensive t
arXiv:2610.07817v1 Announce Type: cross Abstract: Organizations automating operational processes need more than a correct outcome: they need to predict how a process will run, know which one actually