Noisy expert imitation learning requires exponential samples for offline methods but polynomial for a variant of on-policy distillation under a noise condition.
super hub Mixed citations
Qwen Technical Report
Mixed citation behavior. Most common role is background (67%).
540
Pith papers citing it
Background
67% of classified citations
abstract
Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to humans. In this work, we introduce Qwen, the first installment of our large language model series. Qwen is a comprehensive language model series that encompasses distinct models with varying parameter counts. It includes Qwen, the base pretrained language models, and Qwen-Chat, the chat models finetuned with human alignment techniques. The base language models consistently demonstrate superior performance across a multitude of downstream tasks, and the chat models, particularly those trained using Reinforcement Learning from Human Feedback (RLHF), are highly competitive. The chat models possess advanced tool-use and planning capabilities for creating agent applications, showcasing impressive performance even when compared to bigger models on complex tasks like utilizing a code interpreter. Furthermore, we have developed coding-specialized models, Code-Qwen and Code-Qwen-Chat, as well as mathematics-focused models, Math-Qwen-Chat, which are built upon base language models. These models demonstrate significantly improved performance in comparison with open-source models, and slightly fall behind the proprietary models.
hub tools
citation-role summary
background 83
baseline 16
method 16
dataset 1
extension 1
other 1
citation-polarity summary
claims ledger
- abstract Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to humans. In this work, we introduce Qwen, the first installment of our large language model series. Qwen is a comprehensive language model series that encompasses distinct models with varying parameter counts. It includes Qwen, the base pretrained language models, and Qwen-Chat, the chat models finetuned with human alignment techniques. The base language models consistently demonstrate superior performance across a mult
authors
co-cited works
representative citing papers
SeedHijack is a blind, integrity-preserving PRNG hijacking attack that amplifies LLM watermark z-scores up to 2.42x while evading all tested content-side statistical detectors across three schemes and models.
LongAct benchmark evaluates long-horizon household task execution from free-form instructions; HoloMind agent raises performance but top VLMs still reach only 59% goal completion and 16% full-task success.
The upper-tail accumulation scale derived from the gap-counting function N_n sets the critical inverse temperature for softmax attention concentration, unifying prior conflicting laws as special cases of different N_n.
IRIS-14B is the first LLM trained explicitly for GIMPLE-to-LLVM IR translation and outperforms much larger models by up to 44 percentage points on real-world C code.
A classifier trained only on transformer fine-tuning data detects an invariant memorization signature that transfers to Mamba, RWKV-4, and RecurrentGemma with AUCs of 0.963, 0.972, and 0.936.
LiveBench is a contamination-limited LLM benchmark with auto-scored challenging tasks from recent sources across math, coding, reasoning and more, where top models score below 70%.
OSWorld provides the first unified real-computer benchmark for open-ended multimodal agent tasks, exposing large performance gaps between humans and state-of-the-art LLM/VLM agents.
ALEE generates AMR-based English minimal pairs with fine-grained semantic shifts, translates them, and evaluates embedding models on 275+ languages to expose cross-lingual gaps linked to training data and tokenization.
Introduces VidPair-Halluc benchmark of 1K background-controlled adversarial video pairs and 11K QA pairs generated via PairFlow pipeline to evaluate hallucination in LVMs.
A new sensitivity-labeled test collection is released from Enron emails with crowdsourced queries, relevance judgments, and LLM extensions for evaluating sensitivity-aware search.
SAGE is a source-agnostic post-hoc correction for LLM unlearning updates that suppresses components aligned with high-energy retained activation directions while preserving the forgetting carrier.
Introduces Neighbor Leakage Rate showing high trigger leakage in VLAS backdoors at 3% poisoning, caused by broad activation regions in fine-tuning that hard-negative samples can narrow.
Earth-OneVision is a unified 2B-parameter RS-MLLM supporting six modalities and nine tasks via FGVLA, SLIS, and PCMA mechanisms plus a 34M QA-pair dataset, reporting competitive or superior benchmark results versus larger models.
APEX4 co-designs pure INT4 GEMM kernels with ρ-aware granularity adaptation to deliver up to 2.09× end-to-end speedup on GPUs with low ρ while keeping LLaMA-2-70B perplexity within 0.63 of FP16.
SurgiQ is a new 13k-question surgical benchmark showing general-purpose LLMs reach 68.1% accuracy while most biomedical models lag and smaller models stay near random baseline.
Prefix gain measured via student-model solve-rate improvement is used to train a Prefix Utility Model (PUM) that supplies stronger supervision than correctness-based process rewards for mathematical reasoning.
VLMs across families and scales show anchoring to discrete slant angles in zero-shot and prompted settings rather than human-like graded texture-based slant perception.
Affordance2Action introduces A2A-Bench, a manipulation-oriented benchmark for scene-level task-conditioned affordance grounding covering single- and multi-region correspondences, plus an annotation pipeline, and reports gaps in existing segmentation and VLM baselines.
VSTAT benchmark shows state-of-the-art MLLMs perform far below humans and only modestly above answer-prior baselines on visual state tracking, failing at visual perception despite correct textual reasoning.
A large-scale empirical study across tokenizers and diffusion backbones identifies Velocity Irreducible Variance (VIV) as one of the most stable predictors of latent diffusion generation quality.
RogueMerge is a unified attack method that jointly optimizes task vectors to succeed after merging, using stochastic min-max simulation for unknown merging settings and a Taylor-approximated DRO for prompt generalization on generative LLMs.
OctoT2I uses a no-supervision PSEL loop to discover model capability frontiers and route T2I tasks, reaching 0.96 GenEval score with 90.3% speedup over Flow-GRPO.
Moral Trolley Arena shows frontier LLMs produce composite moral preferences that are compressed rather than additive functions of calibrated component act strengths across Moral Foundations Theory.
citing papers explorer
-
When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution
LongAct benchmark evaluates long-horizon household task execution from free-form instructions; HoloMind agent raises performance but top VLMs still reach only 59% goal completion and 16% full-task success.
-
OctoT2I: A Self-Evolving Agentic Text-to-Image Router
OctoT2I uses a no-supervision PSEL loop to discover model capability frontiers and route T2I tasks, reaching 0.96 GenEval score with 90.3% speedup over Flow-GRPO.
-
Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems
AgingBench demonstrates multi-dimensional degradation in deployed AI agents through four aging mechanisms diagnosed by temporal graphs and counterfactual probes across hundreds of runs.
-
ClawForge: Generating Executable Interactive Benchmarks for Command-Line Agents
ClawForge is a generator framework that creates reproducible executable benchmarks for command-line agents under state conflict, with ClawForge-Bench showing frontier models reach at most 45.3% strict accuracy and that state inspection drives most performance gaps.
-
Can Agents Price a Reaction? Evaluating LLMs on Chemical Cost Reasoning
LLM agents reach only 50.6% accuracy on chemical cost estimation within 25% error even with tools, dropping with noise due to parsing, pack selection, and tool-use failures.
-
Multi-modal Reasoning with LLMs for Visual Semantic Arithmetic
SAri-RFT applies GRPO-based reinforcement fine-tuning to LVLMs on novel two-term and three-term visual semantic arithmetic tasks, reaching SOTA on the new IRPD dataset and Visual7W-Telling.
-
From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning
MAGEO is a multi-agent system that distills validated editing patterns into reusable optimization skills for generative engines, outperforming heuristic baselines on visibility and fidelity via a new benchmark and evaluation protocol.
-
RAG-KT: Cross-platform Explainable Knowledge Tracing with Multi-view Fusion Retrieval Generation
RAG-KT frames cross-platform knowledge tracing as context-constrained LLM inference by building unified multi-source context via Question Group abstractions and retrieving complementary reliable context for grounded predictions and interpretable diagnosis.
-
SAGE: A Service Agent Graph-guided Evaluation Benchmark
SAGE is a new multi-agent benchmark that formalizes service SOPs as dynamic dialogue graphs to measure LLM agents on logical compliance and path coverage, uncovering an execution gap and empathy resilience across 27 models in 6 scenarios.
-
How Independent are Large Language Models? A Statistical Framework for Auditing Behavioral Entanglement and Reweighting Verifier Ensembles
A new auditing framework reveals widespread behavioral entanglement among LLMs and shows that reweighting ensembles based on measured independence improves verification accuracy by up to 4.5%.
-
LatentAudit: Real-Time White-Box Faithfulness Monitoring for Retrieval-Augmented Generation with Verifiable Deployment
LatentAudit monitors RAG faithfulness in real time via Mahalanobis distance on residual-stream activations, reaching 0.942 AUROC on PubMedQA with 0.77 ms overhead and supporting Groth16 verification.
-
AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents
AgentHazard benchmark shows computer-use agents remain highly vulnerable, with attack success rates reaching 73.63% on models like Qwen3-Coder powering Claude Code.
-
Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories
DynaSteer is a dynamic representation editing framework that uses pattern clustering, Fisher-LDA, and lookahead entropy monitoring to steer LLM reasoning trajectories toward truth on MATH and coding tasks.
-
Multiagent Protocols with Aggregated Confidence Signals
Introduces protocols to aggregate transformed confidence signals from multiagent debates via soft voting or Bayesian fusion, yielding higher AUARC than single agents or standard baselines while keeping F1 stable across benchmarks.
-
Cross-LLM Consistency in Inference: Evidence from Shared Interactions
LLMs share lower-order interaction patterns for token prediction from identical prompts, with stronger consistency in advanced models, identified via interaction-based explanations.
-
Benchmark Everything Everywhere All at Once
Benchmark Agent is an autonomous agentic system that constructs benchmarks for LLMs and MLLMs via query analysis, subtask design, annotation and quality control, yielding 15 benchmarks with minimal human input.
-
From GPS Points to Travel Patterns: Flexible and Semantic Trajectory Generation with LLMs
HTP hierarchically generates travel patterns via RQ-VAE tokenization then uses SFT-tuned LLMs to produce conditioned trajectory sequences, outperforming baselines by 29.78% on two datasets.
-
Understanding and Mitigating Premature Confidence for Better LLM Reasoning
Premature confidence in LLM chains of thought predicts flawed reasoning and is mitigated by progressive confidence shaping, a label-free RL objective that yields accuracy gains on arithmetic, math, and science tasks.
-
Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems
Combines LTL formal methods with LLMs for auditing, predictive monitoring, and runtime intervention on temporally extended behavioral constraints, outperforming LLM baselines and reducing violations.
-
BEAM: Binary Expert Activation Masking for Dynamic Routing in MoE
BEAM uses binary expert activation masks trained end-to-end to achieve dynamic sparsity in MoE models, cutting FLOPs by 85% with over 98% performance retention.
-
Know When To Fold 'Em: Token-Efficient LLM Synthetic Data Generation via Multi-Stage In-Flight Rejection
MSIFR stops faulty LLM generations early via staged rule-based checks, reducing token consumption 11-78% with no accuracy loss.
-
NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation
NanoResearch introduces a tri-level co-evolving framework of skills, memory, and policy to personalize LLM-powered research automation across projects and users.
-
The Model Knows, the Decoder Finds: Future Value Guided Particle Power Sampling
APPS approximates power targets p(x)^alpha via parallel particle propagation with proposal-corrected reweighting and future-value-guided selection at block boundaries, improving accuracy-runtime trade-offs in training-free decoding.
-
Towards Faster Language Model Inference Using Mixture-of-Experts Flow Matching
Mixture-of-experts flow matching enables non-autoregressive language models to achieve autoregressive-level quality in three sampling steps, delivering up to 1000x faster inference than diffusion models.
-
Towards Knowledgeable Deep Research: Framework and Benchmark
The paper introduces the KDR task, HKA multi-agent framework, and KDR-Bench to enable LLM agents to integrate structured knowledge into deep research reports, with experiments showing outperformance over prior agents.
-
Universal Adversarial Attacks against Closed-Source MLLMs via Target-View Routed Meta Optimization
MCRMO-Attack raises universal targeted attack success rates on unseen images by 23.7% on GPT-4o and 19.9% on Gemini-2.0 over prior universal baselines through stabilized supervision and meta-optimization.
-
FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Language Models
FADE attenuates FFN outputs at critical layers in LVLMs to curb language-prior dominance and cut hallucinations, shown effective on POPE, CHAIR, and MME across three models.
-
EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigation
EvolveNav adds an agentic rule memory with UCB retrieval and a memory-guided preflection module to enable continuous improvement in zero-shot object goal navigation, reporting a 10.1% success rate gain over baselines.
-
The Hidden Power of Scaling Factor in LoRA Optimization
Alpha in LoRA outperforms learning-rate scaling, follows a square-root law with rank, and enables a minimalist LoRA-alpha method that improves performance across tasks.
-
Position: The Turing-Completeness of Autoregressive Transformers Relies Heavily on Context Management
Existing proofs of autoregressive Transformer Turing-completeness apply to scaling families of models rather than fixed systems with context management, so they do not establish Turing-completeness for real-world LLMs.
-
Reconciling Contradictory Views on the Effectiveness of SFT in LLMs: An Interaction Perspective
SFT on LLMs removes noise-like token interactions in a brief early phase before introducing overfitted ones, explaining inconsistent effectiveness across model scales.
-
DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding
DRS-GUI introduces a dynamic region search method with Focus/Shift/Scatter actions and MCTS-based planning that improves GUI grounding accuracy by 14% on ScreenSpot-Pro for both general and GUI-specific MLLMs without any training.
-
From Large Language Model Predicates to Logic Tensor Networks: Neurosymbolic Offer Validation in Regulated Procurement
A neurosymbolic pipeline extracts predicates from offer texts with an LLM and validates them via Logic Tensor Networks, delivering performance comparable to standard models plus built-in interpretability on a real corpus.
-
MolClaw: An Autonomous Agent with Hierarchical Skills for Drug Molecule Evaluation, Screening, and Optimization
MolClaw deploys a hierarchical skill architecture to reach state-of-the-art results on a new benchmark of multi-step drug discovery tasks.
-
Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations
CRAFT uses contrastive representation learning and RL on hidden states to align reasoning models for improved safety against jailbreaks, reporting 79% and 87.7% gains over base models.
-
StepPRM-RTL: Stepwise Process-Reward Guided LLM Fine-Tuning for Enhanced RTL Synthesis
StepPRM-RTL combines stepwise process-reward modeling, RAFT, and MCTS to fine-tune LLMs for RTL code, claiming over 10% gains in functional correctness on Verilog/VHDL benchmarks.
-
DuIVRS-2: An LLM-based Interactive Voice Response System for Large-scale POI Attribute Acquisition
DuIVRS-2 deploys an LLM-driven IVR pipeline that processes 0.4 million calls per day at 83.9 percent task success rate using FSM-guided augmentation, selective CoT generation, and cooperative policy iteration.
-
Towards Robust Argumentative Essay Understanding via TIDE: An Interactive Framework with Trial and Debate
TIDE integrates trial and debate mechanisms to improve criteria-based prompt optimization for argumentative essay tasks including automated scoring, component detection, and relation identification.
-
Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization
An SCM-GRPO framework grounds multi-hop reasoning in structural dependency graphs and optimizes chain length via rule-based RL, outperforming baselines on HoVer and EX-FEVER.
- Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic