News without the noise
48 results for “GSM8K” · page 2 of 3
Research · Safety & security
Answer-Only Disclosure: Private-Context LLM Assistance over Web APIs with a Leakage Ledger
A protocol called ADLER ensures the cloud sees only what the user sees, and a leakage ledger caps how much the answer reveals about private documents
GSM8K: 5.4 s modelled communication time per answer (as reported)
Australian Catholic University, Ant Group, University of Macau
Research · Evaluation & benchmarks
The Winner's Curse in LLM Self-Improvement Loops: Selection Noise, Lock-in, and Acceptance Rules
Experiments with prompt-rewriting systems show that repeatedly selecting candidates on small evaluation sets creates large gaps between reported and held-out performance.
GSM8K: 19.6 pts proxy-held-out gap (as reported)
Meta, Microsoft
Research · Efficiency & systems
DuoRate: Two-Rate Per-Expert Precision Allocation for Mixture-of-Experts Serving
DuoRate stores weights once and adapts read precision per workload, matching 4-bit accuracy at 2.9 bpw
GSM8K: 88.25% accuracy (as reported)
Huawei Technologies Ltd.
Research · Language models
On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models
Sick and colleagues report gains in language and visual reasoning using self-generated supervision rather than human-curated training questions or reference answers.
GSM8K: 80.9% accuracy (as reported)
Google, Ulm University
Research · Language models
Head Dimension Matters in Language Models for Long-Context Retrieval
Under a fixed parameter budget, models with fewer but wider heads outperform those with narrower heads on retrieval tasks.
RULER-100: 41.21% overall score (as reported)
Preferred Networks, Inc.
Research · Language models
TeachBack: Learning to Teach via Bidirectional Preference Optimization for On-Policy Self-Distillation
The TeachBack framework uses bidirectional preference optimization to encourage teachers to produce exploration-rich reasoning trajectories that students can learn from.
AMC23/AIME24/AIME25: 76.29% mean@4 (as reported)
Huazhong University of Science and Technology, Tsinghua University, Harbin Institute of Technology
Research · Evaluation & benchmarks
Predictable performance is suboptimal, and what it means for model routing
Zhang and Hardt connect prediction gains beyond a model’s own confidence to its room for improvement, then test the relationship across 16 language models.
GSM8K: 0.91 Pearson correlation between empirical suboptimality and (as reported)
Research · Efficiency & systems
ValuSpec: Plug-and-Play Candidate Valuation before Target Verification for Tree-Based Speculative Decoding
The plug-and-play module uses transfer-based supervision to align filtering with the target model without training.
GSM8K: 98.25 tokens/s throughput (as reported)
Tongji University, Nanyang Technological University, Marquette University
Research · Efficiency & systems
Is 2:4 Sparsity Still Worth It? Semi-Structured Sparsity versus Quantization in LLM Inference
Across three NVIDIA GPU generations, Qin finds that 2:4 sparsity becomes useful chiefly when no lower dense precision remains available.
GSM8K: 0.61 accuracy (as reported)
Code
Research · Language models
PV-Decoding: Progressive Verification Decoding with Decode Gating for Diffusion Language Models
PV-Decoding uses confidence thresholds and progressive verification to reduce model forward passes by 8–37% while keeping accuracy drop under 1.3%.
GSM8K: 72.9% accuracy (as reported)
Huawei Technologies, City University of Hong Kong
Research · Safety & security
Defending Against Dormant Poisoning Attacks Across Language and Multimodal Agents
It penalizes only updates that weaken safety, reducing harmful agent actions from 93.9% to 14.2%.
ASB: 7% poison activation (as reported)
UNC Chapel Hill, Kyung Hee University
Research · Language models
Next Token or Vector? Learning How Far to Decode
CADENCE predicts variable-length token spans as latent vectors, selecting longer drafts only when the current context appears sufficiently predictable.
GSM8K: 51.7% token acceptance rate (as reported)
Microsoft, University of Massachusetts Amherst
Research · Efficiency & systems
When Does Better Acceptance Pay? A Controlled Study of Speculative Decoding
A controlled study across six drafter recipes and ten benchmarks shows that aligning training and inference conditions narrows method gaps, and acceptance improvements only translate to higher throughput under specific task uncertainty and execution contexts.
GSM8K: 5.44 tokens/s speedup (as reported)
Tianjin University of Technology, Baidu Inc., Shandong University
Research · Language models
Structural Chain-of-Thought: Reasoning with Executable Computational Graphs
The Structural Chain-of-Thought method trains models to generate executable directed acyclic graphs, improving accuracy, efficiency, and faithfulness across multiple benchmarks.
GSM8k+: 0.35 accuracy (as reported)
MIPT, AIRI
Research · Language models
Prism Attention: Proposal-Refined Index Sharing Mechanism for Efficient LLMs Inference
Prism Attention replaces static cross-layer index sharing with dynamic refinement, achieving 3.4x speedup over FlashAttention at 128K tokens.
128K context: 3.36 x end-to-end speedup over FlashAttention (as reported)
Soochow University, Baidu Inc.
Research · Reinforcement learning
ReFlow: Replay-Driven Decoupling for Efficient RL Post-Training
ReFlow, a decoupled and adaptive system, achieves up to 2.06× throughput improvement over existing methods while maintaining model quality.
DAPO-Math-17K: 15.8% trainer idle ratio (as reported)
The University of Hong Kong, University of Science and Technology of China, Alibaba Group
Research · Language models
Compatibility Matters: A Framework for Token-Level Teacher Selection in On-Policy Distillation
A theoretical framework and new routing scheme yield up to 10 percentage point gains in pass@k across math, code, and reasoning tasks.
AIME 2025 × KernelBench L2: 4.37% joint fast0 pass@1 (as reported)
Princeton University, Amazon Annapurna Labs
Research · Agents
Learning from Interaction Experience via Localized Context Distillation
The authors propose a method that identifies and revises only critical spans in a student's trajectory, outperforming both off-policy and on-policy context distillation across math, code, and agent tasks.
AIME24: 61.3% accuracy (avg@12) (as reported)
Tencent, The Chinese University of Hong Kong, Zhejiang University
Research · Language models
Learning to Revise Reasoning with Segment-wise On-Policy Distillation
Replacing student reasoning segments with teacher redrafts boosts accuracy by 5.22% over baselines.
AIME25: 15.6% loop rate (as reported)
The Hong Kong University of Science and Technology (Guangzhou), University of Science and Technology of China, Alibaba Group
Research · Language models
Towards Better Exploration in Sequential Test-Time Scaling
A model-mixing intervention helps language models avoid premature convergence and find answers beyond those accessible through parallel sampling.
multiple reasoning benchmarks: 2.2 pts accuracy improvement (recursive self-aggregation) (as reported)
University of Oxford, MBZUAI, BBC R&D