PPaperPicks

Yiwei Li

Beijing Institute of Technology, School of Computer Science, Beijing, China

21 papers at tracked venues · 16 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0003-2870-7297 ↗

Venues

ACL ×8NeurIPS ×5EMNLP ×3ICLR ×2NAACL ×2AAAI ×1

Frequent coauthors

Peiwen Yuan
DBLP profile ↗ORCID search ↗
×8
Xinglin Wang
DBLP profile ↗ORCID search ↗
×4
Jiayi Shi
DBLP profile ↗ORCID search ↗
×1
Yueqi Zhang
DBLP profile ↗ORCID search ↗
×1
Hang Yin
DBLP profile ↗ORCID search ↗
×1

Papers

  1. LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient
    ACL 2026 ·
    Peiwen Yuan
    DBLP profile ↗ORCID search ↗
  2. Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation
    ACL 2025 ·
    Peiwen Yuan
    DBLP profile ↗ORCID search ↗
  3. CogLM: Tracking Cognitive Development of Large Language Models
    NAACL 2025 ·
    Xinglin Wang
    DBLP profile ↗ORCID search ↗
  4. Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling
    NeurIPS 2025 ·
    Xinglin Wang
    DBLP profile ↗ORCID search ↗
  5. From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MarkerGen
    ACL 2025 ·
    Peiwen Yuan
    DBLP profile ↗ORCID search ↗
  6. InsBank: Evolving Instruction Subset for Ongoing Alignment
    EMNLP 2025 ·
    Jiayi Shi
    DBLP profile ↗ORCID search ↗
  7. Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning
    NAACL 2025 ·
    Xinglin Wang
    DBLP profile ↗ORCID search ↗
  8. Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules
    NeurIPS 2025 ·
    Yueqi Zhang
    DBLP profile ↗ORCID search ↗
  9. Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation
    ACL 2025 · Yiwei Li
  10. Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-Generator
    NeurIPS 2025 ·
    Peiwen Yuan
    DBLP profile ↗ORCID search ↗
  11. Speculative Decoding for Multi-Sample Inference
    EMNLP 2025 · Yiwei Li
  12. Stitch and Tell: A Structured Data Augmentation Method for Spatial Understanding
    NeurIPS 2025 ·
    Hang Yin
    DBLP profile ↗ORCID search ↗
  13. UniCBE: An Uniformity-driven Comparing Based Evaluation Framework with Unified Multi-Objective Optimization
    ICLR 2025 ·
    Peiwen Yuan
    DBLP profile ↗ORCID search ↗
  14. BatchEval: Towards Human-like Text Evaluation
    ACL 2024 ·
    Peiwen Yuan
    DBLP profile ↗ORCID search ↗
  15. Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue Generation
    ACL 2024 · Yiwei Li
  16. Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
    ICLR 2024 · Yiwei Li
  17. Focused Large Language Models are Stable Many-Shot Learners
    EMNLP 2024 ·
    Peiwen Yuan
    DBLP profile ↗ORCID search ↗
  18. Instruction Embedding: Latent Representations of Instructions Towards Task Identification
    NeurIPS 2024 · Yiwei Li
  19. Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation
    ACL 2024 ·
    Xinglin Wang
    DBLP profile ↗ORCID search ↗
  20. Poor-Supervised Evaluation for SuperLLM via Mutual Consistency
    ACL 2024 ·
    Peiwen Yuan
    DBLP profile ↗ORCID search ↗
  21. Turning Dust into Gold: Distilling Complex Reasoning Capabilities from LLMs by Leveraging Negative Data
    AAAI 2024 · Yiwei Li