CritICL Uses Weak Model Failure Patterns to Boost Inference
Yufan Wu · hf · 2026-08-29
CritICL improves LLM reasoning at inference time by leveraging structured failure patterns from smaller models as critique-based guidance, reducing generation and token costs.
Related event: CritICL Uses Small Model Failures to Boost LLM Reasoning(2 posts)→
More from Research
- IBM Proposes Spatial Matryoshka Training for Multi-Granularity Document Retrieval — _reachsumit · 2026-09-01
- Doc-REFRAG: coarse-compress then selectively expand for faster, more accurate multi-image RAG — _reachsumit · 2026-09-01
- Google Releases RSLM: Training-Free Vector Quantization for ANN Search — _reachsumit · 2026-09-01
- CHAP Framework Enables Personalized Generative Retrieval with Single-Pass Inference — _reachsumit · 2026-09-01
- Alibaba Jointly Trains Embeddings and Codebooks for E-commerce Generative Retrieval — _reachsumit · 2026-09-01
- Alibaba Proposes PAO to Prevent Embedding Collapse in RL Fine-Tuning for Retrieval — _reachsumit · 2026-09-01