Transformers are limited to a linearly growing number of accessible output sequences with prompt length, with exponential decay in accessible proportion beyond a critical point, even under unbounded context.
Same task, more tokens: the impact of input length on the reasoning performance of large language models
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
MuMuTestUp is a mutation-guided multi-agent framework for updating test cases in evolving software that strengthens assertions via surviving mutants, targets specific coverage gaps, and uses semantic search instead of exact matching.
LP-GEMM decomposes GEMM operations to propagate packing layouts across dependent calls, cutting redundant data movement while keeping full BLAS compatibility.
Two-stage multilingual then dataset-specific adapter fine-tuning of Gemma-3-27b with headword XML mention representation and iterative annotation achieved first place in the CRAC 2026 LLM track.
citing papers explorer
-
How Many Different Outputs Can a Transformer Generate?
Transformers are limited to a linearly growing number of accessible output sequences with prompt length, with exponential decay in accessible proportion beyond a critical point, even under unbounded context.
-
MuMuTestUp: Mutation-based Multi-Agent Test Case Update
MuMuTestUp is a mutation-guided multi-agent framework for updating test cases in evolving software that strengthens assertions via surviving mutants, targets specific coverage gaps, and uses semantic search instead of exact matching.
-
LP-GEMM: Integrating Layout Propagation into GEMM Operations
LP-GEMM decomposes GEMM operations to propagate packing layouts across dependent calls, cutting redundant data movement while keeping full BLAS compatibility.
-
Closing the Gap at CRAC 2026: Two-Stage Adaptation for LLM-Based Multilingual Coreference Resolution
Two-stage multilingual then dataset-specific adapter fine-tuning of Gemma-3-27b with headword XML mention representation and iterative annotation achieved first place in the CRAC 2026 LLM track.