Transformers Remember First, Forget Last: Dual-Process Interference in LLMs

arXiv 2603.00270•81daf13397f0f04e960a53b764107d60016d8c6fec59c484b153d23093eb994e
CoCoALLM memoryLoRAMuonRecPhotoBench benchmarkQuaSIDRAIEReFeed datasetSODASemantic IDsTARSETiny-Critic RAGagentic RAGclinical QAgenerative recommendationmultimodal embeddingsoptimizer (Muon)parameter-efficient modelsproactive interferencequery rewritingrecommender systemsretrieval-augmented generationretroactive interferencetest-time adaptationtransformers

Paper metadata

arXiv ID
2603.00270
Version
Not specified by this published record
Category
Computer Science — Information Retrieval (cs.IR)

The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.

Evidence and limitations

Source ID
arxiv_cs_ir
Record identifier
81daf13397f0f04e960a53b764107d60016d8c6fec59c484b153d23093eb994e
Enrichment time
2026-03-04T19:50:14Z
AI-assisted enrichment
Yes

This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.