Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
The Attribution-Compression Frontier in Retrieval-Augmented Generation
Deepanshu Mody
Context compression reduces generator input in retrieval-augmented generation, but answer quality alone does not characterize citation attribution. We measure citation attribution…
cs.CL2026
Joint Optimization for Greedy Longest-match Tokenization
Adhiraj Singh, Deepanshu Mody, Ghina Al Shdaifat +4
Recent work has shown that subword vocabularies can be trained to optimize compression for a specific inference rule rather than relying on greedy heuristics such as Byte Pair Enco…