Layer-wise Token Compression applies adaptive token pooling at middle transformer layers for cross-encoder rerankers, preserving MS MARCO ranking quality while raising QPS up to 25% on passages and 116% on documents, with added gains on listwise LLM rerankers and a regularizer effect for long inputs
Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval , pages =
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
method 1polarities
use method 1representative citing papers
Quantized reasoning models produce longer chains of thought, inflating token usage and negating per-token speedups from low-bit quantization across multiple benchmarks.
TASR provides a training-free predicate that stops iterative retrieval on repeated normalized answers plus calibrated logit margin above 0.25, retaining 94.8% of fixed-k=5 F1 at 62.6% of the calls across 32 configurations.
Full-horizon planning with on-demand replanning achieves accuracy parity with single-step planning in tool-calling agents for knowledge base and multi-hop question answering while consuming 2-3 times fewer tokens.
citing papers explorer
-
Layer-wise Token Compression for Efficient Document Reranking
Layer-wise Token Compression applies adaptive token pooling at middle transformer layers for cross-encoder rerankers, preserving MS MARCO ranking quality while raising QPS up to 25% on passages and 116% on documents, with added gains on listwise LLM rerankers and a regularizer effect for long inputs
-
Quantization Inflates Reasoning: Token Inflation as a Hidden Cost of Low-Bit Reasoning Models
Quantized reasoning models produce longer chains of thought, inflating token usage and negating per-token speedups from low-bit quantization across multiple benchmarks.
-
TASR: Training-Free Adaptive Stopping for Iterative Retrieval
TASR provides a training-free predicate that stops iterative retrieval on repeated normalized answers plus calibrated logit margin above 0.25, retaining 94.8% of fixed-k=5 F1 at 62.6% of the calls across 32 configurations.
-
Do Agents Need to Plan Step-by-Step? Rethinking Planning Horizon in Data-Centric Tool Calling
Full-horizon planning with on-demand replanning achieves accuracy parity with single-step planning in tool-calling agents for knowledge base and multi-hop question answering while consuming 2-3 times fewer tokens.