paper-with-me

Papers

Parser States Already Know: Structure-Conditioned KV Persistence for Structured Generation

2026-08-28 · Linze Wu, Xinrui Chen arxiv

Structured generation underpins large language model (LLM) agents that produce JSON, SQL, and function calls, where a single wrong field can cause the downstream action to fail. Constrained decoding already tracks parser transitions to enforce formal validity, and these transitions expose how generated tokens participate in schema-critical decisions such as required fields, arguments, and structural boundaries under the active grammar. Existing KV compression largely leaves this task-relevant structural signal unused. We introduce PASK (Parser-Aware Structural KV Persistence), which turns parser-derived structure into layer-group-specific KV persistence decisions. PASK addresses the mismatch between model-side KV sensitivity and task-level structured risk by using task-error sensitivity to set minimum protection floors and attention-output distortion to allocate residual KV capacity. An offline calibration stage compiles these signals into a persistence policy, leaving only lightweight structure-conditioned lookup online. At a targe total KV budget of 0.33, PASK outperforms the strongest compressed baseline by 17.39 percentage points on average across eight BFCL non-live and Live subcategories on Qwen3-4B. In end-to-end serving, PASK achieves up to 2.2x higher throughput and 3.3x lower TPOT, while using 0.53x the peak GPU memory of Full KV.

📄 PDF Abstract BibTeX arXiv:2608.28276

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Greedy Transition-Based Dependency Parsing with Stack LSTMs

2017-06-01 · CL 2017 6 · Miguel Ballesteros, Chris Dyer, Yoav Goldberg, Noah A. Smith

We introduce a greedy transition-based parser that learns to represent parser states using recurrent neural networks. Our primary innovation that enables us to do this efficiently is a new control structure for sequentia…

Dependency ParsingTransition-Based Dependency Parsing

Transition-Based Dependency Parsing with Stack Long Short-Term Memory

2015-05-29 · IJCNLP 2015 7 · Chris Dyer, Miguel Ballesteros, Wang Ling, Austin Matthews 외

We propose a technique for learning representations of parser states in transition-based dependency parsers. Our primary innovation is a new control structure for sequence-to-sequence neural networks---the stack LSTM. Li…

Dependency ParsingTransition-Based Dependency Parsing

Arc-Standard Spinal Parsing with Stack-LSTMs

2017-09-01 · WS 2017 9 · Miguel Ballesteros, Xavier Carreras

We present a neural transition-based parser for spinal trees, a dependency representation of constituent trees. The parser uses Stack-LSTMs that compose constituent nodes with dependency-based derivations. In experiments…

ARC

Global Reasoning over Database Structures for Text-to-SQL Parsing

2019-08-29 · IJCNLP 2019 11 · Ben Bogin, Matt Gardner, Jonathan Berant

State-of-the-art semantic parsers rely on auto-regressive decoding, emitting one symbol at a time. When tested against complex databases that are unobserved at training time (zero-shot), the parser often struggles to sel…

Graph Neural NetworkSemantic ParsingSQL ParsingText to SQL+1

An Empirical Investigation of Structured Output Modeling for Graph-based Neural Dependency Parsing

2019-07-01 · ACL 2019 7 · Zhisong Zhang, Xuezhe Ma, Eduard Hovy

In this paper, we investigate the aspect of structured output modeling for the state-of-the-art graph-based neural dependency parser (Dozat and Manning, 2017). With evaluations on 14 treebanks, we empirically show that g…

Dependency ParsingSentence