PaperScope
LIVE · 2026-09-25 05:40 UTC

ChunkRank: Model-Aware Text Chunking and Abstention-Aware Answer Selection for LLM Pipelines

Amit Nautiyal, Ayush Bhatt, Gaurav Nautiyal

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.29828 v1
Category
Submitted
2026-09-24

Abstract

We present ChunkRank, an open-source Python library that derives chunk boundaries from a target model's tokenizer and context window, and selects an answer among candidates produced independently per chunk. It ships a validated registry of 90 models across 15 providers and six answer-selection methods, and needs only three core dependencies. For chunking, ChunkRank avoids context-window overflow automatically from the model name, whereas character-based splitters overflow or waste the budget, and a fidelity study across 11 languages shows why token-exact budgets matter beyond English. For answer selection we report a negative result: on NaturalQuestions, TriviaQA and HotpotQA, with extractive and generative readers, no content-based ranker reliably beats taking the first non-empty answer. The reason is reader abstention on chunks that lack the answer, not answer position. A long-context baseline shows that chunking matches single-call reading on single-hop questions, so ChunkRank targets small-window and beyond-window settings. Code, registry and evaluation harness are released.

Comment: 16 pages. Code: https://github.com/AmitoVrito/chunkrank

arXiv abs page · PDF · same-day batch