arXiv Computation and Language

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

ChunkRank is an open‑source Python library that automatically determines chunk boundaries based on a target model’s tokenizer and context window, and then selects an answer from independently produced chunk candidates. It includes a registry of 90 models from 15 providers and six answer‑selection methods, and requires only three core dependencies. Experiments show that token‑exact budgeting is important across 11 languages, and that for several datasets no content‑based ranker outperforms simply taking the first non‑empty answer due to reader abstention on chunks lacking the answer.

arXiv AI

Aug 19

Intent-Driven Dynamic Chunking: Segmenting Documents to Reflect Predicted Information Needs

Intent-Driven Dynamic Chunking (IDC) segments documents by predicting user queries with a Large Language Model and then applying dynamic programming to find optimal chunk boundaries. This method outperforms traditional fixed-length or coherence-based segmentation on five out of six question-answering datasets, improving top-1 retrieval accuracy by 5% to 67% and reducing the number of chunks by 40–60% while maintaining 93–100% answer coverage. IDC demonstrates that aligning document structure with anticipated information needs can significantly boost retrieval performance for long and heterogeneous documents.

By Christos Koutsiaris

llms rag computer-vision

arXiv Computation and Language

Sep 14

EAR: Entity-Aware Partitioning Approach for Retrieval-Augmented Generation Development

The paper introduces EAR, an Entity‑Aware Partitioning approach that improves retrieval‑augmented generation for multiple‑choice question answering by extracting normalized surface anchors from questions, answers, and the corpus. EAR retrieves local windows around matching anchors and can attach a larger parent passage via an extractive summary, reducing retrieved words by 37.5‑40.2% compared to fixed‑size chunks. Experiments on a cleaned MMLU‑style subset with Mistral, Gemma, and DeepSeek show modest accuracy changes, none statistically significant, highlighting EAR’s methodological contribution of compact, inspectable retrieval units.

By Cenab Batu Bora, Oylum Alatl{\i}, Sebnem Bora, Oguz Dikenelli

llms rag nlp benchmarks

arXiv Computation and Language

2d ago

Large Language Model Selection with Limited Annotations

arXiv:2605.24981v2 Announce Type: replace Abstract: Choosing a Large Language Model (LLM) for a given task requires comparing many strong candidates, yet standard evaluation relies on costly annotati...

By Yavuz Durmazkeser, Patrik Okanovic, Andreas Kirsch, Torsten Hoefler, Nezihe Merve G\"urel

llms

arXiv Machine Learning

Aug 6

Relevant but Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard Prompt Compression

arXiv:2608. 04569v1 Announce Type: cross Abstract: Hard prompt compression reduces long-context inference cost by independently scoring tokens, sentences, or chunks and retaining the highest-scoring units under a budget.

By Zhengpei Hu, Kai Li, Dapeng Fu, Xuechao Zou, Yuanhao Tang, Yue Li, Tengfei Cao, Jianqiang Huang

llms rag nlp

arXiv AI

Jun 6

Improving Answer Extraction in Context-based Question Answering Systems Using LLMs

arXiv:2606. 06197v1 Announce Type: cross Abstract: Question answering (QA) systems have achieved notable progress with the advent of large language models (LLMs).

By Hafez Abdelghaffar, Ahmed Alansary, Ali Hamdi

llms nlp fine-tuning benchmarks

arXiv AI

Aug 5

SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG

arXiv:2608. 03860v1 Announce Type: cross Abstract: We introduce SciRet, a compute-aware empirical study of retrieval-augmented generation for scientific question answering over CORD-19.

By Kaysarul Anas Apurba, Md. Hasibul Hasan, Rofiqul Alam Shehab, Asab Azad

rag nlp benchmarks

arXiv AI

23h ago

Regime Boundary Alignment for Evidence-Gated Question Answering

arXiv:2609.37491v1 Announce Type: cross Abstract: Retrieval-augmented language models are expected to answer from the retrieved evidence, but in practice they often keep answering when that evidence...

By Zeyan Li, Qirong Guo, SIyuan Qiu, Hu Xu, Chun Li, Jianfeng Xu

llms rag nlp fine-tuning safety

arXiv AI

Jul 21

BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation

arXiv:2604. 09497v2 Announce Type: replace-cross Abstract: Accurate evaluation is central to the large language model (LLM) ecosystem, guiding model selection and downstream adoption across diverse use cases.

By Hippolyte Gisserot-Boukhlef, Nicolas Boizard, Emmanuel Malherbe, C\'eline Hudelot, Pierre Colombo

llms

arXiv Computation and Language

Sep 14

Parameter-Efficient Retrievers for Polish and European Languages

The paper introduces a three‑stage training pipeline that builds compact, efficient dense retrievers without requiring ground‑truth relevance labels. Using cross‑lingual alignment, relational knowledge distillation, and contrastive fine‑tuning, the authors develop PolDense (six Polish models ranging from 17 M to 1 B parameters) and EuroDense (a 435 M‑parameter model covering nine European languages). Extensive evaluation on 41 Polish and 150 multilingual tasks shows that PolDense‑1B outperforms larger retrievers up to 9 B parameters, while EuroDense leads in task‑averaged and language‑averaged performance among models below 1 B parameters.

By S{\l}awomir Dadas, Rafa{\l} Po\'swiata, Ma{\l}gorzata Gr\k{e}bowiec, Micha{\l} Pere{\l}kiewicz

llms rag fine-tuning efficiency safety

Hugging Face Trending Papers

1d ago

Locating Answer-Correctness Signals in Frozen Large Language Models

Language models expose internal signals that predict whether an answer is correct, readable from a single forward pass of a frozen model without additional generations. Yet existing probes often commi...

llms rag

arXiv AI

Aug 5

Lightweight Chunk Selection for Mobile Retrieval-Augmented Generation

arXiv:2608. 03148v1 Announce Type: cross Abstract: RAG improves the factual grounding of LLM by incorporating external knowledge, but deploying RAG on mobile and edge devices remains challenging because retrieved context increases computation and memory.

By Sicong Chang, Yidan Shen, Wen Yu, Jiefu Chen, Xin Fu, Renjie Hu

llms rag safety

arXiv AI

2d ago

Highlight-Then-Summarize: Learning to Compress Evidence for Long-Context Understanding

The paper introduces Highlight-Then-Summarize (H2S), a two-step approach that first highlights question-relevant evidence in long documents and then condenses it into a compact, question-conditioned summary before generating an answer. The authors built the H2S-Dataset with 6,647 examples spanning 11 benchmark families, and developed H2S-RL to reward evidence selection and summary construction. Evaluated on the H2S-Bench suite, the H2S-14B model outperforms larger open-source models, achieving the highest overall score and maintaining strong performance even with a reduced output budget.

By Zhaoyuan Xia (Peking University, Baidu Inc), Qinghongbing Xie (Tsinghua University), Yung Xiang Hue (Tsinghua University), Jianguang Jiang (Baidu Inc), Gaofeng Lu (Baidu Inc), Zhenyu Jiao (Baidu Inc), Xing Yuan (Baidu Inc), Dai Dai (Baidu Inc), Tong Mo (Peking University), Long Zeng (Tsinghua University)

llms reinforcement-learning benchmarks

Related stories