Cover Image

More Documents, Same Length: Isolating the Challenge of Multiple Documents in RAG

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Levy, Shahar, Mazor, Nir, Shalmon, Lihi, Hassid, Michael, Stanovsky, Gabriel
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SEAM: A Stochastic Benchmark for Multi-Document Tasks
by: Lior, Gili, et al.
Published: (2024)

ReliableEval: A Recipe for Stochastic LLM Evaluation via Method of Moments
by: Lior, Gili, et al.
Published: (2025)

Leveraging Collection-Wide Similarities for Unsupervised Document Structure Extraction
by: Lior, Gili, et al.
Published: (2024)

ScheMatiQ: From Research Question to Structured Data through Interactive Schema Discovery
by: Levy, Shahar, et al.
Published: (2026)

Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models
by: Levy, Mosh, et al.
Published: (2024)

Transformers are Multi-State RNNs
by: Oren, Matanel, et al.
Published: (2024)

LVLM-Aware Multimodal Retrieval for RAG-Based Medical Diagnosis with General-Purpose Models
by: Mazor, Nir, et al.
Published: (2025)

Do Zombies Understand? A Choose-Your-Own-Adventure Exploration of Machine Cognition
by: Goldstein, Ariel, et al.
Published: (2024)

The State and Fate of Summarization Datasets: A Survey
by: Dahan, Noam, et al.
Published: (2024)

Comparing Humans and Models on a Similar Scale: Towards Cognitive Gender Bias Evaluation in Coreference Resolution
by: Lior, Gili, et al.
Published: (2023)

Applying Intrinsic Debiasing on Downstream Tasks: Challenges and Considerations for Machine Translation
by: Iluz, Bar, et al.
Published: (2024)

Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
by: Hassid, Michael, et al.
Published: (2025)

Less LLM, More Documents: Searching for Improved RAG
by: Ning, Jingjie, et al.
Published: (2025)

Leveraging Digitized Newspapers to Collect Summarization Data in Low-Resource Languages
by: Dahan, Noam, et al.
Published: (2025)

Beyond Memorization: Distinguishing between Reductive and Epistemic Reasoning in LLMs using Classic Logic Puzzles
by: Gabay, Adi, et al.
Published: (2026)

In-Context Learning on a Budget: A Case Study in Token Classification
by: Berger, Uri, et al.
Published: (2024)

On Pruning State-Space LLMs
by: Ghattas, Tamer, et al.
Published: (2025)

Comparing the Framing Effect in Humans and LLMs on Naturally Occurring Texts
by: Lior, Gili, et al.
Published: (2025)

LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding
by: Sourati, Zhivar, et al.
Published: (2025)

AmbigDocs: Reasoning across Documents on Different Entities under the Same Name
by: Lee, Yoonsang, et al.
Published: (2024)

PromptSuite: A Task-Agnostic Framework for Multi-Prompt Generation
by: Habba, Eliya, et al.
Published: (2025)

Investigating Length Issues in Document-level Machine Translation
by: Peng, Ziqian, et al.
Published: (2024)

EnronQA: Towards Personalized RAG over Private Documents
by: Ryan, Michael J., et al.
Published: (2025)

Diverse Word Choices, Same Reference: Annotating Lexically-Rich Cross-Document Coreference
by: Zhukova, Anastasia, et al.
Published: (2026)

Time to Talk: LLM Agents for Asynchronous Group Communication in Mafia Games
by: Eckhaus, Niv, et al.
Published: (2025)

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs
by: Itzhak, Itay, et al.
Published: (2025)

Self-Blinding and Counterfactual Self-Simulation Mitigate Biases and Sycophancy in Large Language Models
by: Christian, Brian, et al.
Published: (2026)

CHOP: Chunkwise Context-Preserving Framework for RAG on Multi Documents
by: Park, Hyunseok, et al.
Published: (2026)

LLM Ensemble for RAG: Role of Context Length in Zero-Shot Question Answering for BioASQ Challenge
by: Galat, Dima, et al.
Published: (2025)

Extending Automatic Machine Translation Evaluation to Book-Length Documents
by: Wang, Kuang-Da, et al.
Published: (2025)

Length-Aware Multi-Kernel Transformer for Long Document Classification
by: Han, Guangzeng, et al.
Published: (2024)

Extracting Polymer Nanocomposite Samples from Full-Length Documents
by: Khalighinejad, Ghazal, et al.
Published: (2024)

Less is More for Long Document Summary Evaluation by LLMs
by: Wu, Yunshu, et al.
Published: (2023)

Improving Image Captioning by Mimicking Human Reformulation Feedback at Inference-time
by: Berger, Uri, et al.
Published: (2025)

Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysis
by: Berger, Uri, et al.
Published: (2024)

Looking Beyond The Top-1: Transformers Determine Top Tokens In Order
by: Lioubashevski, Daria, et al.
Published: (2024)

Scaling Analysis of Interleaved Speech-Text Language Models
by: Maimon, Gallil, et al.
Published: (2025)

More of the Same: Persistent Representational Harms Under Increased Representation
by: Mickel, Jennifer, et al.
Published: (2025)

Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations
by: Cho, Sukmin, et al.
Published: (2024)

Quantifying Document Impact in RAG-LLMs
by: Gerami, Armin, et al.
Published: (2025)