arXiv Machine Learning August 6, 2026 By Zhengpei Hu, Kai Li, Dapeng Fu, Xuechao Zou, Yuanhao Tang, Yue Li, Tengfei Cao, Jianqiang Huang

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

Read the original on arXiv Machine Learning →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 7

Detecting Hallucinations in Retrieval-Augmented Generation through Grounding-Aware Sensitivity by Perturbation (GASP)

arXiv:2607. 04223v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) reduces but does not eliminate hallucination, and existing detectors return a single answer-level score that does not indicate which sentence is unsupported, or why.

By Mohamed Aly Bouke

rag nlp benchmarks safety

arXiv Machine Learning

4d ago

Relevance Is Not Sufficient Evidence: Detecting Evidence Gaps Before Generation in RAG

arXiv:2609.37469v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) grounds large language models in external sources, but retrieved passages often name the right entities without...

By Suting Chen, Peichun Hua, Yunming Xiao

llms rag benchmarks

arXiv Machine Learning

Sep 22

AdaMem: Adaptive Memory Token Allocation for Soft Compression in Retrieval-Augmented Generation

arXiv:2609.22100v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves language models with retrieved evidence, but processing many long passages is costly and can introduce...

By Artem Sakhno, Grigorii Davydenko, Omar Zoloev, Julia Belikova, Andrey Savchenko, Maksim Makarenko

llms rag efficiency benchmarks

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 AI

Jun 24

CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression

arXiv:2606. 24083v1 Announce Type: cross Abstract: "Talk short.

By Morayo Danielle Adeyemi, Ryan A. Rossi, Franck Dernoncourt

llms benchmarks

arXiv Computation and Language

Sep 7

Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG

The paper introduces DEX-Comp, a two‑stage training method for soft context compression in Retrieval‑Augmented Generation (RAG). First, a pure distillation warm‑start trains the compression model on correct responses from an uncompressed RAG. Then, hard exploration uses reinforcement learning on queries where the uncompressed RAG fails, encouraging better computation patterns for compressed representations. Experiments on five open‑domain QA benchmarks show that DEX‑Comp compresses retrieved contexts 16×, speeds inference 4×–24×, and matches or surpasses the uncompressed RAG baseline across various retrieval depths.

By Shuyu Guo, Shuo Zhang, Zhaochun Ren

llms rag reinforcement-learning efficiency benchmarks