arXiv Machine Learning September 1, 2026 By Mohammadali Khodabandehlou, Bhaskar Krishnamachari

Compression-Aware Abstention: Teaching LLMs to Refuse When KV-Compression Masks Remove Answer Evidence

Read the original on arXiv Machine Learning →

The Flow has not summarised this story yet — read it at arXiv Machine Learning.

arXiv AI

Jul 14

Length Penalties Make Chain-of-Thought Less Monitorable

arXiv:2607. 09786v1 Announce Type: new Abstract: Length-penalized reinforcement learning can shorten chain-of-thought reasoning while hiding an influence that drives the model's answer.

By Bryce Little

reinforcement-learning benchmarks

Hugging Face Trending Papers

Sep 1

Learning Evidence Sufficiency Boundaries for Selective Answering in Grounded Multi-Hop QA

Grounded question answering systems should answer only when the supplied evidence supports the answer. In multi-hop QA, this requirement is difficult because partial evidence can make an unsupported a...

nlp fine-tuning

arXiv AI

Aug 18

KV-Rescue: Recovering Reasoning Language Model KV Eviction Loss via Stepwise Interleaving

arXiv:2608. 15797v1 Announce Type: new Abstract: KV-cache eviction caps the memory cost of long reasoning traces but is inherently lossy because the model decodes from a partial view of its history.

By Minsoo Cheong, Woosang Lim, Vincent-Daniel Yun, Sungjoo Yoo

llms benchmarks

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 AI

Jun 6

FIDES: Faithful Inference via Deep Evidence Signals for Retrieval-Memory Conflict in RAG

arXiv:2606. 05644v1 Announce Type: new Abstract: When retrieved evidence contradicts parametric memory, language models frequently ignore context and default to memorized priors -- a failure that undermines the core purpose of retrieval augmentation.

By Zhe Yu, Wenpeng Xing, Tiancheng Zhao, Mohan Li, Changting Lin, Meng Han

llms rag benchmarks safety

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

One email a morning, machine-written

Related stories

Length Penalties Make Chain-of-Thought Less Monitorable

Learning Evidence Sufficiency Boundaries for Selective Answering in Grounded Multi-Hop QA

KV-Rescue: Recovering Reasoning Language Model KV Eviction Loss via Stepwise Interleaving

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

FIDES: Faithful Inference via Deep Evidence Signals for Retrieval-Memory Conflict in RAG

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