← Back to all news
arXiv Computation and Language By Ke Wan, Yifan Wang, Liheng Lai, Chen Chen

MORSE: Multi-Context Ordering via Reverse Scoring for Evidence-Preserving Compression

Read the original on arXiv Computation and Language →

The paper introduces MORSE, a method that orders contexts in a way that preserves evidence during compression. By applying a reverse query‑evidence principle to both individual contexts and compressed outputs, MORSE constructs an evidence‑first anchor and guides permutation selection to avoid information preemption. Experiments on multi‑hop QA benchmarks show that MORSE consistently outperforms static reverse ordering and random search, improving evidence retention and downstream QA performance.

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 Computation and Language.

Related stories

arXiv Computation and Language
Sep 7

CacheWeaver: Cache-Aware Evidence Ordering for Efficient Grounded RAG Inference

CacheWeaver is a lightweight prompt‑layer technique that orders evidence for Retrieval‑Augmented Generation (RAG) to improve cache reuse in serving engines like vLLM. By maintaining a prefix tree of recently served evidence sequences and greedily placing the most reusable prefix first, it reduces median time‑to‑first‑token by 20‑33 % across three vLLM configurations without harming answer quality. The greedy policy achieves 97.5 % of the gain possible with oracle ordering, showing that most reusable prefix locality can be recovered with a simple scheduling layer.

By Kaizhen Tan, Rong Gu, Mingyuan Li
rag
More like this →
arXiv Computation and Language
Oct 9

MiniVer-V: Identifying Minimal Sufficient Evidence for Short Video Verification

MiniVer‑V is a new benchmark for short‑video fact‑checking that contains 195 videos, each annotated with a supported, refuted, or insufficient verdict and 5,510 multimodal evidence units (visual keyframes, speech transcripts, and web‑retrieved sources). The authors propose a two‑layer verification framework that first checks claim‑video consistency using internal evidence, then determines the factual verdict with external corroboration, and employs a sufficiency‑driven greedy search to assemble only the minimal evidence needed for a confident decision. Using Claude Sonnet 4, the method achieves a Macro‑F1 of 0.510 with an average of 4.5 evidence units—about 16 % of the full set—while matching the full‑evidence baseline and improving detection of insufficient cases.

By Leran Chen, Lingnan Kong, Zile Cai
llmsmultimodalbenchmarks
More like this →
arXiv Computation and Language
Oct 28

Coverage Under Contradiction: A Benchmark for Negation-Aware Retrieval

Coverage Under Contradiction: A Benchmark for Negation-Aware Retrieval introduces CoverageBench-Negate, a new benchmark that augments the existing CoverageBench with controlled contradictions. For each evidence nugget, a negated counterpart is created and its supporting documents are edited to support the negation while preserving context, resulting in about 63,000 nugget‑document pairs across six datasets. The benchmark includes rich construction metadata, LLM judgments, and a human audit, and baseline experiments show BM25 can distinguish original from edited evidence better than dense retrievers.

By Pasha Abrishamchian, Eugene Yang, Andrew Yates, Nazli Goharian, Ophir Frieder
llmsbenchmarks
More like this →