# Improving Zero-shot Sentence Decontextualisation with Content Selection and Planning

arXiv: https://arxiv.org/abs/2509.17921 · HTML: https://mlsanity.com/paper/2509.17921/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [Extractive Summarization as Text Matching](https://mlsanity.com/paper/2004.08795/) (2020)
- [Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval](https://mlsanity.com/paper/2009.12756/) (2020)
- [AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web](https://mlsanity.com/paper/2305.13117/) (2023)
- [Fine-tune BERT for Extractive Summarization](https://mlsanity.com/paper/1903.10318/) (2019)
- [Decontextualization: Making Sentences Stand-Alone](https://mlsanity.com/paper/2102.05169/) (2021)
- [Semantic Graphs for Generating Deep Questions](https://mlsanity.com/paper/2004.12704/) (2020)
- [Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs](https://mlsanity.com/paper/2104.08400/) (2021)
- [Controllable Open-ended Question Generation with A New Question Type Ontology](https://mlsanity.com/paper/2107.00152/) (2021)
- [End-to-End Beam Retrieval for Multi-Hop Question Answering](https://mlsanity.com/paper/2308.08973/) (2023)
- [Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization](https://mlsanity.com/paper/2209.03549/) (2022)
- [SciDTB: Discourse Dependency TreeBank for Scientific Abstracts](https://mlsanity.com/paper/1806.03653/) (2018)
- [Toward Fast and Accurate Neural Discourse Segmentation](https://mlsanity.com/paper/1808.09147/) (2018)
- [A Question Answering Framework for Decontextualizing User-facing Snippets from Scientific Documents](https://mlsanity.com/paper/2305.14772/) (2023)
- [Improving Question Generation with Multi-level Content Planning](https://mlsanity.com/paper/2310.13512/) (2023)
- [Document-level Claim Extraction and Decontextualisation for Fact-Checking](https://mlsanity.com/paper/2406.03239/) (2024)
- [Controllable Decontextualization of Yes/No Question and Answers into Factual Statements](https://mlsanity.com/paper/2401.09775/) (2024)

## Abstract (arXiv)

Extracting individual sentences from a document as evidence or reasoning steps is commonly done in many NLP tasks. However, extracted sentences often lack context necessary to make them understood, e.g., coreference and background information. To this end, we propose a content selection and planning framework for zero-shot decontextualisation, which determines what content should be mentioned and in what order for a sentence to be understood out of context. Specifically, given a potentially ambiguous sentence and its context, we first segment it into basic semantically-independent units. We then identify potentially ambiguous units from the given sentence, and extract relevant units from the context based on their discourse relations. Finally, we generate a content plan to rewrite the sentence by enriching each ambiguous unit with its relevant units. Experimental results demonstrate that our approach is competitive for sentence decontextualisation, producing sentences that exhibit better semantic integrity and discourse coherence, outperforming existing methods.