# Context Selection for Hypothesis and Statistical Evidence Extraction from Full-Text Scientific Articles

arXiv: https://arxiv.org/abs/2603.21193 · HTML: https://mlsanity.com/paper/2603.21193/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 49 references that are in the map.
- First posted on arXiv 22 Mar 2026.

## Builds on (most cited first, 27 of 27)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Making Retrieval-Augmented Language Models Robust to Irrelevant Context](https://mlsanity.com/paper/2310.01558/) (2023)
- [Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction](https://mlsanity.com/paper/1808.09602/) (2018)
- [PaperBench: Evaluating AI's Ability to Replicate AI Research](https://mlsanity.com/paper/2504.01848/) (2025)
- [Effective Long-Context Scaling of Foundation Models](https://mlsanity.com/paper/2309.16039/) (2023)
- [The Power of Noise: Redefining Retrieval for RAG Systems](https://mlsanity.com/paper/2401.14887/) (2024)
- [Structural Scaffolds for Citation Intent Classification in Scientific Publications](https://mlsanity.com/paper/1904.01608/) (2019)
- [PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts](https://mlsanity.com/paper/1710.06071/) (2017)
- [Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG](https://mlsanity.com/paper/2410.05983/) (2024)
- [SciREX: A Challenge Dataset for Document-Level Information Extraction](https://mlsanity.com/paper/2005.00512/) (2020)
- [Growth rates of modern science: A latent piecewise growth curve approach to model publication numbers from established and new literature databases](https://mlsanity.com/paper/2012.07675/) (2020)
- [Scientific Claim Verification with VERT5ERINI](https://mlsanity.com/paper/2010.11930/) (2020)
- [The Distracting Effect: Understanding Irrelevant Passages in RAG](https://mlsanity.com/paper/2505.06914/) (2025)
- [CURIE: Evaluating LLMs On Multitask Scientific Long Context Understanding and Reasoning](https://mlsanity.com/paper/2503.13517/) (2025)
- [Claim Extraction in Biomedical Publications using Deep Discourse Model and Transfer Learning](https://mlsanity.com/paper/1907.00962/) (2019)
- [Extracting Fine-Grained Knowledge Graphs of Scientific Claims: Dataset and Transformer-Based Results](https://mlsanity.com/paper/2109.10453/) (2021)
- [SciRerankBench: Benchmarking Rerankers Towards Scientific Retrieval-Augmented Generated LLMs](https://mlsanity.com/paper/2508.08742/) (2025)
- [AcademicEval: Live Long-Context LLM Benchmark](https://mlsanity.com/paper/2510.17725/) (2025)
- [Extracting Core Claims from Scientific Articles](https://mlsanity.com/paper/1707.07678/) (2017)
- [How Does Knowledge Selection Help Retrieval Augmented Generation?](https://mlsanity.com/paper/2410.13258/) (2024)

## Abstract (arXiv)

Extracting hypotheses and their supporting statistical evidence from full-text scientific articles is central to the synthesis of empirical findings, but remains difficult due to document length and the distribution of scientific arguments across sections of the paper. The work studies a sequential full-text extraction setting, where the statement of a primary finding in an article's abstract is linked to (i) a corresponding hypothesis statement in the paper body and (ii) the statistical evidence that supports or refutes that hypothesis. This formulation induces a challenging within-document retrieval setting in which many candidate paragraphs are topically related to the finding but differ in rhetorical role, creating hard negatives for retrieval and extraction. Using a two-stage retrieve-and-extract framework, we conduct a controlled study of retrieval design choices, varying context quantity, context quality (standard Retrieval Augmented Generation, reranking, and a fine-tuned retriever paired with reranking), as well as an oracle paragraph setting to separate retrieval failures from extraction limits across four Large Language Model extractors. We find that targeted context selection consistently improves hypothesis extraction relative to full-text prompting, with gains concentrated in configurations that optimize retrieval quality and context cleanliness. In contrast, statistical evidence extraction remains substantially harder. Even with oracle paragraphs, performance remains moderate, indicating persistent extractor limitations in handling hybrid numeric-textual statements rather than retrieval failures alone.