# InteGround: On the Evaluation of Verification and Retrieval Planning in Integrative Grounding

arXiv: https://arxiv.org/abs/2509.16534 · HTML: https://mlsanity.com/paper/2509.16534/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 42 references that are in the map.
- First posted on arXiv 20 Sep 2025.

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

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models](https://mlsanity.com/paper/2108.08877/) (2021)
- [MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents](https://mlsanity.com/paper/2404.10774/) (2024)
- [Measuring Attribution in Natural Language Generation Models](https://mlsanity.com/paper/2112.12870/) (2021)
- [Explaining Answers with Entailment Trees](https://mlsanity.com/paper/2104.08661/) (2021)
- [WiCE: Real-World Entailment for Claims in Wikipedia](https://mlsanity.com/paper/2303.01432/) (2023)
- [Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse](https://mlsanity.com/paper/2409.11242/) (2024)
- [PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognition](https://mlsanity.com/paper/2212.10750/) (2022)
- [StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understanding](https://mlsanity.com/paper/2310.12874/) (2023)
- [Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations](https://mlsanity.com/paper/2311.04335/) (2023)
- [ECon: On the Detection and Resolution of Evidence Conflicts](https://mlsanity.com/paper/2410.04068/) (2024)
- [How Well Do Large Language Models Truly Ground?](https://mlsanity.com/paper/2311.09069/) (2023)
- [Natural Language Inference from Multiple Premises](https://mlsanity.com/paper/1710.02925/) (2017)
- [Natural Language Deduction with Incomplete Information](https://mlsanity.com/paper/2211.00614/) (2022)
- [Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic](https://mlsanity.com/paper/2402.14798/) (2024)

## Built on by (most cited first, 1 of 1)

- [Grounded Normative Rule Generation with Structured Search](https://mlsanity.com/paper/2608.22229/) (2026)

## Abstract (arXiv)

Grounding large language models (LLMs) in external knowledge sources is a promising method for faithful prediction. While existing grounding approaches work well for simple queries, many real-world information needs require synthesizing multiple pieces of evidence. We introduce "integrative grounding" -- the challenge of retrieving and verifying multiple inter-dependent pieces of evidence to support a hypothesis query. To systematically study this problem, we repurpose data from four domains for evaluating integrative grounding capabilities. Our investigation reveals two critical findings: First, in groundedness verification, while LLMs are robust to redundant evidence, they tend to rationalize using internal knowledge when information is incomplete. Second, in examining retrieval planning strategies, we find that undirected planning can degrade performance through noise introduction, while premise abduction emerges as a promising approach due to its logical constraints. Additionally, LLMs' zero-shot self-reflection capabilities consistently improve grounding quality. These insights provide valuable direction for developing more effective integrative grounding systems.