# Multi-Step Semantic Reasoning in Generative Retrieval

arXiv: https://arxiv.org/abs/2603.12368 · HTML: https://mlsanity.com/paper/2603.12368/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 12 Mar 2026.

## Builds on (most cited first, 21 of 21)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [8-bit Optimizers via Block-wise Quantization](https://mlsanity.com/paper/2110.02861/) (2021)
- [LoRA+: Efficient Low Rank Adaptation of Large Models](https://mlsanity.com/paper/2402.12354/) (2024)
- [Transformer Memory as a Differentiable Search Index](https://mlsanity.com/paper/2202.06991/) (2022)
- [Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval](https://mlsanity.com/paper/2108.05540/) (2021)
- [BM25S: Orders of magnitude faster lexical search via eager sparse scoring](https://mlsanity.com/paper/2407.03618/) (2024)
- [Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation](https://mlsanity.com/paper/2206.10128/) (2022)
- [OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2406.01775/) (2024)
- [GERE: Generative Evidence Retrieval for Fact Verification](https://mlsanity.com/paper/2204.05511/) (2022)
- [CorpusBrain: Pre-train a Generative Retrieval Model for Knowledge-Intensive Language Tasks](https://mlsanity.com/paper/2208.07652/) (2022)
- [SEEK: Semantic Reasoning for Object Goal Navigation in Real World Inspection Tasks](https://mlsanity.com/paper/2405.09822/) (2024)
- [CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Tasks](https://mlsanity.com/paper/2402.01176/) (2024)
- [A Unified Generative Retriever for Knowledge-Intensive Language Tasks via Prompt Learning](https://mlsanity.com/paper/2304.14856/) (2023)
- [Improving Document Representations by Generating Pseudo Query Embeddings for Dense Retrieval](https://mlsanity.com/paper/2105.03599/) (2021)
- [Teacher Forcing Recovers Reward Functions for Text Generation](https://mlsanity.com/paper/2210.08708/) (2022)
- [Understanding and Improving Zero-shot Multi-hop Reasoning in Generative Question Answering](https://mlsanity.com/paper/2210.04234/) (2022)

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

- [Lost in Decoding? Reproducing and Stress-Testing the Look-Ahead Prior in Generative Retrieval](https://mlsanity.com/paper/2604.23396/) (2026)

## Abstract (arXiv)

Generative retrieval (GR) models encode a corpus within model parameters and generate relevant document identifiers directly for a given query. While this paradigm shows promise in retrieval tasks, existing GR models struggle with complex queries in numerical contexts, such as those involving semantic reasoning over financial reports, due to limited reasoning capabilities. This limitation leads to suboptimal retrieval accuracy and hinders practical applicability. We propose ReasonGR, a framework designed to enhance multi-step semantic reasoning in numerical contexts within GR. ReasonGR employs a structured prompting strategy combining task-specific instructions with stepwise reasoning guidance to better address complex retrieval queries. Additionally, it integrates a reasoning-focused adaptation module to improve the learning of reasoning-related parameters. Experiments on the FinQA dataset, which contains financial queries over complex documents, demonstrate that ReasonGR improves retrieval accuracy and consistency, indicating its potential for advancing GR models in reasoning-intensive retrieval scenarios.