# Rational Retrieval Acts: Leveraging Pragmatic Reasoning to Improve Sparse Retrieval

arXiv: https://arxiv.org/abs/2505.03676 · HTML: https://mlsanity.com/paper/2505.03676/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 35 references that are in the map.
- First posted on arXiv 6 May 2025.

## Builds on (most cited first, 16 of 16)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction](https://mlsanity.com/paper/2112.01488/) (2021)
- [Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling](https://mlsanity.com/paper/2104.06967/) (2021)
- [Multi-Stage Document Ranking with BERT](https://mlsanity.com/paper/1910.14424/) (2019)
- [A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques](https://mlsanity.com/paper/2106.14807/) (2021)
- [Reasoning About Pragmatics with Neural Listeners and Speakers](https://mlsanity.com/paper/1604.00562/) (2016)
- [Learning Passage Impacts for Inverted Indexes](https://mlsanity.com/paper/2104.12016/) (2021)
- [Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding](https://mlsanity.com/paper/1703.10186/) (2017)
- [SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval](https://mlsanity.com/paper/2009.13013/) (2020)
- [Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes](https://mlsanity.com/paper/2109.08828/) (2021)
- [Pragmatically Informative Image Captioning with Character-Level Inference](https://mlsanity.com/paper/1804.05417/) (2018)
- [Pragmatically Informative Text Generation](https://mlsanity.com/paper/1904.01301/) (2019)
- [Wacky Weights in Learned Sparse Representations and the Revenge of Score-at-a-Time Query Evaluation](https://mlsanity.com/paper/2110.11540/) (2021)
- [Lost in Machine Translation: A Method to Reduce Meaning Loss](https://mlsanity.com/paper/1902.09514/) (2019)

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

- [QueStER: Query Specification for Generative keyword-based Retrieval](https://mlsanity.com/paper/2511.05301/) (2025)

## Abstract (arXiv)

Current sparse neural information retrieval (IR) methods, and to a lesser extent more traditional models such as BM25, do not take into account the document collection and the complex interplay between different term weights when representing a single document. In this paper, we show how the Rational Speech Acts (RSA), a linguistics framework used to minimize the number of features to be communicated when identifying an object in a set, can be adapted to the IR case -- and in particular to the high number of potential features (here, tokens). RSA dynamically modulates token-document interactions by considering the influence of other documents in the dataset, better contrasting document representations. Experiments show that incorporating RSA consistently improves multiple sparse retrieval models and achieves state-of-the-art performance on out-of-domain datasets from the BEIR benchmark. https://github.com/arthur-75/Rational-Retrieval-Acts