# GOLFer: Smaller LM-Generated Documents Hallucination Filter & Combiner for Query Expansion in Information Retrieval

arXiv: https://arxiv.org/abs/2506.04762 · HTML: https://mlsanity.com/paper/2506.04762/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 32 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Builds on (most cited first, 23 of 23)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction](https://mlsanity.com/paper/2112.01488/) (2021)
- [Overview of the TREC 2019 deep learning track](https://mlsanity.com/paper/2003.07820/) (2020)
- [Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval](https://mlsanity.com/paper/2108.05540/) (2021)
- [Overview of the TREC 2020 deep learning track](https://mlsanity.com/paper/2102.07662/) (2021)
- [The Curious Case of Hallucinations in Neural Machine Translation](https://mlsanity.com/paper/2104.06683/) (2021)
- [Dense Text Retrieval based on Pretrained Language Models: A Survey](https://mlsanity.com/paper/2211.14876/) (2022)
- [SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval](https://mlsanity.com/paper/2207.02578/) (2022)
- [Query expansion techniques for information retrieval: A survey](https://mlsanity.com/paper/1708.00247/) (2017)
- [Neural Models for Information Retrieval](https://mlsanity.com/paper/1705.01509/) (2017)
- [Query Expansion with Locally-Trained Word Embeddings](https://mlsanity.com/paper/1605.07891/) (2016)
- [Using Word Embeddings for Automatic Query Expansion](https://mlsanity.com/paper/1606.07608/) (2016)
- [Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage Retrieval](https://mlsanity.com/paper/2208.00511/) (2022)
- [Improving Query Expansion Using WordNet](https://mlsanity.com/paper/1309.4938/) (2013)

## Abstract (arXiv)

Large language models (LLMs)-based query expansion for information retrieval augments queries with generated hypothetical documents with LLMs. However, its performance relies heavily on the scale of the language models (LMs), necessitating larger, more advanced LLMs. This approach is costly, computationally intensive, and often has limited accessibility. To address these limitations, we introduce GOLFer - Smaller LMs-Generated Documents Hallucination Filter & Combiner - a novel method leveraging smaller open-source LMs for query expansion. GOLFer comprises two modules: a hallucination filter and a documents combiner. The former detects and removes non-factual and inconsistent sentences in generated documents, a common issue with smaller LMs, while the latter combines the filtered content with the query using a weight vector to balance their influence. We evaluate GOLFer alongside dominant LLM-based query expansion methods on three web search and ten low-resource datasets. Experimental results demonstrate that GOLFer consistently outperforms other methods using smaller LMs, and maintains competitive performance against methods using large-size LLMs, demonstrating its effectiveness.