Interpret and Control Dense Retrieval with Sparse Latent Features (2025.naacl-short)
Copied to clipboard
| Challenge: | Dense embeddings deliver strong retrieval performance but lack interpretability and controllability. |
| Approach: | They propose a novel approach using sparse autoencoders to interpret and control dense embeddings via latent sparsity. |
| Outcome: | The proposed approach retains the same retrieval accuracy as the original dense vectors, affirming their faithfulness. |
Similar Papers
Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing sparse retrieval methods suffer from a lack of interpretability . we propose a new interpretability framework that decomposes dense embeddings into distinct, interpretable latent concepts. |
| Approach: | They propose a new interpretability framework that leveragesSparse Autoencoders to decompose uninterpretable dense embeddings fromDPR models into distinct, interpretable latent concepts. |
| Outcome: | The proposed interpretability framework achieves high index-space and computational efficiency while maintaining robust performance across vocabulary and semantic mismatches. |
Sparse Latents Steer Retrieval-Augmented Generation (2025.acl-long)
Copied to clipboard
Chunlei Xin, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Xuanang Chen, Xinyan Guan, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun
| Challenge: | In this study, we uncover interpretable latents that govern RAG behavior in large language models . Sparse Autoencoders are used to control large language model (LLM) behavior . |
| Approach: | They leverage Sparse Autoencoders within the LLaMA Scope to uncover latents that govern RAG behaviors. |
| Outcome: | The proposed model can be used to control large language models without architectural modifications. |
Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders (2025.findings-acl)
Copied to clipboard
Kristian Kuznetsov, Laida Kushnareva, Anton Razzhigaev, Polina Druzhinina, Anastasia Voznyuk, Irina Piontkovskaya, Evgeny Burnaev, Serguei Barannikov
| Challenge: | Existing algorithms for AI text detection lack interpretability, limiting their reliability in highstakes applications. |
| Approach: | They extend existing ATD frameworks by using Sparse Autoencoders to extract features from Gemma-2-2b residual stream. |
| Outcome: | The proposed algorithms can extract human-interpretable features from Gemma-2-2b model. |
On the Versatility of Sparse Autoencoders for In-Context Learning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Sparse autoencoders (SAEs) are emerging as a key analytical tool in interpretability for large language models. |
| Approach: | They propose to use SAEs to extract knowledge from billions of tokens for sparse reconstruction. |
| Outcome: | The proposed model can extract knowledge from billions of tokens for sparse reconstruction. |
IMRNNs: An Efficient Method for Interpretable Dense Retrieval via Embedding Modulation (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing dense retrieval methods rely on static embeddings that obscure bidirectional relationship between queries and documents. |
| Approach: | They propose a framework that augments any black-box dense retrievers with dynamic, bidirectional modulation at inference time. |
| Outcome: | a new framework augments any dense retriever with dynamic, bidirectional modulation at inference time. |
Typo-Robust Representation Learning for Dense Retrieval (2023.acl-short)
Copied to clipboard
Panuthep Tasawong, Wuttikorn Ponwitayarat, Peerat Limkonchotiwat, Can Udomcharoenchaikit, Ekapol Chuangsuwanich, Sarana Nutanong
| Challenge: | Dense retrieval is a fundamental building block of information retrieval applications. |
| Approach: | They propose a method that aligns misspelled queries with their pristine counterparts to improve contrast between each query and its surrounding queries. |
| Outcome: | The proposed method outperforms the competitors in all cases with misspelled queries. |
Sparse Autoencoder Features for Classifications and Transferability (2025.emnlp-main)
Copied to clipboard
| Challenge: | Sparse Autoencoders (SAEs) provide potential for uncovering structured, human-interpretable representations in Large Language Models (LLMs). |
| Approach: | They analyze SAEs for interpretable feature extraction from Large Language Models in safety-critical classification tasks. |
| Outcome: | The proposed framework outperforms hidden-state and BoW models while demonstrating cross-lingual toxicity detection and visual classification tasks. |
Dimension Reduction for Efficient Dense Retrieval via Conditional Autoencoder (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing work reserves the principle dimensions of query and document embeddings for building more efficient retrieval systems. |
| Approach: | They propose to use Conditional Autoencoder to compress high-dimensional embeddings to maintain the same embeddable distribution and better recover ranking features. |
| Outcome: | The proposed algorithm achieves comparable ranking performance with its teacher model and makes the retrieval system more efficient. |
SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have impressive capabilities in natural language understanding and generation, but controlling their behavior remains a challenge. |
| Approach: | They propose a supervised steering approach that operates in sparse, interpretable representation spaces. |
| Outcome: | The proposed approach achieves higher success rates with minimal degradation in generation quality compared to existing methods. |
Less is More: Pretrain a Strong Siamese Encoder for Dense Text Retrieval Using a Weak Decoder (2021.emnlp-main)
Copied to clipboard
Shuqi Lu, Di He, Chenyan Xiong, Guolin Ke, Waleed Malik, Zhicheng Dou, Paul Bennett, Tie-Yan Liu, Arnold Overwijk
| Challenge: | Dense retrieval requires high-quality text sequence embeddings to support effective search in the representation space. |
| Approach: | They propose a self-learning method that pre-trains the autoencoder using a weak decoder to push the encoder to provide better sequence representations. |
| Outcome: | The proposed model significantly boosts the effectiveness and few-shot ability of dense retrieval models on web search, news recommendation, and open domain question answering. |