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.

Similar Papers

How Retrieved Context Shapes Internal Representations in RAG (2026.findings-acl)

Copied to clipboard

Challenge: Retrieval-augmented generation (RAG) is a widely adopted approach for enhancing large language models with external knowledge.
Approach: They analyze how different types of retrieved documents affect the hidden states of large language models and how these internal representation shifts relate to downstream generation behavior.
Outcome: The results show that context relevancy and layer-wise processing influence internal representations, providing explanations of LLMs’ output behaviors and insights for RAG system design.
Enhancing Retrieval-Augmented Generation: A Study of Best Practices (2025.coling-main)

Copied to clipboard

Challenge: Retrieval-augmented generation systems have shown remarkable advancements by integrating retrieval mechanisms into language models, enhancing their ability to produce more accurate and contextually relevant responses.
Approach: They propose to integrate query expansion, various novel retrieval strategies, and a Contrastive In-Context Learning RAG to improve response quality.
Outcome: The proposed RAGs incorporate query expansion, various novel retrieval strategies, and a novel Contrastive In-Context Learning RAG.
CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods focus on detecting LLM’s confidence via statistical uncertainty.
Approach: They propose to use a representation perspective to solve adaptive RAG by enabling dynamic retrieval during generation and enabling retrieval only when the query exceeds LLM's internal knowledge.
Outcome: The proposed framework is superior to existing adaptive RAG methods on a diverse set of tasks.
On the Influence of Context Size and Model Choice in Retrieval-Augmented Generation Systems (2025.findings-naacl)

Copied to clipboard

Challenge: Retrieval-augmented generation (RAG) is an approach to augment large language models (LLMs) despite their impressive performance, LLMs can generate plausible sounding but factually incorrect responses (hallucinations)
Approach: They propose to use BM25 and semantic search as retrievers to augment large language models by reducing their reliance on static knowledge and improving answer factuality.
Outcome: The proposed approach improves QA performance on a biomedical task with up to 15 snippets but stagnates or declines beyond that.
DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generation (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for generating large language models face limitations in key aspects such as retrieval triggers and contextual scrutiny of retrieval content.
Approach: They propose a dynamic RAG method that uses cognitive detection and contextual retrieval optimization to determine when retrieval is needed and what to retrieve for LLMs.
Outcome: The proposed method achieves superior performance on all tasks, demonstrating the effectiveness of the proposed method.
Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective (2025.naacl-long)

Copied to clipboard

Challenge: Existing studies have shown that LLMs struggle to identify the boundaries of their own knowledge and tend to prioritize external information over internal knowledge learned during pre-training.
Approach: They conduct a comprehensive analysis of LLM representation behaviors and demonstrate the significance of using representations in knowledge checking.
Outcome: The proposed classifiers improve performance even when dealing with noisy knowledge databases.
LLM-Generated Text May Harm Your Retrieval! A Robust Detection Strategy for Retrieval-Augmented Generation (2026.acl-long)

Copied to clipboard

Challenge: Retrieval-augmented generation (RAG) improves accuracy and timeliness of large language models, but external corpora may become contaminated with LLM-generated texts.
Approach: They propose a method that integrates external knowledge retrieved from external sources into RAG to filter out LLM-generated texts from retrieved results.
Outcome: The proposed method mitigates performance degradation and improves stability of RAG systems.
A Survey of RAG-Reasoning Systems in Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: a survey of RAG-based reasoning-based approaches shows that it is not effective for multi-step inferences.
Approach: They map how advanced reasoning optimizes each stage of RAG . they show how retrieved knowledge supply missing premises and expand context for complex inference .
Outcome: The proposed frameworks achieve state-of-the-art across knowledge-intensive benchmarks.
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.
Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders (2025.emnlp-main)

Copied to clipboard

Challenge: Sparse Autoencoders (SAEs) have recently emerged as powerful tools for interpreting and steering the internal representations of large language models (LLMs).
Approach: They propose a method that identifies the most influential latents by incorporating output-side gradient information.
Outcome: The proposed method identifies the most influential latents by incorporating output-side gradient information.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations