REVIEW 7 cited by
Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Large Language Models (LLMs) exhibit substantial capabilities yet encounter challenges, including hallucination, outdated knowledge, and untraceable reasoning processes. Retrieval-augmented generation (RAG) has emerged as a promising solution, integrating knowledge from external databases to mitigate these challenges. However, inappropriate retrieved passages can potentially hinder the LLMs' capacity to generate comprehensive and high-quality responses. Prior RAG studies on the robustness of retrieval noises often confine themselves to a limited set of noise types, deviating from real-world retrieval environments and limiting practical applicability. In this study, we initially investigate retrieval noises and categorize them into three distinct types, reflecting real-world environments. We analyze the impact of these various retrieval noises on the robustness of LLMs. Subsequently, we propose a novel RAG approach known as Retrieval-augmented Adaptive Adversarial Training (RAAT). RAAT leverages adaptive adversarial training to dynamically adjust the model's training process in response to retrieval noises. Concurrently, it employs multi-task learning to ensure the model's capacity to internally recognize noisy contexts. Extensive experiments demonstrate that the LLaMA-2 7B model trained using RAAT exhibits significant improvements in F1 and EM scores under diverse noise conditions. For reproducibility, we release our code and data at: https://github.com/calubkk/RAAT.
Forward citations
Cited by 7 Pith papers
-
Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking
Shifts in an LLM's hidden-state confidence, before and after a retrieved context, are used as a preference signal to fine-tune a reranker and to trigger retrieval only when initial confidence is low.
-
Multi-Modal Requirements Data-based Acceptance Criteria Generation using LLMs
Multi-modal RAG (text plus UI screenshots) with reward-based polishing generates acceptance criteria from user stories that three industry experts rated near 4/5 on relevance, correctness, and understandability.
-
Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG
A post-training method that divides RAG queries into four knowledge quadrants and uses DPO to make models abstain appropriately, improving accuracy and abstention on NQ, TriviaQA, and WebQ.
-
Predict the Retrieval! Test time adaptation for Retrieval Augmented Generation
Training the language model for a few gradient steps to predict the end of retrieved passages improves specialized-domain RAG accuracy in the paper's tests, by up to 25 points on medical QA.
-
Investigating the Robustness of Retrieval-Augmented Generation at the Query Level
Retrieval-augmented generation performance drops noticeably under minor query perturbations, with end-to-end results often tracking retriever behavior.
-
Boosting Data Utilization for Multilingual Dense Retrieval
A three-stage data-utilization pipeline for multilingual dense retrieval, combining ensemble hard-negative mining, LLM-based filtering/generation, and monolingual topic-diverse mini-batches, improves MIRACL nDCG@10 by...
-
A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models
A survey claims proactive defenses against LLM misinformation outperform post-hoc detection by up to 63%, but no meta-analysis details are provided to support the claim.
Discussion (0). Sign in to comment.