Pith. sign in

REVIEW 14 cited by

Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases

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

arxiv 2403.10446 v1 pith:A6GEO2YG submitted 2024-03-15 cs.CL cs.LG

classification cs.CLcs.LG
keywords datasetsdomain-specificllmsmodelssystemaccuracyfactualhallucinations
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We proposed an end-to-end system design towards utilizing Retrieval Augmented Generation (RAG) to improve the factual accuracy of Large Language Models (LLMs) for domain-specific and time-sensitive queries related to private knowledge-bases. Our system integrates RAG pipeline with upstream datasets processing and downstream performance evaluation. Addressing the challenge of LLM hallucinations, we finetune models with a curated dataset which originates from CMU's extensive resources and annotated with the teacher model. Our experiments demonstrate the system's effectiveness in generating more accurate answers to domain-specific and time-sensitive inquiries. The results also revealed the limitations of fine-tuning LLMs with small-scale and skewed datasets. This research highlights the potential of RAG systems in augmenting LLMs with external datasets for improved performance in knowledge-intensive tasks. Our code and models are available on Github.

Discussion (0). Sign in to comment.

Forward citations

Cited by 14 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs

    cs.CL 2025-06 conditional novelty 7.0 of 10

    The paper introduces a taxonomy and benchmark for knowledge conflicts in search-augmented LLMs, and experiments show that prompting for conflict type improves response quality.

  2. Quasiparticle interference in LiFeAs: Signature of inelastic tunneling through spin fluctuations

    cond-mat.supr-con 2025-08 unverdicted novelty 6.0 of 10

    Replica QPI features in LiFeAs are attributed to inelastic tunneling through spin fluctuations at 8 to 10 meV, matching neutron scattering.

  3. From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs

    cs.CL 2025-07 conditional novelty 6.0 of 10

    TIRESRAG-R1 trains RAG models with sufficiency, thinking, and reflection rewards plus difficulty-aware reweighting, improving multi-hop QA accuracy.

  4. EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora

    cs.IR 2025-06 conditional novelty 6.0 of 10

    EraRAG uses hyperplane-based locality-sensitive hashing to build a hierarchical retrieval graph whose affected regions only are re-summarized when new documents arrive, cutting update cost by up to an order of magnitude.

  5. MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A pre-training task called RAMP, where models practice searching to fill masked text spans, improves downstream agentic open-domain QA performance across Qwen and LLaMA models.

  6. Novobo: Supporting Teachers' Peer Learning of Instructional Gestures by Teaching a Mentee AI-Agent Together

    cs.HC 2025-05 conditional novelty 6.0 of 10

    Novobo, a teachable AI agent that acts as an apprentice teacher, helped 30 teachers in 10 sessions externalize and co-construct knowledge about instructional gestures through group discussion and embodied demonstration.

  7. Integrating Rules and Semantics for LLM-Based C-to-Rust Translation

    cs.SE 2025-08 unverdicted novelty 5.0 of 10

    IRENE combines rule-based retrieval, structured summarization, and compiler feedback to improve LLM-based C-to-Rust translation accuracy and safety.

  8. DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection

    cs.AI 2025-07 conditional novelty 5.0 of 10

    DeRAG shows that five or fewer tokens found by differential evolution can make black-box RAG retrievers rank a chosen wrong document near the top on small BEIR subsets.

  9. Context-Aware Search and Retrieval Over Erasure Channels

    cs.IR 2025-07 conditional novelty 4.0 of 10

    A bivariate Gaussian approximation yields a formula for the retrieval error probability in two-document TF-IDF search over an erasure channel with repetition coding.

  10. LLM-Assisted Question-Answering on Technical Documents Using Structured Data-Aware Retrieval Augmented Generation

    cs.CL 2025-06 reject novelty 4.0 of 10

    A RAG pipeline with OCR, table and image to text conversion, and a RAFT-tuned reranker reports high QA scores, but its 50-question evaluation overlaps with its training manuals and its baseline comparison uses only 5 ...

  11. Fine-Tuning and Prompt Engineering of LLMs, for the Creation of Multi-Agent AI for Addressing Sustainable Protein Production Challenges

    cs.AI 2025-06 conditional novelty 4.0 of 10

    A proof-of-concept multi-agent GPT system for microbial protein literature extraction shows both fine-tuning and prompt engineering improve cosine-similarity scores, with fine-tuning slightly ahead but more variable.

  12. Continually Self-Improving Language Models for Bariatric Surgery Question--Answering

    cs.CL 2025-05 reject novelty 4.0 of 10

    bRAGgen uses a perplexity threshold to trigger web retrieval and LoRA fine-tuning, improving answers on a new bariatric surgery QA dataset, but the evaluation is confounded by test-time adaptation.

  13. A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models

    cs.IR 2025-07 reject novelty 3.0 of 10

    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.

  14. Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges

    cs.AI 2025-06 unverdicted novelty 3.0 of 10

    A review that classifies Reasoning Agentic RAG into predefined (System 1-like) and agentic (System 2-like) workflows, surveying their designs and training strategies.

Pith tools