Pith. sign in

REVIEW 3 cited by

Retrieval Augmented Generation for Domain-specific Question Answering

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2404.14760 v2 pith:BUJBUW53 submitted 2024-04-23 cs.CL cs.AIcs.IRcs.LG

Retrieval Augmented Generation for Domain-specific Question Answering

Sanat Sharma , David Seunghyun Yoon , Franck Dernoncourt , Dewang Sultania , Karishma Bagga , Mengjiao Zhang , Trung Bui , Varun Kotte This is my paper
classification cs.CL cs.AIcs.IRcs.LG
keywords largegenerationlanguageansweringapproachdomain-specificmodelsquestion
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Question answering (QA) has become an important application in the advanced development of large language models. General pre-trained large language models for question-answering are not trained to properly understand the knowledge or terminology for a specific domain, such as finance, healthcare, education, and customer service for a product. To better cater to domain-specific understanding, we build an in-house question-answering system for Adobe products. We propose a novel framework to compile a large question-answer database and develop the approach for retrieval-aware finetuning of a Large Language model. We showcase that fine-tuning the retriever leads to major improvements in the final generation. Our overall approach reduces hallucinations during generation while keeping in context the latest retrieval information for contextual grounding.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

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

  1. How You Ask Matters! Adaptive RAG Robustness to Query Variations

    cs.CL 2026-04 unverdicted novelty 7.0

    Adaptive RAG systems exhibit a large robustness gap: small surface changes in semantically identical queries cause big shifts in retrieval decisions and answer accuracy.

  2. PASC: Pipeline-Aware Conformal Prediction with Joint Coverage Guarantees for Multi-Stage NLP and LLM Pipelines

    cs.LG 2026-05 unverdicted novelty 6.0

    PASC converts multi-stage joint coverage into a single scalar conformal problem on the joint max nonconformity score, delivering finite-sample distribution-free guarantees and higher empirical coverage than Bonferroni...

  3. UCCI: Calibrated Uncertainty for Cost-Optimal LLM Cascade Routing

    cs.LG 2026-05 unverdicted novelty 5.0

    UCCI calibrates LLM uncertainty to error probabilities with isotonic regression for cost-optimal cascade routing, delivering 31% cost savings at maintained accuracy on a 75k-query NER task.