Pith Number

pith:YFWTNFBR

pith:2026:YFWTNFBRXI6Z667E2OUXYKE7SW

not attested not anchored not stored refs resolved

Domain Adaptation of Large Language Models for Polymer-Composite Additive Manufacturing Using Retrieval-Augmented Generation and Fine-Tuning

Erina Baynojir Joyee, Minhaj Nur Alam, Saiful Islam Sagor, Tania Haghighi

Retrieval-augmented generation adapts large language models to additive manufacturing questions far better than fine-tuning on raw domain text.

arxiv:2605.12516 v1 · 2026-04-02 · cs.CL · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{YFWTNFBRXI6Z667E2OUXYKE7SW}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Results show that the RAG model consistently outperforms the baseline. Among the 200 questions, 75.5% of RAG responses are judged more accurate, 85.2% are preferred overall, and 90.8% are rated more relevant than baseline responses. In contrast, fine-tuning on raw AM text reduces performance, producing more accurate answers in only 5.6% of cases and more relevant answers in 32.5% of cases.

C2weakest assumption

That the 200 expert-designed questions and the mechanical engineering experts' judgments provide an unbiased and representative measure of real-world answer quality, and that the fine-tuning performed was a fair test of naive domain adaptation without additional techniques such as instruction tuning or data cleaning.

C3one line summary

RAG-adapted LLaMA-3-8B outperforms both baseline and fine-tuned models on expert-rated accuracy (75.5%), relevance (90.8%), and overall preference (85.2%) for additive manufacturing questions.

References

38 extracted · 38 resolved · 3 Pith anchors

[1] Methodology This section outlines the complete methodological framework used to adapt and evaluate a general-purpose LLM in the AM domain. The methodology integrates domain -specific dataset construct

[2] Better Answer

[3] Discussions The results of this study demonstrate that retrieval -based augmentation is significantly more effective than direct fine -tuning for adapting large language models to specialized engineer

[4] The results show that retrieval-augmented generation significantly improves model performance by g rounding responses in domain -specific knowledge

[5] LLaMA: Open and Efficient Foundation Language Models 2023 · arXiv:2302.13971

Receipt and verification

First computed	2026-05-18T03:10:02.908703Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c16d369431ba3d9f7be4d3a97c289f95af1f5fccdeb763e3ec7f33f314422c58

Aliases

arxiv: 2605.12516 · arxiv_version: 2605.12516v1 · doi: 10.48550/arxiv.2605.12516 · pith_short_12: YFWTNFBRXI6Z · pith_short_16: YFWTNFBRXI6Z667E · pith_short_8: YFWTNFBR

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/YFWTNFBRXI6Z667E2OUXYKE7SW \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: c16d369431ba3d9f7be4d3a97c289f95af1f5fccdeb763e3ec7f33f314422c58

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "923fa106d2c3c37153497128d3760fbdf7ec884475e929270c78a8cee96b2396",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-04-02T20:52:34Z",
    "title_canon_sha256": "1bb59d3c23e3fb573fe4080bc54667ae879dd41d297e36c8ac406a3c6e126e9c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12516",
    "kind": "arxiv",
    "version": 1
  }
}