Retrieval Augmented Generation of Literature-derived Polymer Knowledge: The Example of a Biodegradable Polymer Expert System

Sonakshi Gupta; Akhlak Mahmood; Wei Xiong; Rampi Ramprasad

cs.CEFeb 18, 2026

Retrieval Augmented Generation of Literature-derived Polymer Knowledge: The Example of a Biodegradable Polymer Expert System

Authors: Sonakshi Gupta, Akhlak Mahmood, Wei Xiong, Rampi Ramprasad

Organizations: School of Computational Science and Engineering, Georgia Institute of Technology, 771 Ferst Drive NW, Atlanta 30332, GA, USA. · Matmerize, Inc., Atlanta 30308, GA, USA. · School of Materials Science and Engineering, Georgia Institute of Technology, 771 Ferst Drive NW, Atlanta, GA 30332, USA

Abstract

Polymer literature contains a large and growing body of experimental knowledge, yet much of it is buried in unstructured text and inconsistent terminology, making systematic retrieval and reasoning difficult. Existing tools typically extract narrow, study-specific facts in isolation, failing to preserve the cross-study context required to answer broader scientific questions. Retrieval-augmented generation (RAG) offers a promising way to overcome this limitation by combining large language models (LLMs) with external retrieval, but its effectiveness depends strongly on how domain knowledge is represented. In this work, we develop two retrieval pipelines: a dense semantic vector-based approach (VectorRAG) and a graph-based approach (GraphRAG). Using over 1,000 polyhydroxyalkanoate (PHA) papers, we construct context-preserving paragraph embeddings and a canonicalized structured knowledge graph supporting entity disambiguation and multi-hop reasoning. We evaluate these pipelines through standard retrieval metrics, comparisons with general state-of-the-art systems such as GPT and Gemini, and qualitative validation by a domain chemist. The results show that GraphRAG achieves higher precision and interpretability, while VectorRAG provides broader recall, highlighting complementary trade-offs. Expert validation further confirms that the tailored pipelines, particularly GraphRAG, produce well-grounded, citation-reliable responses with strong domain relevance. By grounding every statement in evidence, these systems enable researchers to navigate the literature, compare findings across studies, and uncover patterns that are difficult to extract manually. More broadly, this work establishes a practical framework for building materials science assistants using curated corpora and retrieval design, reducing reliance on proprietary models while enabling trustworthy literature analysis at scale.

Figures & tables

Figure 1: (a) Overview of the retrieval-augmented generation (RAG) framework for literature-grounded question answering on PHAs. The curated PHA corpus, comprising 1,028 articles and 44,609 parsed paragraphs, serves as the shared knowledge base for both VectorRAG and GraphRAG retrieval pipelines. Retrieved contextual evidence from each pipeline is provided to a LLM to generate literature-grounded responses. (b) Example scientific queries and corresponding responses generated by the Polymer Literature Scholar. Responses are synthesized by aggregating evidence retrieved from multiple relevant studies within the PHA corpus, as indicated by the document symbol.

Figure 2: VectorRAG workflow for literature-grounded question answering on PHAs. ( a ) Backend processing of the corpus, where full-text articles are parsed, contextually grouped into condensed text chunks, and embedded into a dense semantic space for similarity-based retrieval. ( b ) Retrieval-augmented inference, in which user queries are encoded in the same latent space and matched to the most semantically aligned text segments from the corpus. ( c ) Conceptual representation of the embedding space illustrating how relevant paragraphs are identified through cosine similarity between the query vector and its nearest neighbors. ( d ) Example of a representative query showing retrieved literature passages and the corresponding grounded, citation-linked response generated by the language model.

Figure 3: GraphRAG workflow for knowledge graph–based question answering on PHAs. ( a ) Backend processing of the corpus, where entities and relationships are extracted from literature, normalized, and stored as relational tuples in a relational database. ( b ) Retrieval and reasoning stage showing how user queries are decomposed into entity–relation pairs, matched to canonical entities, and re-ranked through a path-based scoring strategy to identify the most relevant subgraphs for grounded response generation. ( c ) Example of entity canonicalization, where multiple related mentions (e.g., PHB–Ag, maleated PHB, 3-armed PHB) are merged into a unified canonical node representing PHB. The accompanying bar plot highlights the top canonical entities ranked by cluster size, demonstrating how normalization improves graph connectivity and recall. ( d ) Representative example showing a user query, retrieved knowledge graph tuples, and the corresponding grounded response synthesized by the language model with supporting citations.

Models	Context limit	Recall	Accuracy	Avg. response time (s)	Avg. total cost ($)
GraphRAG
GPT-4o-mini	300 tuples	0.982	0.991	7.18	0.00097
Llama-3.1-70B	300 tuples	0.991	0.991	10.23	0.00000
VectorRAG
GPT-4o-mini	8 paragraphs	0.973	1.000	16.43	0.00186
Llama-3.1-70B	8 paragraphs	0.973	1.000	41.75	0.00000

Table 1: Controlled Evaluation : Reported metrics include recall, accuracy, and average per-query response time and cost for GraphRAG and VectorRAG on a subset of 21 PHA DOIs, using optimized context limits of 300 tuples and 8 paragraphs, respectively.

Models	Context limit	Recall	Accuracy	Avg. response time (s)	Avg. total cost ($)
GraphRAG
GPT-4o-mini	300 tuples	0.938	0.973	34.14	0.00070
Llama-3.1-70B	300 tuples	0.903	0.964	24.18	0.0
VectorRAG
GPT-4o-mini	8 paragraphs	0.717	0.960	17.69	0.00184
Llama-3.1-70B	8 paragraphs	0.717	0.960	40.35	0.0

Table 2: Evaluation at Scale : Reported metrics include recall, accuracy, and average per-query response time and cost for GraphRAG and VectorRAG on 1028 PHA DOIs, using optimized context limits of 300 tuples and 8 paragraphs, respectively.

Question	GraphRAG Response	VectorRAG Response
1. What are the main monomeric products of abiotic PHB hydrolysis and under what conditions are they typically formed?	The main monomeric products of abiotic PHB hydrolysis are (R)-3-HBA and CA [4]. This process typically occurs under conditions of 70–220 °C [5].	The main monomeric products of abiotic PHB hydrolysis are D-(-)-3-hydroxybutyric acid (3HBA) and crotonic acid (CA). These products are typically formed under acidic or alkaline conditions, where the ester linkages in the polymer chain undergo hydrolysis. Specifically, at neutral pH (7.4), 3HB is a major intermediate product of PHB degradation [1]. Under acidic conditions (0.1–4.0 M H), 3HBA and CA are formed, with CA being the dominant monomeric product in highly concentrated acid solutions (80–98 wt% H2SO4) [2]. Conversely, alkaline conditions (0.1–4.0 M OH-) result in higher amounts of both 3HB and CA.
2. What challenges are associated with producing low-density PLA foams, and how can these be addressed?	Producing low-density PLA foams presents several challenges, primarily related to the material’s intrinsic properties and processing conditions. 1. Melt Strength and Elasticity: PLA exhibits low melt elasticity and low melt strength, which complicates the production of low-density foams. These properties can hinder the ability to achieve the desired foam structure during processing [211][212]. 2. Crystallinity and Foamability: High crystallinity in PLA can limit the expansion of the produced foam, reducing its foamability [200]. Additionally, slow crystallization kinetics contribute to the challenges in achieving uniform cell structures and desirable densities [266]. 3. Cell Structure Uniformity: Achieving uniform cell structures in large-scale settings is particularly challenging for low-density PLA foams. This uniformity is critical for maintaining consistent mechanical properties throughout the foam [213].	Producing low-density PLA foams is challenged by factors such as PLA’s poor melt strength and low melt elasticity, which lead to inadequate foaming behavior without modifications. Additionally, the crystallization behavior of PLA can hinder foaming, particularly at higher crystallization rates, which can prevent effective cell formation and growth. The $CO_{2}$ induced crystallization at high pressures can further complicate the foaming process by increasing crystalline regions that reduce foamability. These challenges can be addressed by blending PLA with polyhydroxybutyrate (PHBV), which improves the rheological properties and enhances foamability. PHBV acts as a nucleating agent for PLA, potentially leading to better cell structure and reduced density in the foams.
	4. Surface-to-Volume Ratios: Producing foams with high surface-to-volume ratios is another challenge, as it impacts the foam’s overall performance and applications [214]. 5. Processing Variables: The interaction between material properties and processing conditions is crucial in determining foam characteristics. Variations in pressure, temperature, and the type of foaming agents used can significantly affect the final foam structure [220][250]. To address these challenges, several strategies could be employed: – Additives and Blending: Incorporating additives or blending PLA with other polymers, such as PHBV, can enhance the foaming properties and mechanical strength of the resulting foams [18][130]. Optimized Processing Techniques: Utilizing advanced processing techniques, such as film/foam coextrusion, may enhance the production of low-density PLA foams by allowing better control over processing parameters [21][264].	Adjusting the composition of the blend and optimizing processing conditions, such as foaming temperature and pressure, can also help achieve the desired foam properties while minimizing the adverse effects of crystallization and melt strength limitations [1][2][4][8].
3. How do the physical and thermal properties of P(3HB) and P(4HB) differ and what are the implications of these differences for their potential applications?	The knowledge graph does not provide specific details on the physical and thermal properties of P(3HB) and P(4HB) directly. However, it does mention the analysis of PHB, which is related to P(3HB) and has implications for thermal behavior and processing. 1. PHB (a homopolymer of 3HB) is analyzed by thermal analysis to understand its properties [4]. 2. The difference between melting and thermal degradation temperatures affects the processability of PHB production [20]. 3. Blending with other polymers can improve mechanical properties, flexibility/ductility, and processability of PHAs [14].	The physical and thermal properties of P(3HB) and P(4HB) differ significantly, which has implications for their potential applications. P(3HB) is a highly crystalline, water-insoluble polymer with a high Young’s modulus (3.5 GPa) and low tensile strength (43 MPa). It is brittle, with an elongation at break of only 5%, making it less suitable for applications requiring flexibility [3]. Its melting temperature is around 180 °C, and it possesses a glass transition temperature of approximately 4 °C [5]. These characteristics limit its use primarily to applications where rigidity and stability are needed.
	While these points provide some context about the thermal properties of PHB, they do not directly compare P(3HB) and P(4HB) or provide their specific physical properties and implications for applications. Therefore, there is insufficient information in the knowledge graph to answer the question regarding the differences between P(3HB) and P(4HB) and their implications comprehensively.	In contrast, P(4HB) is a strong, malleable thermoplastic with a tensile strength comparable to polyethylene and an elongation at break of 100% [4]. This high elasticity makes P(4HB) suitable for applications requiring flexibility and resilience. Its thermal properties include a lower melting point of about 164 °C and a glass transition temperature of 3 °C [6], which allows for easier processing and adaptability in various applications. The differences in mechanical properties imply that while P(3HB) may be used in rigid applications, such as packaging or structural components, P(4HB) is better suited for applications requiring elasticity and flexibility, such as in biomedical devices or flexible films. Additionally, the ability to create copolymers, such as P(3HB-co-4HB), allows for tailored properties that can merge the strengths of both polymers for diverse applications [8].

Table 3: Qualitative comparison of GraphRAG and VectorRAG responses to representative polymer science questions, illustrating differences in retrieval behavior, reasoning depth, and grounding style between the two pipelines.

Figure 4: Domain-expert evaluation of five RAG pipelines across General, Paper-specific, and Multi-paper questions. Scores reflect how well each system balanced factual grounding, contextual coverage, and citation reliability. GraphRAG (GPT-4o-mini) and ChatGPT-5 with Web Search achieved the highest overall performance, with other pipelines showing moderate but consistent results.

Retrieval-Augmented Generation

Retrieval-augmented generation connects language models to external knowledge so answers can use current, domain-specific evidence.

See all 792 papers

Sep 29, 2026

Re-ranking and Late Interaction Drive Retrieval Quality: A Controlled Comparison of RAG Strategies for Scientific Question Answering

Retrieval-Augmented Generation (RAG) is now the standard way to ground Large Language Models (LLMs) in external knowledge, yet the design space of retrieval pipelines is large and the trade-offs between variants are not well understood, especially on domain-specific corpora at realistic scale. In this work, we present a controlled comparison of six retrieval strategies for scientific question answering: (i) classic top-k dense retrieval, (ii) LLM-based query rephrasing, (iii) query rephrasing followed by LLM-based reranking, (iv) multi-query fusion via Reciprocal Rank Fusion (RRF), (v) an agentic tool-call pipeline in which the generator decides for itself whether to retrieve, and (vi) late-interaction retrieval with ColBERTv2. All six pipelines share the same generator (Meta-Llama/Llama-3.1-8B-Instruct), prompt, and evaluation protocol; the five single-vector pipelines additionally share SPECTER2 embeddings and a Chroma vector store; and all six retrieve from the full corpus of 463,971 arXiv papers dated 2024-2025. To support reproducible, large-scale evaluation, we also release a synthetic question dataset of 19,484 problem-statement and methodology questions generated by Llama-3.1-8B-Instruct from a random sample of 10,000 papers across academic domains (query generation succeeded for 9,742 of them), and every strategy is evaluated on this same query set. We describe the architecture and implementation of each pipeline, release the code and the synthetic question dataset, and evaluate each strategy with an LLM-as-a-judge protocol along multiple quality dimensions, together with direct gold-paper retrieval metrics. The result is an open testbed for studying the cost and quality trade-offs of RAG design choices on a research-literature corpus, and a basis for future work on faithfulness, retrieval robustness, and agentic retrieval.

Bhagyesh Rathi, Eshan Chawla, William B. Andreopoulos

San Jose State University, Department of Computer Science

Late Interaction Retrieval Scientific QA LLM Reranking Agentic Retrieval RAG Evaluation

Ask PDF

Feb 19, 2026

Enhancing Scientific Literature Chatbots with Retrieval-Augmented Generation: A Performance Evaluation of Vector and Graph-Based Systems

This paper investigates the enhancement of scientific literature chatbots through retrieval-augmented generation (RAG), with a focus on evaluating vector- and graph-based retrieval systems. The proposed chatbot leverages both structured (graph) and unstructured (vector) databases to access scientific articles and gray literature, enabling efficient triage of sources according to research objectives. To systematically assess performance, we examine two use-case scenarios: retrieval from a single uploaded document and retrieval from a large-scale corpus. Benchmark test sets were generated using a GPT model, with selected outputs annotated for evaluation. The comparative analysis emphasizes retrieval accuracy and response relevance, providing insight into the strengths and limitations of each approach. The findings demonstrate the potential of hybrid RAG systems to improve accessibility to scientific knowledge and to support evidence-based decision making.

Hamideh Ghanadian, Amin Kamali, Mohammad Hossein Tekieh

Pest Management Regulatory Agency (PMRA), Health Canada, Ottawa, ON, Canada · Faculty of Engineering, University of Ottawa, Ottawa, ON, Canada · Oral Health Branch (OHB), Health Canada, Ottawa, ON, Canada

RAG Evaluation Graph Retrieval-Augmented Generation Hybrid Retrieval IR Evaluation Scientific QA

Ask PDF

Mar 23, 2026

Graph-Aware Late Chunking for Retrieval-Augmented Generation in Biomedical Literature

Retrieval-Augmented Generation (RAG) systems for biomedical literature are typically evaluated using ranking metrics like Mean Reciprocal Rank (MRR), which measure how well the system identifies the single most relevant chunk. We argue that for full-text scientific documents, this paradigm is incomplete: it rewards retrieval precision while ignoring retrieval breadth -- the ability to surface evidence from across a document's structural sections. We propose GraLC-RAG, a framework that unifies late chunking with graph-aware structural intelligence, introducing structure-aware chunk boundary detection, UMLS knowledge graph infusion, and graph-guided hybrid retrieval. We evaluate six strategies on 2,359 IMRaD-filtered PubMed Central articles using 2,033 cross-section questions and two metric families: standard ranking metrics (MRR, Recall@k) and structural coverage metrics (SecCov@k, CS Recall). Our results expose a sharp divergence: content-similarity methods achieve the highest MRR (0.517) but always retrieve from a single section, while structure-aware methods retrieve from up to 15.6x more sections. Generation experiments show that KG-infused retrieval narrows the answer-quality gap to delta-F1 = 0.009 while maintaining 4.6x section diversity. These findings demonstrate that standard metrics systematically undervalue structural retrieval and that closing the multi-section synthesis gap is a key open problem for biomedical RAG.

Pouria Mortezaagha, Arya Rahgozar

Methodological Implementation Research, Ottawa Hospital Research Institute, Ottawa, ON, Canada · School of Engineering Design and Teaching Innovation, University of Ottawa, Ottawa, ON, Canada

Retrieval-Augmented Generation Biomedical IR Graph Retrieval-Augmented Generation Document Chunking RAG Evaluation Hybrid Retrieval

Ask PDF

Abstract

Retrieval-Augmented Generation

Explore similar work

Re-ranking and Late Interaction Drive Retrieval Quality: A Controlled Comparison of RAG Strategies for Scientific Question Answering

Enhancing Scientific Literature Chatbots with Retrieval-Augmented Generation: A Performance Evaluation of Vector and Graph-Based Systems

Graph-Aware Late Chunking for Retrieval-Augmented Generation in Biomedical Literature