HCI‑LLM: Building a Local Research Assistant for 8,000+ CHI Papers

The Problem That Started It (A Supervisor’s Question)

It started with a simple moment in the lab.

My supervisor, YunSuen Pai, came to me with a problem that every HCI researcher quietly suffers from:

“We have thousands of CHI papers… how do we actually use them when we need to write, design a study, or find gaps—without spending weeks doing Ctrl+F across PDFs?”

The obvious answer is “use an LLM.”

The real HCI answer is: you don’t just need answers—you need trust.

Because in research, it’s not enough for a system to be fluent. It needs to be:

grounded (show sources)
auditable (prove where the answer came from)
privacy-preserving (papers stay local)
fast (so it fits real workflow)

That’s how HCI‑LLM (a.k.a. HCI Research Assistant) was born: a fully local RAG-based research assistant for exploring 8,000+ CHI conference papers.

What I Built (In One Sentence)

A local system that ingests CHI PDFs → builds a vector database → answers questions with citations and confidence—without sending anything to the cloud.

At a high level:

PDFs → Text/Metadata → Chunking → Embeddings → ChromaDB
Query → Retrieval → Context → Local LLM (LMStudio) → Answer + Sources + Confidence

Why “Local” Matters (More Than You Think)

If you’re doing HCI research, your PDFs can include:

copyrighted proceedings
unpublished drafts
sensitive notes and ideas
early research directions

Uploading that to a hosted API is often a non-starter.

So I designed the system to be 100% local:

PDFs stay on disk
vector DB persists locally
LLM runs via LMStudio (OpenAI-compatible local server)

That choice shaped everything else: performance, UX, and reliability.

Core Features That Make It Useful (Not Just “Cool”)

HCI‑LLM isn’t a single chat box. It’s a workflow tool:

1) Semantic Search Across Thousands of Papers

Instead of keyword search, you can ask:

“What are common evaluation methods for accessibility tools?”
“How do papers measure cognitive load in XR?”
“Summarize approaches to participatory design for older adults.”

And get a response backed by relevant paper chunks + citations.

2) Specialized Research “Skills”

The system supports structured modes like:

Literature review
Methodology analysis
Gap analysis
Comparative analysis
Brainstorming research ideas (with scoring)

These aren’t gimmicks—they are prompts + scaffolds aligned with real research tasks.

3) Analytics

Because discovery isn’t only Q&A:

papers by year
topic distributions
trends
(eventually) author networks + citation context

The Most Important Part: Anti‑Hallucination (Trust Design)

If an LLM confidently makes things up, it’s worse than useless.

So the RAG pipeline is designed around citation-backed responses:

retrieval filters by similarity threshold
confidence scoring considers evidence + sources
explicit “I don’t know” when confidence is low
low temperature for factual modes

In other words: trust is a feature, not an afterthought.

Scaling Up: 8,000+ PDFs Without Re‑Ingesting Forever

One underrated challenge is operational:

ingestion takes time, and re-ingesting a 5,000–8,000 PDF library is painful.

So HCI‑LLM is designed for:

persistent vector DB (ChromaDB on disk)
incremental ingestion (only new files are processed)
checkpointing (resume if interrupted)
parallel processing for speed

That matters because real research libraries grow weekly.

Quick Start (If You Want to Try It)

If you have the repo, the workflow is:

cd HCI-Agent/HCI_LLM
./setup.sh
./start.sh

Then:

Streamlit UI: http://localhost:8501
API Docs: http://localhost:8000/docs

To ingest papers:

python scripts/ingest.py --max-files 10
python scripts/ingest.py --parallel --workers 8

What I Learned (HCI Lens)

Building HCI‑LLM taught me that “LLM UX” isn’t just prompts—it’s:

provenance UI (sources must be legible)
error UX (“no answer” should be graceful, not failure)
workflow fit (what do researchers do before and after the answer?)
performance as UX (latency changes trust)

The system is a research tool, but also a design experiment:

How do we build LLM interfaces that earn trust in high-stakes knowledge work?

What’s Next

I’m actively iterating on:

better citation UI + chunk highlighting inside PDFs
deeper analytics (author networks, method clustering)
evaluation with real research workflows (time saved, quality of related work, confidence)
better “study design” assistance with constraints and templates

If you’re curious, the project lives here:

GitHub: https://github.com/GTamilSelvan07/HCI-Agent

Images I’d Love to Add (If You Want to Share)

If you send me 2–4 images, I’ll wire them into the post immediately:

Streamlit UI screenshot (chat + citations)
Analytics tab screenshot
Ingestion pipeline diagram or a terminal screenshot with ingestion stats
A candid photo that fits the story (you at the lab / your notebook / your setup)

Drop them into public/images/blog/hci-llm/ as:

hero.png
ui-chat.png
ui-analytics.png
pipeline.png

HCI‑LLM: Building a Local Research Assistant for 8,000+ CHI Papers