# Semi-supervised Instruction Tuning for Large Language Models on Text-Attributed Graphs

arXiv: https://arxiv.org/abs/2601.12807 · HTML: https://mlsanity.com/paper/2601.12807/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 19 Jan 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 9 of 9)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [LLaGA: Large Language and Graph Assistant](https://mlsanity.com/paper/2402.08170/) (2024)
- [A Survey on Data Selection for LLM Instruction Tuning](https://mlsanity.com/paper/2402.05123/) (2024)
- [InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment](https://mlsanity.com/paper/2402.08785/) (2024)
- [GLBench: A Comprehensive Benchmark for Graph with Large Language Models](https://mlsanity.com/paper/2407.07457/) (2024)
- [Graph-oriented Instruction Tuning of Large Language Models for Generic Graph Mining](https://mlsanity.com/paper/2403.04780/) (2024)
- [BNEM: A Boltzmann Sampler Based on Bootstrapped Noised Energy Matching](https://mlsanity.com/paper/2409.09787/) (2024)
- [Beyond Human Data: Aligning Multimodal Large Language Models by Iterative Self-Evolution](https://mlsanity.com/paper/2412.15650/) (2024)
- [Semi-supervised Fine-tuning for Large Language Models](https://mlsanity.com/paper/2410.14745/) (2024)

## Abstract (arXiv)

The emergent reasoning capabilities of Large Language Models (LLMs) offer a transformative paradigm for analyzing text-attributed graphs. While instruction tuning is the prevailing method for adapting pre-trained LLMs to graph learning tasks like node classification, it requires a substantial volume of annotated (INSTRUCTION, OUTPUT) pairs deriving from labeled nodes. This requirement is particularly prohibitive in the social domain, where obtaining expert labels for sensitive or evolving content is costly and slow. Furthermore, standard graph instruction tuning fails to exploit the vast amount of unlabeled nodes, which contain latent correlations due to edge connections that are beneficial for downstream predictions. To bridge this gap, we propose a novel Semi-supervised Instruction Tuning pipeline for Graph Learning, named SIT-Graph. Notably, SIT-Graph is model-agnostic and can be seamlessly integrated into any graph instruction tuning method that utilizes LLMs as the predictor. SIT-Graph operates via an iterative self-training process. Initially, the model is fine-tuned using instruction pairs constructed solely from the labeled nodes. Then it generates confidence-filtered pseudo-responses for unlabeled nodes to strategically augment the dataset for the next round of fine-tuning. Finally, this iterative refinement progressively aligns the LLM with the underlying node correlations. Extensive experiments demonstrate that when incorporated into state-of-the-art graph instruction tuning methods, SIT-Graph significantly enhances their performance on text-attributed graph benchmarks, achieving over 20% improvement under the low label ratio settings.