# Unify Graph Learning with Text: Unleashing LLM Potentials for Session Search

arXiv: https://arxiv.org/abs/2505.14156 · HTML: https://mlsanity.com/paper/2505.14156/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 57 references that are in the map.
- First posted on arXiv 20 May 2025.

## Builds on (most cited first, 30 of 31)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Link Prediction Based on Graph Neural Networks](https://mlsanity.com/paper/1802.09691/) (2018)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training](https://mlsanity.com/paper/2006.09963/) (2020)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [Document Ranking with a Pretrained Sequence-to-Sequence Model](https://mlsanity.com/paper/2003.06713/) (2020)
- [Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents](https://mlsanity.com/paper/2304.09542/) (2023)
- [Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting](https://mlsanity.com/paper/2306.17563/) (2023)
- [GPT-GNN: Generative Pre-Training of Graph Neural Networks](https://mlsanity.com/paper/2006.15437/) (2020)
- [Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Health](https://mlsanity.com/paper/2306.10070/) (2023)
- [mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset](https://mlsanity.com/paper/2108.13897/) (2021)
- [Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum](https://mlsanity.com/paper/2308.14034/) (2023)
- [Pytrec_eval: An Extremely Fast Python Interface to trec_eval](https://mlsanity.com/paper/1805.01597/) (2018)
- [Exploring Large Language Model for Graph Data Understanding in Online Job Recommendations](https://mlsanity.com/paper/2307.05722/) (2023)
- [Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications](https://mlsanity.com/paper/2306.02592/) (2023)
- [Adaptive Transfer Learning on Graph Neural Networks](https://mlsanity.com/paper/2107.08765/) (2021)
- [Target-aware Abstractive Related Work Generation with Contrastive Learning](https://mlsanity.com/paper/2205.13339/) (2022)
- [Contrastive Learning of User Behavior Sequence for Context-Aware Document Ranking](https://mlsanity.com/paper/2108.10510/) (2021)
- [Context Attentive Document Ranking and Query Suggestion](https://mlsanity.com/paper/1906.02329/) (2019)
- [Neural IR Meets Graph Embedding: A Ranking Model for Product Search](https://mlsanity.com/paper/1901.08286/) (2019)
- [Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks](https://mlsanity.com/paper/2105.10323/) (2021)
- [Enhancing User Behavior Sequence Modeling by Generative Tasks for Session Search](https://mlsanity.com/paper/2208.10846/) (2022)
- [Scientific Paper Extractive Summarization Enhanced by Citation Graphs](https://mlsanity.com/paper/2212.04214/) (2022)

## Built on by (most cited first, 3 of 3)

- [A Scalable and Efficient Signal Integration System for Job Matching](https://mlsanity.com/paper/2507.09797/) (2025)
- [CogGuard: Cognitive and Operational Profiling for Proactive Warning in Edge Intelligent Services](https://mlsanity.com/paper/2606.15199/) (2026)
- [GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMs](https://mlsanity.com/paper/2609.12265/) (2026)

## Abstract (arXiv)

Session search involves a series of interactive queries and actions to fulfill user's complex information need. Current strategies typically prioritize sequential modeling for deep semantic understanding, overlooking the graph structure in interactions. While some approaches focus on capturing structural information, they use a generalized representation for documents, neglecting the word-level semantic modeling. In this paper, we propose Symbolic Graph Ranker (SGR), which aims to take advantage of both text-based and graph-based approaches by leveraging the power of recent Large Language Models (LLMs). Concretely, we first introduce a set of symbolic grammar rules to convert session graph into text. This allows integrating session history, interaction process, and task instruction seamlessly as inputs for the LLM. Moreover, given the natural discrepancy between LLMs pre-trained on textual corpora, and the symbolic language we produce using our graph-to-text grammar, our objective is to enhance LLMs' ability to capture graph structures within a textual format. To achieve this, we introduce a set of self-supervised symbolic learning tasks including link prediction, node content generation, and generative contrastive learning, to enable LLMs to capture the topological information from coarse-grained to fine-grained. Experiment results and comprehensive analysis on two benchmark datasets, AOL and Tiangong-ST, confirm the superiority of our approach. Our paradigm also offers a novel and effective methodology that bridges the gap between traditional search strategies and modern LLMs.