# Can an LLM Induce a Graph? Investigating Memory Drift and Context Length

arXiv: https://arxiv.org/abs/2510.03611 · HTML: https://mlsanity.com/paper/2510.03611/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 49 references that are in the map.
- First posted on arXiv 4 Oct 2025.

## Builds on (most cited first, 30 of 34)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models](https://mlsanity.com/paper/2304.09842/) (2023)
- [Long-context LLMs Struggle with Long In-context Learning](https://mlsanity.com/paper/2404.02060/) (2024)
- [Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models](https://mlsanity.com/paper/2402.14848/) (2024)
- [Training Language Models with Memory Augmentation](https://mlsanity.com/paper/2205.12674/) (2022)
- [Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion](https://mlsanity.com/paper/2203.13224/) (2022)
- [Graph-ToolFormer: To Empower LLMs with Graph Reasoning Ability via Prompt Augmented by ChatGPT](https://mlsanity.com/paper/2304.11116/) (2023)
- [One Thousand and One Pairs: A "novel" challenge for long-context language models](https://mlsanity.com/paper/2406.16264/) (2024)
- [Self-Knowledge Guided Retrieval Augmentation for Large Language Models](https://mlsanity.com/paper/2310.05002/) (2023)
- [DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing](https://mlsanity.com/paper/2410.12189/) (2024)
- [LLMAEL: Large Language Models are Good Context Augmenters for Entity Linking](https://mlsanity.com/paper/2407.04020/) (2024)
- [Counting-Stars: A Multi-evidence, Position-aware, and Scalable Benchmark for Evaluating Long-Context Large Language Models](https://mlsanity.com/paper/2403.11802/) (2024)
- [Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding](https://mlsanity.com/paper/2410.01671/) (2024)
- [MedOdyssey: A Medical Domain Benchmark for Long Context Evaluation Up to 200K Tokens](https://mlsanity.com/paper/2406.15019/) (2024)
- [Forgetting Curve: A Reliable Method for Evaluating Memorization Capability for Long-context Models](https://mlsanity.com/paper/2410.04727/) (2024)
- [OneNet: A Fine-Tuning Free Framework for Few-Shot Entity Linking via Large Language Model Prompting](https://mlsanity.com/paper/2410.07549/) (2024)
- [LLM with Relation Classifier for Document-Level Relation Extraction](https://mlsanity.com/paper/2408.13889/) (2024)
- [Steering LLM Summarization with Visual Workspaces for Sensemaking](https://mlsanity.com/paper/2409.17289/) (2024)

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

- [Graph-based Agent Memory: Taxonomy, Techniques, and Applications](https://mlsanity.com/paper/2602.05665/) (2026)
- [Governing Evolving Memory in LLM Agents: Risks, Mechanisms, and the Stability and Safety Governed Memory (SSGM) Framework](https://mlsanity.com/paper/2603.11768/) (2026)
- [Fine-Tuning Small Language Models for Solution-Oriented Windows Event Log Analysis](https://mlsanity.com/paper/2605.06330/) (2026)

## Abstract (arXiv)

Recently proposed evaluation benchmarks aim to characterize the effective context length and the forgetting tendencies of large language models (LLMs). However, these benchmarks often rely on simplistic 'needle in a haystack' retrieval or continuation tasks that may not accurately reflect the performance of these models in information-dense scenarios. Thus, rather than simple next token prediction, we argue for evaluating these models on more complex reasoning tasks that requires them to induce structured relational knowledge from the text - such as graphs from potentially noisy natural language content. While the input text can be viewed as generated in terms of a graph, its structure is not made explicit and connections must be induced from distributed textual cues, separated by long contexts and interspersed with irrelevant information. Our findings reveal that LLMs begin to exhibit memory drift and contextual forgetting at much shorter effective lengths when tasked with this form of relational reasoning, compared to what existing benchmarks suggest. With these findings, we offer recommendations for the optimal use of popular LLMs for complex reasoning tasks. We further show that even models specialized for reasoning, such as OpenAI o1, remain vulnerable to early memory drift in these settings. These results point to significant limitations in the models' ability to abstract structured knowledge from unstructured input and highlight the need for architectural adaptations to improve long-range reasoning.