# LLM as Attention-Informed NTM and Topic Modeling as long-input Generation: Interpretability and long-Context Capability

arXiv: https://arxiv.org/abs/2510.03174 · HTML: https://mlsanity.com/paper/2510.03174/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 3 Oct 2025.

## Builds on (most cited first, 22 of 22)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023)
- [Topic Modeling in Embedding Spaces](https://mlsanity.com/paper/1907.04907/) (2019)
- [Autoencoding Variational Inference For Topic Models](https://mlsanity.com/paper/1703.01488/) (2017)
- [Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence](https://mlsanity.com/paper/2004.03974/) (2020)
- [Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooM](https://mlsanity.com/paper/2404.12259/) (2024)
- [Neural Topic Model via Optimal Transport](https://mlsanity.com/paper/2008.13537/) (2020)
- [Effective Neural Topic Modeling with Embedding Clustering Regularization](https://mlsanity.com/paper/2306.04217/) (2023)
- [Mitigating Data Sparsity for Short Text Topic Modeling by Topic-Semantic Contrastive Learning](https://mlsanity.com/paper/2211.12878/) (2022)
- [Large Language Models Offer an Alternative to the Traditional Approach of Topic Modelling](https://mlsanity.com/paper/2403.16248/) (2024)
- [FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Model](https://mlsanity.com/paper/2405.17978/) (2024)
- [CHIME: LLM-Assisted Hierarchical Organization of Scientific Studies for Literature Review Support](https://mlsanity.com/paper/2407.16148/) (2024)
- [Prompting Large Language Models for Topic Modeling](https://mlsanity.com/paper/2312.09693/) (2023)
- [Towards the TopMost: A Topic Modeling System Toolkit](https://mlsanity.com/paper/2309.06908/) (2023)
- [Bridging the Evaluation Gap: Leveraging Large Language Models for Topic Model Evaluation](https://mlsanity.com/paper/2502.07352/) (2025)
- [Retrieval Augmented Generation for Topic Modeling in Organizational Research: An Introduction with Empirical Demonstration](https://mlsanity.com/paper/2502.20963/) (2025)
- [Lost-in-the-Middle in Long-Text Generation: Synthetic Dataset, Evaluation Framework, and Mitigation](https://mlsanity.com/paper/2503.06868/) (2025)
- [Multi-Scale Manifold Alignment for Interpreting Large Language Models: A Unified Information-Geometric Framework](https://mlsanity.com/paper/2505.20333/) (2025)

## Abstract (arXiv)

Topic modeling aims to produce interpretable topic representations and topic--document correspondences from corpora, but classical neural topic models (NTMs) remain constrained by limited representation assumptions and semantic abstraction ability. We study LLM-based topic modeling from both white-box and black-box perspectives. For white-box LLMs, we propose an attention-informed framework that recovers interpretable structures analogous to those in NTMs, including document-topic and topic-word distributions. This validates the view that LLM can serve as an attention-informed NTM. For black-box LLMs, we reformulate topic modeling as a structured long-input task and introduce a post-generation signal compensation method based on diversified topic cues and hybrid retrieval. Experiments show that recovered attention structures support effective topic assignment and keyword extraction, while black-box long-context LLMs achieve competitive or stronger performance than other baselines. These findings suggest a connection between LLMs and NTMs and highlight the promise of long-context LLMs for topic modeling.