# AHAM: Adapt, Help, Ask, Model -- Harvesting LLMs for literature mining

arXiv: https://arxiv.org/abs/2312.15784 · HTML: https://mlsanity.com/paper/2312.15784/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 27 references that are in the map.
- First posted on arXiv 25 Dec 2023.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://mlsanity.com/paper/2004.09813/) (2020)
- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [Can language models learn from explanations in context?](https://mlsanity.com/paper/2204.02329/) (2022)
- [SciMON: Scientific Inspiration Machines Optimized for Novelty](https://mlsanity.com/paper/2305.14259/) (2023)
- [What In-Context Learning "Learns" In-Context: Disentangling Task Recognition and Task Learning](https://mlsanity.com/paper/2305.09731/) (2023)
- [Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation](https://mlsanity.com/paper/2010.02666/) (2020)
- [GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval](https://mlsanity.com/paper/2112.07577/) (2021)
- [TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning](https://mlsanity.com/paper/2104.06979/) (2021)
- [Out of Thin Air: Is Zero-Shot Cross-Lingual Keyword Detection Better Than Unsupervised?](https://mlsanity.com/paper/2202.06650/) (2022)
- [Scientometric analysis and knowledge mapping of literature-based discovery (1986-2020)](https://mlsanity.com/paper/2006.08486/) (2020)
- [Retrieval-efficiency trade-off of Unsupervised Keyword Extraction](https://mlsanity.com/paper/2208.07262/) (2022)

## Built on by (most cited first, 5 of 5)

- [LimTopic: LLM-based Topic Modeling and Text Summarization for Analyzing Scientific Articles limitations](https://mlsanity.com/paper/2503.10658/) (2025)
- [Evaluating and explaining training strategies for zero-shot cross-lingual news sentiment analysis](https://mlsanity.com/paper/2409.20054/) (2024)
- [LLM-Assisted Topic Reduction for BERTopic on Social Media Data](https://mlsanity.com/paper/2509.19365/) (2025)
- [Make Literature-Based Discovery Great Again through Reproducible Pipelines](https://mlsanity.com/paper/2502.16450/) (2025)
- [HAMLET: Healthcare-focused Adaptive Multilingual Learning Embedding-based Topic Modeling](https://mlsanity.com/paper/2505.07157/) (2025)

## Abstract (arXiv)

In an era marked by a rapid increase in scientific publications, researchers grapple with the challenge of keeping pace with field-specific advances. We present the `AHAM' methodology and a metric that guides the domain-specific adaptation of the BERTopic topic modeling framework to improve scientific text analysis. By utilizing the LLaMa2 generative language model, we generate topic definitions via one-shot learning by crafting prompts with the help of domain experts to guide the LLM for literature mining by asking it to model the topic names. For inter-topic similarity evaluation, we leverage metrics from language generation and translation processes to assess lexical and semantic similarity of the generated topics. Our system aims to reduce both the ratio of outlier topics to the total number of topics and the similarity between topic definitions. The methodology has been assessed on a newly gathered corpus of scientific papers on literature-based discovery. Through rigorous evaluation by domain experts, AHAM has been validated as effective in uncovering intriguing and novel insights within broad research areas. We explore the impact of domain adaptation of sentence-transformers for the task of topic modeling using two datasets, each specialized to specific scientific domains within arXiv and medarxiv. We evaluate the impact of data size, the niche of adaptation, and the importance of domain adaptation. Our results suggest a strong interaction between domain adaptation and topic modeling precision in terms of outliers and topic definitions.