Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers? (2025.coling-main)
Copied to clipboard
Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang
| Challenge: | Large language models have shown remarkable performances across a wide range of tasks, but mechanisms by which they encode tasks of varying complexity remain poorly understood. |
| Approach: | They propose to explore the possibility that LLMs process concepts in different layers . they propose to categorize concepts based on their level of abstraction . |
| Outcome: | The proposed model can process complex concepts in shallow layers, the authors show . the proposed model could be used to prob complex tasks in shallow ones . |
Similar Papers
How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies have focused on enhancing the factualness of large language models using context knowledge. |
| Approach: | They propose to use ChatGPT to construct probing datasets that provide diverse and coherent evidence corresponding to various facts. |
| Outcome: | The proposed model can encode knowledge across different layers, and it is compared with existing models. |
Towards Concept-Aware Large Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Concepts play a pivotal role in various human cognitive functions, including reasoning and communication. |
| Approach: | They analyze how well contemporary large language models capture human concepts and their structure . they propose a method for pretraining LLMs using concepts and a simpler approach . |
| Outcome: | The proposed method matches human intuition and improves robustness of predictions. |
Explaining Language Model Predictions with High-Impact Concepts (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods to explain large language models (LLMs) are mostly correlational and lack causal features due to compositional nature of languages. |
| Approach: | They propose a framework to provide impact-aware explanations for large language models that are robust to feature changes and influential to the model’s predictions. |
| Outcome: | The proposed explanations improve on real and synthetic tasks and are robust to feature changes and influential to the model’s predictions. |
Conceptual Hierarchies within LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing literature has explored abstraction within large language models (LLMs). |
| Approach: | They generate a dataset of semantic hierarchies and investigate their storage locations in six LLMs using activation patching, a causal intervention technique. |
| Outcome: | The results show that concepts at finer levels of granularity are stored around 61-78% of the time before those at coarser levels. |
Knowledge Boundary of Large Language Models: A Survey (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) store vast amount of knowledge in their parameters, but they still have limitations in the memorization and utilization of certain knowledge. |
| Approach: | They propose a comprehensive definition of the LLM knowledge boundary and introduce a formalized taxonomy categorizing knowledge into four distinct types. |
| Outcome: | The proposed definition of the LLM knowledge boundary and taxonomy categorizes knowledge into four distinct types . aims to offer a comprehensive overview, facilitate access to key issues, and inspire further advancements in LLM research. |
Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth (2025.emnlp-main)
Copied to clipboard
| Challenge: | Despite excelling at many natural language processing tasks, large language models fail to grasp the layered semantics of Drivelological text. |
| Approach: | They construct a benchmark dataset of over 1,200+ carefully curated and diverse examples across English, Mandarin, Spanish, French, Japanese, and Korean to examine their Drivelological characteristics. |
| Outcome: | The proposed models lack conceptual understanding and lack conceptual and semantic accuracy. |
How Programming Concepts and Neurons Are Shared in Code Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Several studies have focused on programming languages in a monolingual setting, but most focus on programming language models. |
| Approach: | They perform a few-shot translation task on 21 PL pairs using two Llama-based models and decode the embeddings of intermediate layers. |
| Outcome: | The proposed model assigns high probability to English tokens in the second half of the intermediate layers and language-specific neurons are concentrated in the bottom layers . the model's concept space is closer to English (including PL keywords) and the model is more efficient at identifying language-related neurons. |
Layer by Layer: Uncovering Where Multi-Task Learning Happens in Instruction-Tuned Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained large language models retain task-specific knowledge, but where and to what extent they retain it remains unexplored. |
| Approach: | They investigate the task-specific information encoded in pre-trained LLMs and the effects of instruction tuning on their representations across over 60 NLP tasks. |
| Outcome: | The results show that pre-trained models retain task-specific knowledge . some tasks are already encoded in pre-train models, but others benefit from instruction tuning. |
Do Large Language Models Know How Much They Know? (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models are highly capable systems, but their capabilities and limitations are unclear. |
| Approach: | They develop a benchmark that challenges LLMs to recall all information they possess on specific topics. |
| Outcome: | The proposed model can recall excessive, insufficient, or the precise amount of information they possess on a given topic, indicating their awareness of how much they know about the given topic. |
Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages (2025.naacl-long)
Copied to clipboard
| Challenge: | In the brains of human bilinguals, syntax processing may occur in similar regions for their first and second language, depending on factors like when the second language was learned and language proficiency. |
| Approach: | They propose to use sparse autoencoders to train Llama-3-8B and Aya-23-8B models to train multilingual models that share morphsyntactic representations of grammatical concepts. |
| Outcome: | The proposed model can predict plural verbs in different languages by activating the same plural feature. |