How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study

• URL: http://arxiv.org/abs/2402.16061v2
• Date: Mon, 4 Mar 2024 13:37:48 GMT
• Title: How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study
• Authors: Tianjie Ju, Weiwei Sun, Wei Du, Xinwei Yuan, Zhaochun Ren, Gongshen Liu
• Abstract summary: This paper investigates the layer-wise capability of large language models to encode knowledge. We leverage the powerful generative capability of ChatGPT to construct probing datasets. Experiments on conflicting and newly acquired knowledge show that LLMs prefer to encode more context knowledge in the upper layers.
• Score: 27.23388511249688
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Previous work has showcased the intriguing capability of large language models (LLMs) in retrieving facts and processing context knowledge. However, only limited research exists on the layer-wise capability of LLMs to encode knowledge, which challenges our understanding of their internal mechanisms. In this paper, we devote the first attempt to investigate the layer-wise capability of LLMs through probing tasks. We leverage the powerful generative capability of ChatGPT to construct probing datasets, providing diverse and coherent evidence corresponding to various facts. We employ $\mathcal V$-usable information as the validation metric to better reflect the capability in encoding context knowledge across different layers. Our experiments on conflicting and newly acquired knowledge show that LLMs: (1) prefer to encode more context knowledge in the upper layers; (2) primarily encode context knowledge within knowledge-related entity tokens at lower layers while progressively expanding more knowledge within other tokens at upper layers; and (3) gradually forget the earlier context knowledge retained within the intermediate layers when provided with irrelevant evidence. Code is publicly available at https://github.com/Jometeorie/probing_llama.

Related papers

• Looking into Black Box Code Language Models [2.5324062203985935]
  We use two state-of-the-art codeLMs, Codegen-Mono and Ploycoder, and three widely used programming languages, Java, Go, and Python. We show concepts of interest can be edited within feed-forward layers without compromising codeLM performance.
  arXiv  Detail & Related papers  (2024-07-05T21:13:41Z)
• Knowledge Graph-Enhanced Large Language Models via Path Selection [58.228392005755026]
  Large Language Models (LLMs) have shown unprecedented performance in various real-world applications. LLMs are known to generate factually inaccurate outputs, a.k.a. the hallucination problem. We propose a principled framework KELP with three stages to handle the above problems.
  arXiv  Detail & Related papers  (2024-06-19T21:45:20Z)
• Prompting Large Language Models with Knowledge Graphs for Question Answering Involving Long-tail Facts [50.06633829833144]
  Large Language Models (LLMs) are effective in performing various NLP tasks, but struggle to handle tasks that require extensive, real-world knowledge. We propose a benchmark that requires knowledge of long-tail facts for answering the involved questions. Our experiments show that LLMs alone struggle with answering these questions, especially when the long-tail level is high or rich knowledge is required.
  arXiv  Detail & Related papers  (2024-05-10T15:10:20Z)
• Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding [9.2433070542025]
  Large language models (LLMs) tend to inadequately integrate input context during text generation. We introduce a novel approach integrating contrastive decoding with adversarial irrelevant passages as negative samples.
  arXiv  Detail & Related papers  (2024-05-04T20:38:41Z)
• Robust and Scalable Model Editing for Large Language Models [75.95623066605259]
  We propose EREN (Edit models by REading Notes) to improve the scalability and robustness of LLM editing. Unlike existing techniques, it can integrate knowledge from multiple edits, and correctly respond to syntactically similar but semantically unrelated inputs.
  arXiv  Detail & Related papers  (2024-03-26T06:57:23Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)
• DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models [79.01926242857613]
  Large language models (LLMs) are prone to hallucinations, generating content that deviates from facts seen during pretraining. We propose a simple decoding strategy for reducing hallucinations with pretrained LLMs. We find that this Decoding by Contrasting Layers (DoLa) approach is able to better surface factual knowledge and reduce the generation of incorrect facts.
  arXiv  Detail & Related papers  (2023-09-07T17:45:31Z)
• Knowledge Solver: Teaching LLMs to Search for Domain Knowledge from Knowledge Graphs [19.0797968186656]
  Large language models (LLMs) are versatile and can solve different tasks due to their emergent ability and generalizability. In some previous works, additional modules like graph neural networks (GNNs) are trained on retrieved knowledge from external knowledge bases.
  arXiv  Detail & Related papers  (2023-09-06T15:55:01Z)
• TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledge [83.55215993730326]
  We propose augmenting TExt Generation via Task-specific and Open-world Knowledge (TegTok) in a unified framework. Our model selects knowledge entries from two types of knowledge sources through dense retrieval and then injects them into the input encoding and output decoding stages respectively.
  arXiv  Detail & Related papers  (2022-03-16T10:37:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.