Papers with š¯’±-usable information analysis
Exploiting Contextual Knowledge in LLMs through š¯’±-usable Information based Layer Enhancement (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to enhance the context-faithfulness of Large Language Models (LLMs) ignore the fundamental mechanism of how contextual information is processed within LLMsā€™ internal states. |
| Approach: | They propose a method that enhances the utilization of contextual knowledge within LLMsā€™ internal representations by employing V-usable information analysis. |
| Outcome: | The proposed method improves context-faithfulness generation in Question-Answering tasks, particularly in scenarios involving unknown or conflicting contextual knowledge. |