Context-faithful Prompting for Large Language Models

2023/03/20 by Wenxuan Zhou, Sheng Zhang, Zhou, Wenxuan +5 · 8 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2303.11315

openalex publication_date 2023/03/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Large language models (LLMs) encode parametric knowledge about world facts and have shown remarkable performance in knowledge-driven NLP tasks. However, their reliance on parametric knowledge may cause them to overlook contextual cues, leading to incorrect predictions in context-sensitive NLP tasks (e.g., knowledge acquisition tasks). In this paper, we seek to assess and enhance LLMs' contextual faithfulness in two aspects: knowledge conflict and prediction with abstention. We demonstrate that LLMs' faithfulness can be significantly improved using carefully designed prompting strategies. In particular, we identify opinion-based prompts and counterfactual demonstrations as the most effective methods. Opinion-based prompts reframe the context as a narrator's statement and inquire about the narrator's opinions, while counterfactual demonstrations use instances containing false facts to improve faithfulness in knowledge conflict situations. Neither technique requires additional training. We conduct experiments on three datasets of two standard NLP tasks, machine reading comprehension and relation extraction, and the results demonstrate significant improvement in faithfulness to contexts. Code and data are released at https://github.com/wzhouad/context-faithful-llm.

Cited by

• Autonomous Construction-Site Safety Inspection Using Mobile Robots: A Multilayer VLM-LLM Pipeline
• Epidemiology of Large Language Models: A Benchmark for Observational Distribution Knowledge
• Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models
• Mitigating Modal Imbalance in Multimodal Reasoning
• COSTAR-A: A prompting framework for enhancing Large Language Model performance on Point-of-View questions
• Copy-Paste to Mitigate Large Language Model Hallucinations
• SSFO: Self-Supervised Faithfulness Optimization for Retrieval-Augmented Generation
• Vibe Check: Understanding the Effects of LLM-Based Conversational Agents' Personality and Alignment on User Perceptions in Goal-Oriented Tasks

Related

• FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation
• Do Large Language Models Understand Logic or Just Mimick Context?
• Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering
• Supervised Knowledge Makes Large Language Models Better In-context Learners
• When Context Leads but Parametric Memory Follows in Large Language Models