A survey of LLM alignment: Instruction understanding, intention reasoning, and reliable dialogue generation

Large language models have demonstrated exceptional capabilities in understanding and generation. However, in real-world scenarios, users’ natural language expressions are often inherently fuzzy, ambiguous, and uncertain, leading to challenges such as vagueness, polysemy, and contextual ambiguity. This paper focuses on three challenges in LLM-based text generation tasks: instruction understanding, intention reasoning, and reliable dialogue generation. Regarding complex human instructions, LLMs have deficiencies in understanding long contexts and instructions in multi-round conversations. For intention reasoning, LLMs may exhibit inconsistent command reasoning, difficulty reasoning about commands containing incorrect information, difficulty understanding user ambiguous language commands, and a weak understanding of user intentions in commands. Besides, in terms of reliable dialogue generation, LLMs may produce unstable generated content and unethical outputs. To this end, we classify and analyze the performance of LLMs in challenging scenarios and conduct a comprehensive evaluation of existing solutions. Furthermore, we introduce benchmarks and categorize them based on the aforementioned three core challenges. Finally, we explore potential directions for future research to enhance the reliability and adaptability of LLMs in real-world applications.