Factors That Support Grounded Responses in LLM Conversations: A Rapid Review
This work addresses reliability issues in LLM-based applications by synthesizing alignment strategies, though it is incremental as a review of existing methods.
The paper reviewed techniques to improve LLM conversations by aligning responses with user intent, ensuring grounding, and reducing hallucinations, identifying inference-time approaches as particularly efficient for these goals without retraining.
Large language models (LLMs) may generate outputs that are misaligned with user intent, lack contextual grounding, or exhibit hallucinations during conversation, which compromises the reliability of LLM-based applications. This review aimed to identify and analyze techniques that align LLM responses with conversational goals, ensure grounding, and reduce hallucination and topic drift. We conducted a Rapid Review guided by the PRISMA framework and the PICO strategy to structure the search, filtering, and selection processes. The alignment strategies identified were categorized according to the LLM lifecycle phase in which they operate: inference-time, post-training, and reinforcement learning-based methods. Among these, inference-time approaches emerged as particularly efficient, aligning outputs without retraining while supporting user intent, contextual grounding, and hallucination mitigation. The reviewed techniques provided structured mechanisms for improving the quality and reliability of LLM responses across key alignment objectives.