# Factors That Support Grounded Responses in LLM Conversations: A Rapid Review

arXiv: https://arxiv.org/abs/2511.21762 · HTML: https://mlsanity.com/paper/2511.21762/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Builds on (most cited first, 23 of 23)

- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [RRHF: Rank Responses to Align Language Models with Human Feedback without tears](https://mlsanity.com/paper/2304.05302/) (2023)
- [The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning](https://mlsanity.com/paper/2312.01552/) (2023)
- [Large Language Model Alignment: A Survey](https://mlsanity.com/paper/2309.15025/) (2023)
- [Nash Learning from Human Feedback](https://mlsanity.com/paper/2312.00886/) (2023)
- [Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning](https://mlsanity.com/paper/2302.02662/) (2023)
- [Mitigating the Alignment Tax of RLHF](https://mlsanity.com/paper/2309.06256/) (2023)
- [RAIN: Your Language Models Can Align Themselves without Finetuning](https://mlsanity.com/paper/2309.07124/) (2023)
- [LLM Post-Training: A Deep Dive into Reasoning Large Language Models](https://mlsanity.com/paper/2502.21321/) (2025)
- [ARGS: Alignment as Reward-Guided Search](https://mlsanity.com/paper/2402.01694/) (2024)
- [Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation](https://mlsanity.com/paper/2402.09267/) (2024)
- [Reinforcement Learning Enhanced LLMs: A Survey](https://mlsanity.com/paper/2412.10400/) (2024)
- [SALMON: Self-Alignment with Instructable Reward Models](https://mlsanity.com/paper/2310.05910/) (2023)
- [RS-DPO: A Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language Models](https://mlsanity.com/paper/2402.10038/) (2024)
- [Can LLM Graph Reasoning Generalize beyond Pattern Memorization?](https://mlsanity.com/paper/2406.15992/) (2024)
- [CodecLM: Aligning Language Models with Tailored Synthetic Data](https://mlsanity.com/paper/2404.05875/) (2024)
- [Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment](https://mlsanity.com/paper/2311.04072/) (2023)
- [Improving Generalization of Alignment with Human Preferences through Group Invariant Learning](https://mlsanity.com/paper/2310.11971/) (2023)
- [Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback](https://mlsanity.com/paper/2401.11458/) (2024)
- [Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation](https://mlsanity.com/paper/2402.11907/) (2024)
- [Unsupervised Large Language Model Alignment for Information Retrieval via Contrastive Feedback](https://mlsanity.com/paper/2309.17078/) (2023)
- [Automatic Pair Construction for Contrastive Post-training](https://mlsanity.com/paper/2310.02263/) (2023)
- [Hybrid Alignment Training for Large Language Models](https://mlsanity.com/paper/2406.15178/) (2024)

## Abstract (arXiv)

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.