# Grounding Gaps in Language Model Generations

arXiv: https://arxiv.org/abs/2311.09144 · HTML: https://mlsanity.com/paper/2311.09144/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 99 references that are in the map.
- First posted on arXiv 15 Nov 2023.

## Builds on (most cited first, 30 of 37)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [Social Simulacra: Creating Populated Prototypes for Social Computing Systems](https://mlsanity.com/paper/2208.04024/) (2022)
- [Towards Emotional Support Dialog Systems](https://mlsanity.com/paper/2106.01144/) (2021)
- [Understanding Dataset Difficulty with V-Usable Information](https://mlsanity.com/paper/2110.08420/) (2021)
- [A Long Way to Go: Investigating Length Correlations in RLHF](https://mlsanity.com/paper/2310.03716/) (2023)
- [Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good](https://mlsanity.com/paper/1906.06725/) (2019)
- [Eliciting Human Preferences with Language Models](https://mlsanity.com/paper/2310.11589/) (2023)
- [MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Tasks](https://mlsanity.com/paper/2109.06275/) (2021)
- [Rehearsal: Simulating Conflict to Teach Conflict Resolution](https://mlsanity.com/paper/2309.12309/) (2023)
- [Grounding 'Grounding' in NLP](https://mlsanity.com/paper/2106.02192/) (2021)
- [Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations](https://mlsanity.com/paper/2311.05584/) (2023)
- [Is ChatGPT a Good Teacher Coach? Measuring Zero-Shot Performance For Scoring and Providing Actionable Insights on Classroom Instruction](https://mlsanity.com/paper/2306.03090/) (2023)
- [Decision-Oriented Dialogue for Human-AI Collaboration](https://mlsanity.com/paper/2305.20076/) (2023)
- [A Survey on Asking Clarification Questions Datasets in Conversational Systems](https://mlsanity.com/paper/2305.15933/) (2023)
- [Grounding Conversations with Improvised Dialogues](https://mlsanity.com/paper/2004.09544/) (2020)
- [Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction](https://mlsanity.com/paper/2011.13137/) (2020)

## Built on by (most cited first, 30 of 47)

- [A Computational Framework for Behavioral Assessment of LLM Therapists](https://mlsanity.com/paper/2401.00820/) (2024)
- [Creating General User Models from Computer Use](https://mlsanity.com/paper/2505.10831/) (2025)
- [Navigating Rifts in Human-LLM Grounding: Study and Benchmark](https://mlsanity.com/paper/2503.13975/) (2025)
- [Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMs](https://mlsanity.com/paper/2408.01417/) (2024)
- [Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectification](https://mlsanity.com/paper/2510.11408/) (2025)
- [Taxonomy of User Needs and Actions](https://mlsanity.com/paper/2510.06124/) (2025)
- [Don't lie to your friends: Learning what you know from collaborative self-play](https://mlsanity.com/paper/2503.14481/) (2025)
- [Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful Beliefs](https://mlsanity.com/paper/2601.04435/) (2026)
- [MACAROON: Training Vision-Language Models To Be Your Engaged Partners](https://mlsanity.com/paper/2406.14137/) (2024)
- [Can LLMs Ground when they (Don't) Know: A Study on Direct and Loaded Political Questions](https://mlsanity.com/paper/2506.08952/) (2025)
- [RAcQUEt: Unveiling the Dangers of Overlooked Referential Ambiguity in Visual LLMs](https://mlsanity.com/paper/2412.13835/) (2024)
- [MT-PingEval: Evaluating Multi-Turn Collaboration with Private Information Games](https://mlsanity.com/paper/2602.24188/) (2026)
- [SWAY: A Counterfactual Computational Linguistic Approach to Measuring and Mitigating Sycophancy](https://mlsanity.com/paper/2604.02423/) (2026)
- [Just-In-Time Objectives: A General Approach for Specialized AI Interactions](https://mlsanity.com/paper/2510.14591/) (2025)
- [The Behavior Gap: Evaluating Zero-shot LLM Agents in Complex Task-Oriented Dialogs](https://mlsanity.com/paper/2506.12266/) (2025)
- [Retrieval-augmented systems can be dangerous medical communicators](https://mlsanity.com/paper/2502.14898/) (2025)
- [Query Understanding in LLM-based Conversational Information Seeking](https://mlsanity.com/paper/2504.06356/) (2025)
- [Plantain: Plan-Answer Interleaved Reasoning](https://mlsanity.com/paper/2512.03176/) (2025)
- [Learning Steerable Clarification Policies with Collaborative Self-play](https://mlsanity.com/paper/2512.04068/) (2025)
- [Taking Action Towards Graceful Interaction: The Effects of Performing Actions on Modelling Policies for Instruction Clarification Requests](https://mlsanity.com/paper/2401.17039/) (2024)
- [Understanding Common Ground Misalignment in Goal-Oriented Dialog: A Case-Study with Ubuntu Chat Logs](https://mlsanity.com/paper/2503.12370/) (2025)
- [Promoting Constructive Deliberation: Reframing for Receptiveness](https://mlsanity.com/paper/2405.15067/) (2024)
- [A Study on Leveraging Search and Self-Feedback for Agent Reasoning](https://mlsanity.com/paper/2502.12094/) (2025)
- [Semantic Commit: Helping Users Update Intent Specifications for AI Memory at Scale](https://mlsanity.com/paper/2504.09283/) (2025)
- [Characterizing Language Use in a Collaborative Situated Game](https://mlsanity.com/paper/2512.03381/) (2025)
- [NewsInterview: a Dataset and a Playground to Evaluate LLMs' Ground Gap via Informational Interviews](https://mlsanity.com/paper/2411.13779/) (2024)
- [Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations](https://mlsanity.com/paper/2510.12699/) (2025)
- [Reference Games as a Testbed for the Alignment of Model Uncertainty and Clarification Requests](https://mlsanity.com/paper/2601.07820/) (2026)
- [TEA-Bench: A Systematic Benchmarking of Tool-enhanced Emotional Support Dialogue Agent](https://mlsanity.com/paper/2601.18700/) (2026)
- [Reflections and New Directions for Human-Centered Large Language Models](https://mlsanity.com/paper/2605.06901/) (2026)

## Abstract (arXiv)

Effective conversation requires common ground: a shared understanding between the participants. Common ground, however, does not emerge spontaneously in conversation. Speakers and listeners work together to both identify and construct a shared basis while avoiding misunderstanding. To accomplish grounding, humans rely on a range of dialogue acts, like clarification (What do you mean?) and acknowledgment (I understand.). However, it is unclear whether large language models (LLMs) generate text that reflects human grounding. To this end, we curate a set of grounding acts and propose corresponding metrics that quantify attempted grounding. We study whether LLM generations contain grounding acts, simulating turn-taking from several dialogue datasets and comparing results to humans. We find that -- compared to humans -- LLMs generate language with less conversational grounding, instead generating text that appears to simply presume common ground. To understand the roots of the identified grounding gap, we examine the role of instruction tuning and preference optimization, finding that training on contemporary preference data leads to a reduction in generated grounding acts. Altogether, we highlight the need for more research investigating conversational grounding in human-AI interaction.