Navigating Rifts in Human-LLM Grounding: Study and Benchmark

• URL: http://arxiv.org/abs/2503.13975v1
• Date: Tue, 18 Mar 2025 07:24:05 GMT
• Title: Navigating Rifts in Human-LLM Grounding: Study and Benchmark
• Authors: Omar Shaikh, Hussein Mozannar, Gagan Bansal, Adam Fourney, Eric Horvitz,
• Abstract summary: We analyze logs from three human-assistant datasets: WildChat, MultiWOZ, and Bing Chat.<n>Our findings reveal significant differences in human-human and human-LLM grounding.
• Score: 30.579037010055092
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language models excel at following instructions but often struggle with the collaborative aspects of conversation that humans naturally employ. This limitation in grounding -- the process by which conversation participants establish mutual understanding -- can lead to outcomes ranging from frustrated users to serious consequences in high-stakes scenarios. To systematically study grounding challenges in human-LLM interactions, we analyze logs from three human-assistant datasets: WildChat, MultiWOZ, and Bing Chat. We develop a taxonomy of grounding acts and build models to annotate and forecast grounding behavior. Our findings reveal significant differences in human-human and human-LLM grounding: LLMs were three times less likely to initiate clarification and sixteen times less likely to provide follow-up requests than humans. Additionally, early grounding failures predicted later interaction breakdowns. Building on these insights, we introduce RIFTS: a benchmark derived from publicly available LLM interaction data containing situations where LLMs fail to initiate grounding. We note that current frontier models perform poorly on RIFTS, highlighting the need to reconsider how we train and prompt LLMs for human interaction. To this end, we develop a preliminary intervention that mitigates grounding failures.

Related papers

• If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs [55.8331366739144]
  We introduce LIFESTATE-BENCH, a benchmark designed to assess lifelong learning in large language models (LLMs) Our fact checking evaluation probes models' self-awareness, episodic memory retrieval, and relationship tracking, across both parametric and non-parametric approaches.
  arXiv  Detail & Related papers  (2025-03-30T16:50:57Z)
• NewsInterview: a Dataset and a Playground to Evaluate LLMs' Ground Gap via Informational Interviews [65.35458530702442]
  We focus on journalistic interviews, a domain rich in grounding communication and abundant in data. We curate a dataset of 40,000 two-person informational interviews from NPR and CNN. LLMs are significantly less likely than human interviewers to use acknowledgements and to pivot to higher-level questions.
  arXiv  Detail & Related papers  (2024-11-21T01:37:38Z)
• Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Dialogue [25.89926022671521]
  We generate a large-scale dataset of 100,000 paired LLM-LLM and human-LLM dialogues from the WildChat dataset. We find relatively low alignment between simulations and human interactions, demonstrating a systematic divergence along the multiple textual properties.
  arXiv  Detail & Related papers  (2024-09-12T18:00:18Z)
• Modulating Language Model Experiences through Frictions [56.17593192325438]
  Over-consumption of language model outputs risks propagating unchecked errors in the short-term and damaging human capabilities for critical thinking in the long-term. We propose selective frictions for language model experiences, inspired by behavioral science interventions, to dampen misuse.
  arXiv  Detail & Related papers  (2024-06-24T16:31:11Z)
• It Couldn't Help But Overhear: On the Limits of Modelling Meta-Communicative Grounding Acts with Supervised Learning [19.812562421377706]
  Overhearers are deprived of the privilege of performing grounding acts and can only conjecture about intended meanings. We show that there is evidence pointing to the impossibility of properly modelling human meta-communicative acts with data-driven learning models. Most importantly, we wish to bring this topic back to the community's table, encouraging discussion on the consequences of having models designed to only "listen in"
  arXiv  Detail & Related papers  (2024-05-02T09:55:19Z)
• Groundedness in Retrieval-augmented Long-form Generation: An Empirical Study [61.74571814707054]
  We evaluate whether every generated sentence is grounded in retrieved documents or the model's pre-training data. Across 3 datasets and 4 model families, our findings reveal that a significant fraction of generated sentences are consistently ungrounded. Our results show that while larger models tend to ground their outputs more effectively, a significant portion of correct answers remains compromised by hallucinations.
  arXiv  Detail & Related papers  (2024-04-10T14:50:10Z)
• A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia [57.31074448586854]
  Large language models (LLMs) have an impressive ability to draw on novel information supplied in their context. Yet the mechanisms underlying this contextual grounding remain unknown. We present a novel method to study grounding abilities using Fakepedia.
  arXiv  Detail & Related papers  (2023-12-04T17:35:42Z)
• Grounding Gaps in Language Model Generations [67.79817087930678]
  We study whether large language models generate text that reflects human grounding. We find that -- compared to humans -- LLMs generate language with less conversational grounding. To understand the roots of the identified grounding gap, we examine the role of instruction tuning and preference optimization.
  arXiv  Detail & Related papers  (2023-11-15T17:40:27Z)
• Large Language Models as Zero-Shot Human Models for Human-Robot Interaction [12.455647753787442]
  Large-language models (LLMs) can act as zero-shot human models for human-robot interaction. LLMs achieve performance comparable to purpose-built models. We present one case study on a simulated trust-based table-clearing task.
  arXiv  Detail & Related papers  (2023-03-06T23:16:24Z)
• Human Trajectory Forecasting in Crowds: A Deep Learning Perspective [89.4600982169]
  We present an in-depth analysis of existing deep learning-based methods for modelling social interactions. We propose two knowledge-based data-driven methods to effectively capture these social interactions. We develop a large scale interaction-centric benchmark TrajNet++, a significant yet missing component in the field of human trajectory forecasting.
  arXiv  Detail & Related papers  (2020-07-07T17:19:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.