NewsInterview: a Dataset and a Playground to Evaluate LLMs’ Grounding Gap via Informational Interviews (2025.acl-long)
Copied to clipboard
Alexander Spangher, Michael Lu, Sriya Kalyan, Hyundong Justin Cho, Tenghao Huang, Weiyan Shi, Jonathan May
| Challenge: | Existing large datasets (1k-10k transcripts) are generated via crowdsourcing and are inherently unnatural. |
| Approach: | They curate a dataset of 40,000 two-person informational interviews from NPR and CNN . they find that LLMs are significantly less likely than human interviewers to use acknowledgements and pivot to higher-level questions. |
| Outcome: | The proposed model is based on 40,000 interviews with journalists and CNN . |
Similar Papers
Evaluating the Effectiveness of Large Language Models in Establishing Conversational Grounding (2024.emnlp-main)
Copied to clipboard
| Challenge: | despite its importance, there has been limited research on conversational grounding in recent years . pre-trained language models have been costly and time-consuming to evaluate . |
| Approach: | They evaluate the performance of large language models in various aspects of conversational grounding . they propose ways to enhance the capabilities of the models that lag in this aspect . |
| Outcome: | The proposed model performance is based on pre-trained language models and a large pre-training dataset. |
How Well Do Large Language Models Truly Ground? (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing research defines “grounding” as having the correct answer, which does not ensure the reliability of the entire response. |
| Approach: | They propose a stricter definition of grounding: fully utilizes the necessary knowledge from the provided context and stays within the limits of that knowledge. |
| Outcome: | The proposed model can be ground on external contexts and maintain its correct answer. |
Can LLMs Ground when they (Don’t) Know: A Study on Direct and Loaded Political Questions (2025.acl-long)
Copied to clipboard
| Challenge: | Using large language models, interlocutors can reach mutual understanding even when they do not possess perfect knowledge. |
| Approach: | They examine whether loaded questions lead LLMs to engage in active grounding and correct false user beliefs in connection to their level of knowledge and their political bias. |
| Outcome: | The proposed model can answer direct knowledge questions and loaded questions that presuppose misinformation, while ignoring false user beliefs. |
Grounding Gaps in Language Model Generations (2024.naacl-long)
Copied to clipboard
| Challenge: | Effective conversation requires common ground, but it does not emerge spontaneously. |
| Approach: | They propose a set of grounding acts and metrics that quantify attempted grounding . they find that large language models generate language with less conversational grounding than humans . |
| Outcome: | The proposed models generate language with less conversational grounding than humans . compared to humans, they generate language that appears to presume common ground . |
DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text (2024.findings-naacl)
Copied to clipboard
| Challenge: | Retrievalaugmented LLMs have been used to ground LLM in external knowledge . a gap exists in the current landscape regarding the effectiveness of grounding LLM on heterogeneous knowledge sources. |
| Approach: | They propose a model that uses symbolic language to generate symbolic queries . they use a dataset that is generated using predefined reasoning chains and human annotation . |
| Outcome: | The proposed model outperforms previous approaches by a significant margin in QA tasks over text. |
Do LLMs Plan Like Human Writers? Comparing Journalist Coverage of Press Releases with LLMs (2024.emnlp-main)
Copied to clipboard
| Challenge: | Journalists engage in multiple steps in news writing that depend on human creativity, such as exploring different “angles” and selecting sources. |
| Approach: | They propose to use large language models to help journalists plan their news coverage . they find that LLMs recommend more creative angles and more informational sources . |
| Outcome: | The proposed models align better with humans when recommending angles, compared with informational sources. |
InteGround: On the Evaluation of Verification and Retrieval Planning in Integrative Grounding (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing grounding approaches work well for simple queries, but many real-world information needs require synthesizing multiple pieces of evidence. |
| Approach: | They introduce "integrative grounding" to evaluate the ability to ground large language models in external knowledge sources. |
| Outcome: | The proposed approach is robust to redundant evidence, but rationalizes using internal knowledge when information is incomplete. |
Navigating Rifts in Human-LLM Grounding: Study and Benchmark (2025.acl-long)
Copied to clipboard
| Challenge: | Language models excel at following instructions but struggle with collaborative aspects of conversation that humans naturally employ. |
| Approach: | They analyze logs from WildChat, MultiWOZ, and Bing Chat to examine grounding challenges . they propose a benchmark to determine when LLMs fail to initiate grounding . |
| Outcome: | The proposed model predicts interactions that fail to ground with users . the proposed model is based on human-human interactions with humans . |
How Accurate Are LLMs at Multi-Question Answering on Conversational Transcripts? (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are used for question answering over long contexts . high computational costs and latency hinder the process . |
| Approach: | They explore the capabilities of Large Language Models to answer multiple questions based on the same conversational context. |
| Outcome: | The proposed models outperform proprietary and public models in question answering . their results show that they can be cost-effective and transparent . |
LUCID: LLM-Generated Utterances for Complex and Interesting Dialogues (2024.naacl-srw)
Copied to clipboard
Joe Stacey, Jianpeng Cheng, John Torr, Tristan Guigue, Joris Driesen, Alexandru Coca, Mark Gaynor, Anders Johannsen
| Challenge: | Existing datasets with limited domain coverage and few challenging conversational phenomena are often unlabelled . Existing data is limited in quality and lacks a robust evaluation process . |
| Approach: | They propose a high quality data generation system that generates high quality dialogues using 4,277 conversations across 100 intents. |
| Outcome: | The proposed system produces high quality dialogue data with high quality labels. |