# Scenarios and Approaches for Situated Natural Language Explanations

arXiv: https://arxiv.org/abs/2406.05035 · HTML: https://mlsanity.com/paper/2406.05035/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 7 Jun 2024.

## Builds on (most cited first, 24 of 24)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [WT5?! Training Text-to-Text Models to Explain their Predictions](https://mlsanity.com/paper/2004.14546/) (2020)
- [Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing](https://mlsanity.com/paper/2102.12060/) (2021)
- [Reframing Human-AI Collaboration for Generating Free-Text Explanations](https://mlsanity.com/paper/2112.08674/) (2021)
- [SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agents](https://mlsanity.com/paper/2403.08715/) (2024)
- [Evaluating Large Language Model Biases in Persona-Steered Generation](https://mlsanity.com/paper/2405.20253/) (2024)
- [Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanations](https://mlsanity.com/paper/1910.03065/) (2019)
- [Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong](https://mlsanity.com/paper/2310.12558/) (2023)
- [The Who in XAI: How AI Background Shapes Perceptions of AI Explanations](https://mlsanity.com/paper/2107.13509/) (2021)
- [Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI](https://mlsanity.com/paper/2206.10847/) (2022)
- [Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales](https://mlsanity.com/paper/2305.07095/) (2023)
- [A Study of Automatic Metrics for the Evaluation of Natural Language Explanations](https://mlsanity.com/paper/2103.08545/) (2021)
- [LLM-Generated Black-box Explanations Can Be Adversarially Helpful](https://mlsanity.com/paper/2405.06800/) (2024)
- [FRAME: Evaluating Rationale-Label Consistency Metrics for Free-Text Rationales](https://mlsanity.com/paper/2207.00779/) (2022)
- [What Else Do I Need to Know? The Effect of Background Information on Users' Reliance on QA Systems](https://mlsanity.com/paper/2305.14331/) (2023)
- [Sequential Explanations with Mental Model-Based Policies](https://mlsanity.com/paper/2007.09028/) (2020)
- [Is the Pope Catholic? Yes, the Pope is Catholic. Generative Evaluation of Non-Literal Intent Resolution in LLMs](https://mlsanity.com/paper/2405.08760/) (2024)

## Built on by (most cited first, 1 of 1)

- [Persona Prompting as a Lens on LLM Social Reasoning](https://mlsanity.com/paper/2601.20757/) (2026)

## Abstract (arXiv)

Large language models (LLMs) can be used to generate natural language explanations (NLE) that are adapted to different users' situations. However, there is yet to be a quantitative evaluation of the extent of such adaptation. To bridge this gap, we collect a benchmarking dataset, Situation-Based Explanation. This dataset contains 100 explanandums. Each explanandum is paired with explanations targeted at three distinct audience types-such as educators, students, and professionals-enabling us to assess how well the explanations meet the specific informational needs and contexts of these diverse groups e.g. students, teachers, and parents. For each "explanandum paired with an audience" situation, we include a human-written explanation. These allow us to compute scores that quantify how the LLMs adapt the explanations to the situations. On an array of pretrained language models with varying sizes, we examine three categories of prompting methods: rule-based prompting, meta-prompting, and in-context learning prompting. We find that 1) language models can generate prompts that result in explanations more precisely aligned with the target situations, 2) explicitly modeling an "assistant" persona by prompting "You are a helpful assistant..." is not a necessary prompt technique for situated NLE tasks, and 3) the in-context learning prompts only can help LLMs learn the demonstration template but can't improve their inference performance. SBE and our analysis facilitate future research towards generating situated natural language explanations.