# Characterizing Large Language Models as Rationalizers of Knowledge-intensive Tasks

arXiv: https://arxiv.org/abs/2311.05085 · HTML: https://mlsanity.com/paper/2311.05085/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 58 of its 86 references that are in the map.
- First posted on arXiv 9 Nov 2023.

## Builds on (most cited first, 30 of 58)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Green AI](https://mlsanity.com/paper/1907.10597/) (2019)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback](https://mlsanity.com/paper/2302.12813/) (2023)
- [Metrics for Explainable AI: Challenges and Prospects](https://mlsanity.com/paper/1812.04608/) (2018)
- [KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning](https://mlsanity.com/paper/1909.02151/) (2019)
- [Multimodal Explanations: Justifying Decisions and Pointing to the Evidence](https://mlsanity.com/paper/1802.08129/) (2018)
- [Unsupervised Commonsense Question Answering with Self-Talk](https://mlsanity.com/paper/2004.05483/) (2020)
- [Measuring Association Between Labels and Free-Text Rationales](https://mlsanity.com/paper/2010.12762/) (2020)
- [Generating Visual Explanations](https://mlsanity.com/paper/1603.08507/) (2016)
- [Post-hoc Interpretability for Neural NLP: A Survey](https://mlsanity.com/paper/2108.04840/) (2021)
- [Deep Bidirectional Language-Knowledge Graph Pretraining](https://mlsanity.com/paper/2210.09338/) (2022)
- [WT5?! Training Text-to-Text Models to Explain their Predictions](https://mlsanity.com/paper/2004.14546/) (2020)
- [Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework](https://mlsanity.com/paper/2305.03268/) (2023)

## Built on by (most cited first, 9 of 9)

- [Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above](https://mlsanity.com/paper/2502.14127/) (2025)
- [KnowTuning: Knowledge-aware Fine-tuning for Large Language Models](https://mlsanity.com/paper/2402.11176/) (2024)
- [A Rose by Any Other Name: LLM-Generated Explanations Are Good Proxies for Human Explanations to Collect Label Distributions on NLI](https://mlsanity.com/paper/2412.13942/) (2024)
- [Orchestrating Agents and Data for Enterprise: A Blueprint Architecture for Compound AI](https://mlsanity.com/paper/2504.08148/) (2025)
- [Systematic Characterization of LLM Quantization: A Performance, Energy, and Quality Perspective](https://mlsanity.com/paper/2508.16712/) (2025)
- [STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings](https://mlsanity.com/paper/2504.13416/) (2025)
- [CMDBench: A Benchmark for Coarse-to-fine Multimodal Data Discovery in Compound AI Systems](https://mlsanity.com/paper/2406.00583/) (2024)
- [POEM: Interactive Prompt Optimization for Enhancing Multimodal Reasoning of Large Language Models](https://mlsanity.com/paper/2406.03843/) (2024)
- [Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study](https://mlsanity.com/paper/2508.09776/) (2025)

## Abstract (arXiv)

Large language models (LLMs) are proficient at generating fluent text with minimal task-specific supervision. Yet, their ability to provide well-grounded rationalizations for knowledge-intensive tasks remains under-explored. Such tasks, like commonsense multiple-choice questions, require rationales based on world knowledge to support predictions and refute alternate options. We consider the task of generating knowledge-guided rationalization in natural language by using expert-written examples in a few-shot manner. Surprisingly, crowd-workers preferred knowledge-grounded rationales over crowdsourced rationalizations, citing their factuality, sufficiency, and comprehensive refutations. Although LLMs-generated rationales were preferable, further improvements in conciseness and novelty are required. In another study, we show how rationalization of incorrect model predictions erodes humans' trust in LLM-generated rationales. Motivated by these observations, we create a two-stage pipeline to review task predictions and eliminate potential incorrect decisions before rationalization, enabling trustworthy rationale generation.