# Define, Evaluate, and Improve Task-Oriented Cognitive Capabilities for Instruction Generation Models

arXiv: https://arxiv.org/abs/2301.05149 · HTML: https://mlsanity.com/paper/2301.05149/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 93 references that are in the map.
- First posted on arXiv 21 Dec 2022.

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [From Recognition to Cognition: Visual Commonsense Reasoning](https://mlsanity.com/paper/1811.10830/) (2018)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)
- [Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding](https://mlsanity.com/paper/2010.07954/) (2020)
- [Speaker-Follower Models for Vision-and-Language Navigation](https://mlsanity.com/paper/1806.02724/) (2018)
- [How Much Can CLIP Benefit Vision-and-Language Tasks?](https://mlsanity.com/paper/2107.06383/) (2021)
- [A Recurrent Vision-and-Language BERT for Navigation](https://mlsanity.com/paper/2011.13922/) (2020)
- [Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout](https://mlsanity.com/paper/1904.04195/) (2019)
- [Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs](https://mlsanity.com/paper/2210.13312/) (2022)
- [Improving Vision-and-Language Navigation with Image-Text Pairs from the Web](https://mlsanity.com/paper/2004.14973/) (2020)
- [Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation](https://mlsanity.com/paper/1905.12255/) (2019)
- [General Evaluation for Instruction Conditioned Navigation using Dynamic Time Warping](https://mlsanity.com/paper/1907.05446/) (2019)
- [A fine-grained comparison of pragmatic language understanding in humans and language models](https://mlsanity.com/paper/2212.06801/) (2022)
- [Reasoning About Pragmatics with Neural Listeners and Speakers](https://mlsanity.com/paper/1604.00562/) (2016)
- [Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning](https://mlsanity.com/paper/2005.07064/) (2020)
- [Evaluating Theory of Mind in Question Answering](https://mlsanity.com/paper/1808.09352/) (2018)
- [Less is More: Generating Grounded Navigation Instructions from Landmarks](https://mlsanity.com/paper/2111.12872/) (2021)
- [A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning](https://mlsanity.com/paper/2210.03112/) (2022)
- [Unified Pragmatic Models for Generating and Following Instructions](https://mlsanity.com/paper/1711.04987/) (2017)
- [Inferring Rewards from Language in Context](https://mlsanity.com/paper/2204.02515/) (2022)
- [The PhotoBook Dataset: Building Common Ground through Visually-Grounded Dialogue](https://mlsanity.com/paper/1906.01530/) (2019)
- [On the Evaluation of Vision-and-Language Navigation Instructions](https://mlsanity.com/paper/2101.10504/) (2021)
- [A Natural Language Corpus of Common Grounding under Continuous and Partially-Observable Context](https://mlsanity.com/paper/1907.03399/) (2019)
- [RMM: A Recursive Mental Model for Dialog Navigation](https://mlsanity.com/paper/2005.00728/) (2020)
- [Few-shot Language Coordination by Modeling Theory of Mind](https://mlsanity.com/paper/2107.05697/) (2021)

## Built on by (most cited first, 7 of 7)

- [Position: Towards Bidirectional Human-AI Alignment](https://mlsanity.com/paper/2406.09264/) (2024)
- [Language Models are Bounded Pragmatic Speakers: Understanding RLHF from a Bayesian Cognitive Modeling Perspective](https://mlsanity.com/paper/2305.17760/) (2023)
- [Vision-Language Models Are Not Pragmatically Competent in Referring Expression Generation](https://mlsanity.com/paper/2504.16060/) (2025)
- [Hallucination Detection for Grounded Instruction Generation](https://mlsanity.com/paper/2310.15319/) (2023)
- [Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting Corrections](https://mlsanity.com/paper/2402.16973/) (2024)
- [Utility-based Adaptive Teaching Strategies using Bayesian Theory of Mind](https://mlsanity.com/paper/2309.17275/) (2023)
- [Pragmatics Meets Culture: Culturally-adapted Artwork Description Generation and Evaluation](https://mlsanity.com/paper/2604.02557/) (2026)

## Abstract (arXiv)

Recent work studies the cognitive capabilities of language models through psychological tests designed for humans. While these studies are helpful for understanding the general capabilities of these models, there is no guarantee that a model possessing sufficient capabilities to pass those tests would actually use those capabilities in performing real-life tasks. In this work, we formulate task-oriented cognitive capabilities, which are human-like cognitive capabilities that language models leverage to perform tasks. These capabilities are (i) the ability to quickly generate good candidate utterances (the search capability) (ii) the ability to predict how a listener interprets those utterances and choose the most appropriate one (the pragmatic capability). We design an evaluation scheme for comparing these capabilities of a language model with those of a human. Applying this scheme to examine various models in a navigation instruction generation problem, we find that their pragmatic capability is severely lacking. This insight leads us to augment them with better models of the listener and obtain a significant boost of 11% in success rate in guiding real humans. Our work advocates for having a principled procedure for aligning language models with humans that involves (i) formulating task-oriented capabilities, (ii) devising a method to quantify their deficiency, and (iii) iteratively improving them.