Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting Corrections Article Swipe
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2402.16973
Language models will inevitably err in situations with which they are unfamiliar. However, by effectively communicating uncertainties, they can still guide humans toward making sound decisions in those contexts. We demonstrate this idea by developing HEAR, a system that can successfully guide humans in simulated residential environments despite generating potentially inaccurate instructions. Diverging from systems that provide users with only the instructions they generate, HEAR warns users of potential errors in its instructions and suggests corrections. This rich uncertainty information effectively prevents misguidance and reduces the search space for users. Evaluation with 80 users shows that HEAR achieves a 13% increase in success rate and a 29% reduction in final location error distance compared to only presenting instructions to users. Interestingly, we find that offering users possibilities to explore, HEAR motivates them to make more attempts at the task, ultimately leading to a higher success rate. To our best knowledge, this work is the first to show the practical benefits of uncertainty communication in a long-horizon sequential decision-making problem.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2402.16973
- https://arxiv.org/pdf/2402.16973
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4392270653
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4392270653Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2402.16973Digital Object Identifier
- Title
-
Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting CorrectionsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-02-26Full publication date if available
- Authors
-
Lingjun Zhao, Khanh Nguyen, Hal DauméList of authors in order
- Landing page
-
https://arxiv.org/abs/2402.16973Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2402.16973Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2402.16973Direct OA link when available
- Concepts
-
Imperfect, Computer science, Psychology, Cognitive psychology, Philosophy, LinguisticsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4392270653 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2402.16973 |
| ids.doi | https://doi.org/10.48550/arxiv.2402.16973 |
| ids.openalex | https://openalex.org/W4392270653 |
| fwci | |
| type | preprint |
| title | Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting Corrections |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10533 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.7547000050544739 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1706 |
| topics[0].subfield.display_name | Computer Science Applications |
| topics[0].display_name | Teaching and Learning Programming |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2780310539 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8396378755569458 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q12547192 |
| concepts[0].display_name | Imperfect |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.4711875915527344 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C15744967 |
| concepts[2].level | 0 |
| concepts[2].score | 0.41930168867111206 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[2].display_name | Psychology |
| concepts[3].id | https://openalex.org/C180747234 |
| concepts[3].level | 1 |
| concepts[3].score | 0.3792603015899658 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q23373 |
| concepts[3].display_name | Cognitive psychology |
| concepts[4].id | https://openalex.org/C138885662 |
| concepts[4].level | 0 |
| concepts[4].score | 0.10313084721565247 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[4].display_name | Philosophy |
| concepts[5].id | https://openalex.org/C41895202 |
| concepts[5].level | 1 |
| concepts[5].score | 0.07864588499069214 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[5].display_name | Linguistics |
| keywords[0].id | https://openalex.org/keywords/imperfect |
| keywords[0].score | 0.8396378755569458 |
| keywords[0].display_name | Imperfect |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.4711875915527344 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/psychology |
| keywords[2].score | 0.41930168867111206 |
| keywords[2].display_name | Psychology |
| keywords[3].id | https://openalex.org/keywords/cognitive-psychology |
| keywords[3].score | 0.3792603015899658 |
| keywords[3].display_name | Cognitive psychology |
| keywords[4].id | https://openalex.org/keywords/philosophy |
| keywords[4].score | 0.10313084721565247 |
| keywords[4].display_name | Philosophy |
| keywords[5].id | https://openalex.org/keywords/linguistics |
| keywords[5].score | 0.07864588499069214 |
| keywords[5].display_name | Linguistics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2402.16973 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | cc-by-nc-sa |
| locations[0].pdf_url | https://arxiv.org/pdf/2402.16973 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | https://openalex.org/licenses/cc-by-nc-sa |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2402.16973 |
| locations[1].id | doi:10.48550/arxiv.2402.16973 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2402.16973 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5102321745 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Lingjun Zhao |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zhao, Lingjun |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5013166244 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-0400-1070 |
| authorships[1].author.display_name | Khanh Nguyen |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Nguyen, Khanh |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5019928111 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-3760-345X |
| authorships[2].author.display_name | Hal Daumé |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Daumé III, Hal |
| authorships[2].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2402.16973 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting Corrections |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10533 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.7547000050544739 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1706 |
| primary_topic.subfield.display_name | Computer Science Applications |
| primary_topic.display_name | Teaching and Learning Programming |
| related_works | https://openalex.org/W2748952813, https://openalex.org/W2374250903, https://openalex.org/W1546413948, https://openalex.org/W2263832889, https://openalex.org/W2243884323, https://openalex.org/W42072456, https://openalex.org/W2390279801, https://openalex.org/W4243095785, https://openalex.org/W2358668433, https://openalex.org/W4387894447 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2402.16973 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | cc-by-nc-sa |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2402.16973 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by-nc-sa |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2402.16973 |
| primary_location.id | pmh:oai:arXiv.org:2402.16973 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | cc-by-nc-sa |
| primary_location.pdf_url | https://arxiv.org/pdf/2402.16973 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | https://openalex.org/licenses/cc-by-nc-sa |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2402.16973 |
| publication_date | 2024-02-26 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 36, 98, 105, 142, 164 |
| abstract_inverted_index.80 | 92 |
| abstract_inverted_index.To | 146 |
| abstract_inverted_index.We | 29 |
| abstract_inverted_index.at | 136 |
| abstract_inverted_index.by | 13, 33 |
| abstract_inverted_index.in | 5, 26, 43, 70, 101, 108, 163 |
| abstract_inverted_index.is | 152 |
| abstract_inverted_index.of | 67, 160 |
| abstract_inverted_index.to | 114, 118, 127, 132, 141, 155 |
| abstract_inverted_index.we | 121 |
| abstract_inverted_index.13% | 99 |
| abstract_inverted_index.29% | 106 |
| abstract_inverted_index.and | 73, 83, 104 |
| abstract_inverted_index.are | 10 |
| abstract_inverted_index.can | 18, 39 |
| abstract_inverted_index.err | 4 |
| abstract_inverted_index.for | 88 |
| abstract_inverted_index.its | 71 |
| abstract_inverted_index.our | 147 |
| abstract_inverted_index.the | 60, 85, 137, 153, 157 |
| abstract_inverted_index.HEAR | 64, 96, 129 |
| abstract_inverted_index.This | 76 |
| abstract_inverted_index.best | 148 |
| abstract_inverted_index.find | 122 |
| abstract_inverted_index.from | 53 |
| abstract_inverted_index.idea | 32 |
| abstract_inverted_index.make | 133 |
| abstract_inverted_index.more | 134 |
| abstract_inverted_index.only | 59, 115 |
| abstract_inverted_index.rate | 103 |
| abstract_inverted_index.rich | 77 |
| abstract_inverted_index.show | 156 |
| abstract_inverted_index.that | 38, 55, 95, 123 |
| abstract_inverted_index.them | 131 |
| abstract_inverted_index.they | 9, 17, 62 |
| abstract_inverted_index.this | 31, 150 |
| abstract_inverted_index.will | 2 |
| abstract_inverted_index.with | 7, 58, 91 |
| abstract_inverted_index.work | 151 |
| abstract_inverted_index.HEAR, | 35 |
| abstract_inverted_index.error | 111 |
| abstract_inverted_index.final | 109 |
| abstract_inverted_index.first | 154 |
| abstract_inverted_index.guide | 20, 41 |
| abstract_inverted_index.rate. | 145 |
| abstract_inverted_index.shows | 94 |
| abstract_inverted_index.sound | 24 |
| abstract_inverted_index.space | 87 |
| abstract_inverted_index.still | 19 |
| abstract_inverted_index.task, | 138 |
| abstract_inverted_index.those | 27 |
| abstract_inverted_index.users | 57, 66, 93, 125 |
| abstract_inverted_index.warns | 65 |
| abstract_inverted_index.which | 8 |
| abstract_inverted_index.errors | 69 |
| abstract_inverted_index.higher | 143 |
| abstract_inverted_index.humans | 21, 42 |
| abstract_inverted_index.making | 23 |
| abstract_inverted_index.models | 1 |
| abstract_inverted_index.search | 86 |
| abstract_inverted_index.system | 37 |
| abstract_inverted_index.toward | 22 |
| abstract_inverted_index.users. | 89, 119 |
| abstract_inverted_index.despite | 47 |
| abstract_inverted_index.leading | 140 |
| abstract_inverted_index.provide | 56 |
| abstract_inverted_index.reduces | 84 |
| abstract_inverted_index.success | 102, 144 |
| abstract_inverted_index.systems | 54 |
| abstract_inverted_index.However, | 12 |
| abstract_inverted_index.Language | 0 |
| abstract_inverted_index.achieves | 97 |
| abstract_inverted_index.attempts | 135 |
| abstract_inverted_index.benefits | 159 |
| abstract_inverted_index.compared | 113 |
| abstract_inverted_index.distance | 112 |
| abstract_inverted_index.explore, | 128 |
| abstract_inverted_index.increase | 100 |
| abstract_inverted_index.location | 110 |
| abstract_inverted_index.offering | 124 |
| abstract_inverted_index.prevents | 81 |
| abstract_inverted_index.problem. | 168 |
| abstract_inverted_index.suggests | 74 |
| abstract_inverted_index.Diverging | 52 |
| abstract_inverted_index.contexts. | 28 |
| abstract_inverted_index.decisions | 25 |
| abstract_inverted_index.generate, | 63 |
| abstract_inverted_index.motivates | 130 |
| abstract_inverted_index.potential | 68 |
| abstract_inverted_index.practical | 158 |
| abstract_inverted_index.reduction | 107 |
| abstract_inverted_index.simulated | 44 |
| abstract_inverted_index.Evaluation | 90 |
| abstract_inverted_index.developing | 34 |
| abstract_inverted_index.generating | 48 |
| abstract_inverted_index.inaccurate | 50 |
| abstract_inverted_index.inevitably | 3 |
| abstract_inverted_index.knowledge, | 149 |
| abstract_inverted_index.presenting | 116 |
| abstract_inverted_index.sequential | 166 |
| abstract_inverted_index.situations | 6 |
| abstract_inverted_index.ultimately | 139 |
| abstract_inverted_index.demonstrate | 30 |
| abstract_inverted_index.effectively | 14, 80 |
| abstract_inverted_index.information | 79 |
| abstract_inverted_index.misguidance | 82 |
| abstract_inverted_index.potentially | 49 |
| abstract_inverted_index.residential | 45 |
| abstract_inverted_index.uncertainty | 78, 161 |
| abstract_inverted_index.unfamiliar. | 11 |
| abstract_inverted_index.corrections. | 75 |
| abstract_inverted_index.environments | 46 |
| abstract_inverted_index.instructions | 61, 72, 117 |
| abstract_inverted_index.long-horizon | 165 |
| abstract_inverted_index.successfully | 40 |
| abstract_inverted_index.communicating | 15 |
| abstract_inverted_index.communication | 162 |
| abstract_inverted_index.instructions. | 51 |
| abstract_inverted_index.possibilities | 126 |
| abstract_inverted_index.Interestingly, | 120 |
| abstract_inverted_index.uncertainties, | 16 |
| abstract_inverted_index.decision-making | 167 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile |