SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.12546 · EMNLP · 2024

Liar, Liar, Logical Mire: A Benchmark for Suppositional Reasoning in Large Language Models

Barbara Plank, Philipp Mondorf

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
mainlp/TruthQuest canonical 6 of 8
FunctionStatusWhere it lives
assemble_few_shot_example Ran mainlp/TruthQuest/gen_data.py
pointer only (licence: CC-BY-SA-4.0) · get_code("8ae9aaf535c1971f")
inverse_permut Ran mainlp/TruthQuest/metareasoning/dataprep/data_generator.py
pointer only (licence: CC-BY-SA-4.0) · get_code("ac725e68c1bf5a84")
load_json Ran mainlp/TruthQuest/metareasoning/utils/utils.py
pointer only (licence: CC-BY-SA-4.0) · get_code("33346b27774b1973")
random_k_sublist Ran mainlp/TruthQuest/metareasoning/dataprep/data_generator.py
pointer only (licence: CC-BY-SA-4.0) · get_code("a308874da0bd519f")
random_permut Ran mainlp/TruthQuest/metareasoning/dataprep/data_generator.py
pointer only (licence: CC-BY-SA-4.0) · get_code("1afdf7479ae45b66")
reorder_list Ran mainlp/TruthQuest/evaluate_conclusion.py
pointer only (licence: CC-BY-SA-4.0) · get_code("1935e2c60609666f")
read_text_file Not yet run mainlp/TruthQuest/metareasoning/utils/utils.py
pointer only (licence: CC-BY-SA-4.0) · get_code("c387ce2fd70d9c06")
read_yaml_file Not yet run mainlp/TruthQuest/metareasoning/utils/utils.py
pointer only (licence: CC-BY-SA-4.0) · get_code("d05488b912cd3af0")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Knights and knaves problems represent a classic genre of logical puzzles where characters either tell the truth or lie. The objective is to logically deduce each character's identity based on their statements. The challenge arises from the truth-telling or lying behavior, which influences the logical implications of each statement. Solving these puzzles requires not only direct deductions from individual statements, but the ability to assess the truthfulness of statements by reasoning through various hypothetical scenarios. As such, knights and knaves puzzles serve as compelling examples of suppositional reasoning. In this paper, we introduce TruthQuest, a benchmark for suppositional reasoning based on the principles of knights and knaves puzzles. Our benchmark presents problems of varying complexity, considering both the number of characters and the types of logical statements involved. Evaluations on TruthQuest show that large language models like Llama 3 and Mixtral-8x7B exhibit significant difficulties solving these tasks. A detailed error analysis of the models' output reveals that lower-performing models exhibit a diverse range of reasoning errors, frequently failing to grasp the concept of truth and lies. In comparison, more proficient models primarily struggle with accurately inferring the logical implications of potentially false statements.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.12546")
get_code_for_paper("2406.12546")
have("2406.12546")

Connect an agent — have() is free.