Greg Durrett, Swarat Chaudhuri, Zayne Sprague, Kaj Bostrom
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
A growing body of work studies how to answer a question or verify a claim by generating a natural language "proof": a chain of deductive inferences yielding the answer based on a set of premises. However, these methods can only make sound deductions when they follow from evidence that is given. We propose a new system that can handle the underspecified setting where not all premises are stated at the outset; that is, additional assumptions need to be materialized to prove a claim. By using a natural language generation model to abductively infer a premise given another premise and a conclusion, we can impute missing pieces of evidence needed for the conclusion to be true. Our system searches over two fringes in a bidirectional fashion, interleaving deductive (forward-chaining) and abductive (backwardchaining) generation steps. We sample multiple possible outputs for each step to achieve coverage of the search space, at the same time ensuring correctness by filtering lowquality generations with a round-trip validation procedure. Results on a modified version of the EntailmentBank dataset and a new dataset called Everyday Norms: Why Not? show that abductive generation with validation can recover premises across in-and out-of-domain settings. 1 1 Code and data publicly available at https: //github.com/Zayne-sprague/Natural_Language_ Deduction_with_Incomplete_Information.git A human is a kind of animal Astronauts are human.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2211.00614")
get_code_for_paper("2211.00614")
have("2211.00614")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2211.00614.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2211.00614)
Connect an agent — have() is free.