Search Results for author:
Found 8 papers, 3 papers with code
EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers
(1) EPT-X model: An explainable neural model that sets a baseline for algebraic word problem solving task, in terms of model’s correctness, plausibility, and faithfulness.
Ranked #1 on
Math Word Problem Solving
on PEN
Point to the Expression: Solving Algebraic Word Problems using the Expression-Pointer Transformer Model
The contribution of this paper is two-fold; (1) We propose a pure neural model, EPT, which can address the expression fragmentation and the operand-context separation.
Ranked #3 on
Math Word Problem Solving
on DRAW-1K
DART: An AIGT Detector using AMR of Rephrased Text
The experimental result shows that DART can discriminate multiple black-box LLMs without using syntactic features and knowing the origin of AIGT.
Leveraging Large Language Models for Active Merchant Non-player Characters
First, we define passive pricing as the limited ability of merchants to modify predefined item prices.
Examining Identity Drift in Conversations of LLM Agents
We hope these three findings can help to improve persona stability in AI-driven dialogue systems, particularly in long-term conversations.
Microscopic Analysis on LLM players via Social Deduction Game
We conducted an experiment with four LLMs, analyzing their gameplay behavior in SpyGame both quantitatively and qualitatively.
People will agree what I think: Investigating LLM's False Consensus Effect
As the false belief in a model can harm the usability of such systems, LLMs should not have cognitive biases that humans have.
Generating Equation by Utilizing Operators : GEO model
In this paper, we propose the GEO (Generation of Equations by utilizing Operators) model that does not use hand-crafted features and addresses two issues that are present in existing neural models: 1. missing domain-specific knowledge features and 2. losing encoder-level knowledge.
Ranked #2 on
Math Word Problem Solving
on DRAW-1K
