Tootfinder

One vs. Many: Comprehending Accurate Information from Multiple Erroneous and Inconsistent AI Generations
Yoonjoo Lee, Kihoon Son, Tae Soo Kim, Jisu Kim, John Joon Young Chung, Eytan Adar, Juho Kim
https://arxiv.org/abs/2405.05581

One vs. Many: Comprehending Accurate Information from Multiple Erroneous and Inconsistent AI Generations
As Large Language Models (LLMs) are nondeterministic, the same input can generate different outputs, some of which may be incorrect or hallucinated. If run again, the LLM may correct itself and produce the correct answer. Unfortunately, most LLM-powered systems resort to single results which, correct or not, users accept. Having the LLM produce multiple outputs may help identify disagreements or alternatives. However, it is not obvious how the user will interpret conflicts or inconsistencies. T…

Clue-Instruct: Text-Based Clue Generation for Educational Crossword Puzzles
Andrea Zugarini, Kamyar Zeinalipour, Surya Sai Kadali, Marco Maggini, Marco Gori, Leonardo Rigutini
https://arxiv.org/abs/2404.06186

Clue-Instruct: Text-Based Clue Generation for Educational Crossword Puzzles
Crossword puzzles are popular linguistic games often used as tools to engage students in learning. Educational crosswords are characterized by less cryptic and more factual clues that distinguish them from traditional crossword puzzles. Despite there exist several publicly available clue-answer pair databases for traditional crosswords, educational clue-answer pairs datasets are missing. In this article, we propose a methodology to build educational clue generation datasets that can be used to …

Logic Query of Thoughts: Guiding Large Language Models to Answer Complex Logic Queries with Knowledge Graphs
Lihui Liu, Zihao Wang, Ruizhong Qiu, Yikun Ban, Hanghang Tong
https://arxiv.org/abs/2404.04264

Logic Query of Thoughts: Guiding Large Language Models to Answer Complex Logic Queries with Knowledge Graphs
Despite the superb performance in many tasks, large language models (LLMs) bear the risk of generating hallucination or even wrong answers when confronted with tasks that demand the accuracy of knowledge. The issue becomes even more noticeable when addressing logic queries that require multiple logic reasoning steps. On the other hand, knowledge graph (KG) based question answering methods are capable of accurately identifying the correct answers with the help of knowledge graph, yet its accurac…

SELF-[IN]CORRECT: LLMs Struggle with Refining Self-Generated Responses
Dongwei Jiang, Jingyu Zhang, Orion Weller, Nathaniel Weir, Benjamin Van Durme, Daniel Khashabi
https://arxiv.org/abs/2404.04298

SELF-[IN]CORRECT: LLMs Struggle with Refining Self-Generated Responses
Can LLMs continually improve their previous outputs for better results? An affirmative answer would require LLMs to be better at discriminating among previously-generated alternatives, than generating initial responses. We explore the validity of this hypothesis in practice. We first introduce a unified framework that allows us to compare the generative and discriminative capability of any model on any task. Then, in our resulting experimental analysis of several LLMs, we do not observe the per…

One vs. Many: Comprehending Accurate Information from Multiple Erroneous and Inconsistent AI Generations
Yoonjoo Lee, Kihoon Son, Tae Soo Kim, Jisu Kim, John Joon Young Chung, Eytan Adar, Juho Kim
https://arxiv.org/abs/2405.05581

One vs. Many: Comprehending Accurate Information from Multiple Erroneous and Inconsistent AI Generations
As Large Language Models (LLMs) are nondeterministic, the same input can generate different outputs, some of which may be incorrect or hallucinated. If run again, the LLM may correct itself and produce the correct answer. Unfortunately, most LLM-powered systems resort to single results which, correct or not, users accept. Having the LLM produce multiple outputs may help identify disagreements or alternatives. However, it is not obvious how the user will interpret conflicts or inconsistencies. T…

Calibration of luminosity correlations of gamma-ray bursts using quasars
Sarveshkumar Purohit, Shantanu Desai
https://arxiv.org/abs/2404.06334 https://

Calibration of luminosity correlations of gamma-ray bursts using quasars
In order to test the efficacy of Gamma-ray Bursts (GRBs) as cosmological probes, we the characterize the scatter in the correlations between six pairs of GRB related observables, which have previously also been studied in arXiv:2011.14040. However, some of these observables depend on the luminosity distance, for which one needs to assume an underlying cosmological model. In order to circumvent this circularity problem, we use X-ray and UV fluxes of quasars as distance anchors to calculate the l…

Homology of Moment Frames
Zoe Cooperband, Allan McRobie, Cameron Millar, Bernd Schulze
https://arxiv.org/abs/2404.07184 https://arxiv…

Homology of Moment Frames
Using homological techniques we show that a pin-anchored frame that involves only moments and shears provides a conceptual bridge between the statics of moment frames and the kinematics of pin-jointed trusses. One immediate result is a long exact sequence whose alternating sum of dimensions gives a novel counting rule for self-stresses and mechanisms. This combines the Maxwell-Calladine count for pin-jointed trusses with the circuit rank (first Betti number) associated with self-stresses in mom…

Authorship Attribution in Bangla Literature (AABL) via Transfer Learning using ULMFiT
Aisha Khatun, Anisur Rahman, Md Saiful Islam, Hemayet Ahmed Chowdhury, Ayesha Tasnim
https://arxiv.org/abs/2403.05519

Authorship Attribution in Bangla Literature (AABL) via Transfer Learning using ULMFiT
Authorship Attribution is the task of creating an appropriate characterization of text that captures the authors' writing style to identify the original author of a given piece of text. With increased anonymity on the internet, this task has become increasingly crucial in various security and plagiarism detection fields. Despite significant advancements in other languages such as English, Spanish, and Chinese, Bangla lacks comprehensive research in this field due to its complex linguistic featu…

Authorship Attribution in Bangla Literature (AABL) via Transfer Learning using ULMFiT
Aisha Khatun, Anisur Rahman, Md Saiful Islam, Hemayet Ahmed Chowdhury, Ayesha Tasnim
https://arxiv.org/abs/2403.05519

Authorship Attribution in Bangla Literature (AABL) via Transfer Learning using ULMFiT
Authorship Attribution is the task of creating an appropriate characterization of text that captures the authors' writing style to identify the original author of a given piece of text. With increased anonymity on the internet, this task has become increasingly crucial in various security and plagiarism detection fields. Despite significant advancements in other languages such as English, Spanish, and Chinese, Bangla lacks comprehensive research in this field due to its complex linguistic featu…

This https://arxiv.org/abs/2404.19733 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Iterative Reasoning Preference Optimization
Iterative preference optimization methods have recently been shown to perform well for general instruction tuning tasks, but typically make little improvement on reasoning tasks (Yuan et al., 2024, Chen et al., 2024). In this work we develop an iterative approach that optimizes the preference between competing generated Chain-of-Thought (CoT) candidates by optimizing for winning vs. losing reasoning steps that lead to the correct answer. We train using a modified DPO loss (Rafailov et al., 2023…