Tootfinder

This https://arxiv.org/abs/2310.18235 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation
Evaluating text-to-image models is notoriously difficult. A strong recent approach for assessing text-image faithfulness is based on QG/A (question generation and answering), which uses pre-trained foundational models to automatically generate a set of questions and answers from the prompt, and output images are scored based on whether these answers extracted with a visual question answering model are consistent with the prompt-based answers. This kind of evaluation is naturally dependent on th…

Improving Retrieval for RAG based Question Answering Models on Financial Documents
Spurthi Setty, Katherine Jijo, Eden Chung, Natan Vidra
https://arxiv.org/abs/2404.07221

Improving Retrieval for RAG based Question Answering Models on Financial Documents
The effectiveness of Large Language Models (LLMs) in generating accurate responses relies heavily on the quality of input provided, particularly when employing Retrieval Augmented Generation (RAG) techniques. RAG enhances LLMs by sourcing the most relevant text chunk(s) to base queries upon. Despite the significant advancements in LLMs' response quality in recent years, users may still encounter inaccuracies or irrelevant answers; these issues often stem from suboptimal text chunk retrieval by …

Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought
James Chua, Edward Rees, Hunar Batra, Samuel R. Bowman, Julian Michael, Ethan Perez, Miles Turpin
https://arxiv.org/abs/2403.05518

Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought
While chain-of-thought prompting (CoT) has the potential to improve the explainability of language model reasoning, it can systematically misrepresent the factors influencing models' behavior--for example, rationalizing answers in line with a user's opinion without mentioning this bias. To mitigate this biased reasoning problem, we introduce bias-augmented consistency training (BCT), an unsupervised fine-tuning scheme that trains models to give consistent reasoning across prompts with and witho…

Two good questions this morning from Andrew Simonet. The second is one I don’t think we talk about enough: you can’t just have the greatest art from the greatest artists, without the whole cultural ecosystem that produces and nurtures them. The minor artists and the failed experiments all play essential roles too.
https://

Design emails people love to get.
Beginners and experts use Flodesk to grow their business. Design emails and forms that look great on any device. Try it free.

This https://arxiv.org/abs/2211.04134 has been replaced.
link: https://scholar.google.com/scholar?q=a

Consistent Query Answering for Primary Keys and Conjunctive Queries with Counting
The problem of consistent query answering for primary keys and self-join-free conjunctive queries has been intensively studied in recent years and is by now well understood. In this paper, we study an extension of this problem with counting. The queries we consider count how many times each value occurs in a designated (possibly composite) column of an answer to a full conjunctive query. In a setting of database repairs, we adopt the semantics of [Arenas et al., ICDT 2001] which computes tight …

Unraveling the Dilemma of AI Errors: Exploring the Effectiveness of Human and Machine Explanations for Large Language Models
Marvin Pafla, Kate Larson, Mark Hancock
https://arxiv.org/abs/2404.07725

Unraveling the Dilemma of AI Errors: Exploring the Effectiveness of Human and Machine Explanations for Large Language Models
The field of eXplainable artificial intelligence (XAI) has produced a plethora of methods (e.g., saliency-maps) to gain insight into artificial intelligence (AI) models, and has exploded with the rise of deep learning (DL). However, human-participant studies question the efficacy of these methods, particularly when the AI output is wrong. In this study, we collected and analyzed 156 human-generated text and saliency-based explanations collected in a question-answering task (N=40) and compared t…

Ministerium: Verstärkung nach Charkiw entsandt
Die Ukraine hat nach Angaben ihres Verteidigungsministeriums militärische Verstärkung in das Grenzgebiet in der nordöstlichen Region Charkiw entsandt. Damit sollen die dortigen Truppen dabei unterstützt werden, russische Angriffe abzuwehren, begründet das Ministerium die Maßnahmen. Russische Truppen hätten am frühen Morgen versucht, die Grenze mit gepanzerten Fahrzeugen zu durchb…
📑

Ukraine-Liveblog: ++ USA kündigen neue Militärhilfe für Kiew an ++
Die USA haben weitere Militärhilfe für Kiew im Wert von 400 Millionen Dollar bekanntgegeben. Bundesentwicklungsministerin Schulze hat in Lwiw eine Werkstatt zur Herstellung von Prothesen für Kriegsverletzte eröffnet. Die Entwicklungen im Liveblog.

Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought
James Chua, Edward Rees, Hunar Batra, Samuel R. Bowman, Julian Michael, Ethan Perez, Miles Turpin
https://arxiv.org/abs/2403.05518

Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought
While chain-of-thought prompting (CoT) has the potential to improve the explainability of language model reasoning, it can systematically misrepresent the factors influencing models' behavior--for example, rationalizing answers in line with a user's opinion without mentioning this bias. To mitigate this biased reasoning problem, we introduce bias-augmented consistency training (BCT), an unsupervised fine-tuning scheme that trains models to give consistent reasoning across prompts with and witho…

Two good questions this morning from Andrew Simonet. The second is one I don’t think we talk about enough: you can’t just have the greatest art from the greatest artists, without the whole cultural ecosystem that produces and nurtures them. The minor artists and the failed experiments all play essential roles too.
https://

Design emails people love to get.
Beginners and experts use Flodesk to grow their business. Design emails and forms that look great on any device. Try it free.

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 …