Tootfinder

Comical snark
Not entirely fair, because there _are_ some doctors looking into Long Covid properly...
"Physicians can help you with post Covid symptoms about as much as toddlers with one of those pretend doctor kits. Actually, the toddler probably has better advice because they might actually say something helpful like “take a nap” instead of the “deconditioning” BS from the “trained” physicians (who have nearly zero training in post-viral pathologies)."
#LongCovid

Taking command of a new vessel is always a big ceremony in #StarTrek. But in the military, everything needs a proper order, which we will look at for today's #TrekTriviaTuesday.
As always no googling and no spoiling the answer for others. Please boost after voting! :BoostOK:
Vo…

This https://arxiv.org/abs/2402.18060 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions
LLMs have demonstrated impressive performance in answering medical questions, such as passing scores on medical licensing examinations. However, medical board exam questions or general clinical questions do not capture the complexity of realistic clinical cases. Moreover, the lack of reference explanations means we cannot easily evaluate the reasoning of model decisions, a crucial component of supporting doctors in making complex medical decisions. To address these challenges, we construct two …

answers from electrical engineers and FPGA/ASIC designers only: any strong preference towards using "combinatorial logic" or "combinational logic"?

InfiCoder-Eval: Systematically Evaluating the Question-Answering Capabilities of Code Large Language Models
Linyi Li, Shijie Geng, Zhenwen Li, Yibo He, Hao Yu, Ziyue Hua, Guanghan Ning, Siwei Wang, Tao Xie, Hongxia Yang
https://arxiv.org/abs/2404.07940

InfiCoder-Eval: Systematically Evaluating the Question-Answering Capabilities of Code Large Language Models
Large Language Models for understanding and generating code (code LLMs) have witnessed tremendous progress in recent years. With the rapid development of code LLMs, many popular evaluation benchmarks, such as HumanEval, DS-1000, and MBPP, have emerged to measure the performance of code LLMs with a particular focus on code generation tasks. However, they are insufficient to cover the full range of expected capabilities of code LLMs, which span beyond code generation to answering diverse coding-r…

This summer’s Democratic National Convention could be hit by protests and scenes of chaos that undermine Joe Biden's reelection campaign.
Already, 65-plus organizations in Chicago and elsewhere have formed a coalition to “March on the DNC” when it opens there on Aug. 19.
Activists have sued in federal court, alleging First Amendment violations because the city has only offered permits for demonstrations miles from the United Center, where Biden is scheduled to accept the Dem…

Noting campus protests, Democrats are preparing for intense action at their summer convention
As pro-Palestinian demonstrations escalate on college campuses around the country, critics of President Joe Biden’s handling of the Israel-Hamas war suggest this summer’s Democratic National Convention could be hit by protests and scenes of chaos that undermine his reelection. Already, more than 65 organizations in Chicago and elsewhere have formed a coalition to “March on the DNC” when it opens there on Aug. 19. Protesters preparing for the convention hope to channel the anger on many …

This https://arxiv.org/abs/2402.18060 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions
LLMs have demonstrated impressive performance in answering medical questions, such as passing scores on medical licensing examinations. However, medical board exam questions or general clinical questions do not capture the complexity of realistic clinical cases. Moreover, the lack of reference explanations means we cannot easily evaluate the reasoning of model decisions, a crucial component of supporting doctors in making complex medical decisions. To address these challenges, we construct two …

Fine-tuning Large Language Models with Sequential Instructions
Hanxu Hu, Pinzhen Chen, Edoardo M. Ponti
https://arxiv.org/abs/2403.07794 https://

Fine-tuning Large Language Models with Sequential Instructions
Large language models (LLMs) struggle to follow a sequence of instructions in a single query as they may ignore or misinterpret part of it. This impairs their performance in complex problems whose solution requires multiple intermediate steps, such as multilingual (translate then answer) and multimodal (caption then answer) tasks. We empirically verify this with open-source LLMs as large as LLaMA-2 70B and Mixtral-8x7B. Targeting the scarcity of sequential instructions in present-day data, we p…

Fine-tuning Large Language Models with Sequential Instructions
Hanxu Hu, Pinzhen Chen, Edoardo M. Ponti
https://arxiv.org/abs/2403.07794 https://

Fine-tuning Large Language Models with Sequential Instructions
Large language models (LLMs) struggle to follow a sequence of instructions in a single query as they may ignore or misinterpret part of it. This impairs their performance in complex problems whose solution requires multiple intermediate steps, such as multilingual (translate then answer) and multimodal (caption then answer) tasks. We empirically verify this with open-source LLMs as large as LLaMA-2 70B and Mixtral-8x7B. Targeting the scarcity of sequential instructions in present-day data, we p…

RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback
Yanming Liu, Xinyue Peng, Xuhong Zhang, Weihao Liu, Jianwei Yin, Jiannan Cao, Tianyu Du
https://arxiv.org/abs/2403.06840

RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback
Large language models (LLMs) demonstrate exceptional performance in numerous tasks but still heavily rely on knowledge stored in their parameters. Moreover, updating this knowledge incurs high training costs. Retrieval-augmented generation (RAG) methods address this issue by integrating external knowledge. The model can answer questions it couldn't previously by retrieving knowledge relevant to the query. This approach improves performance in certain scenarios for specific tasks. However, if ir…