Retrieval-augmented generation (RAG) offers an effective approach for addressing question answering (QA) tasks. However, the imperfections of the retrievers in RAG models often result in the retrieval of irrelevant information, which could introduce noises and degrade the performance, especially when handling multi-hop questions that require multiple steps of reasoning. To enhance the multi-hop reasoning ability of RAG models, we propose TRACE. TRACE constructs knowledge-grounded reasoning chains, which are a series of logically connected knowledge triples, to identify and integrate supporting evidence from the retrieved documents for answering questions. Specifically, TRACE employs a KG Generator to create a knowledge graph (KG) from the retrieved documents, and then uses an Autoregressive Reasoning Chain Constructor to build reasoning chains. Experimental results on three multi-hop QA datasets show that TRACE achieves an average performance improvement of up to 14.03% compared to using all the retrieved documents. Moreover, the results indicate that using reasoning chains as context, rather than the entire documents, is often sufficient to correctly answer questions.

Vice President Kamala Harris on Wednesday explained artificial intelligence as she convened a roundtable with labor and civil rights leaders to talk about the technology. "AI Czar" and Vice President Kamala Harris was ridiculed on social media for her "stunning" description of artificial intelligence on Wednesday. In the latest example of Harris' "word salad" moments, the vice president spoke at the Eisenhower Executive Office Building in Washington, D.C., and gave what people saw as a condescending and long-winded description of AI. "I think the first part of this issue that should be articulated is AI is kind of a fancy thing," Harris said. It means artificial intelligence, but ultimately what it is, is it's about machine learning." She added, "And so, the machine is taught -- and part of the issue here is what information is going into the machine that will then determine -- and we can predict then, if we think about what information is going in, what then will be produced in terms of decisions and opinions that may be made through that process." Vice President Kamala Harris speaks during a meeting with civil rights leaders and consumer protection experts to discuss the societal impact of artificial intelligence, in the Eisenhower Executive Office building in Washington, DC, on July 12, 2023. "So to reduce it down to its most simple point, this is part of the issue that we have here is thinking about what is going into a decision, and then whether that decision is actually legitimate and reflective of the needs and the life experiences of all the people," Kamala concluded. "Kamala Harris talks to Americans like we are all in kindergarten.

Few-shot question answering (QA) aims at precisely discovering answers to a set of questions from context passages while only a few training samples are available. Although existing studies have made some progress and can usually achieve proper results, they suffer from understanding deep semantics for reasoning out the questions. In this paper, we develop Gotta, a Generative prOmpT-based daTa Augmentation framework to mitigate the challenge above. Inspired by the human reasoning process, we propose to integrate the cloze task to enhance few-shot QA learning. Following the recent success of prompt-tuning, we present the cloze task in the same format as the main QA task, allowing the model to learn both tasks seamlessly together to fully take advantage of the power of prompt-tuning. Extensive experiments on widely used benchmarks demonstrate that Gotta consistently outperforms competitive baselines, validating the effectiveness of our proposed prompt-tuning-based cloze task, which not only fine-tunes language models but also learns to guide reasoning in QA tasks. Further analysis shows that the prompt-based loss incorporates the auxiliary task better than the multi-task loss, highlighting the strength of prompt-tuning on the few-shot QA task.

Hello my friend, hope you are well! It's my birthday today and I was supposed to be going for an islands hoping trip, unfortunately due to the rising Covid cases we have no choice but to postpone the plan:'(. Thank you for reading my newsletter . This post is public so feel free to share it. Anyway I was just sharing haha!

The arrival of The Mitchells vs. the Machines on Netflix feels like the detonation of a confetti bomb--it's a colorful, inventive, and all-around delightful movie. In fact, as my colleague Sam Adams wrote for Slate, it's the first great animated movie of 2021. Directed by Mike Rianda and co-directed by Jeff Rowe, the movie stars Abbi Jacobson as Katie, a girl about to head to college, and Danny McBride, Maya Rudolph, and Rianda respectively as her father, mother, and younger brother Aaron, all of whom join her on a road trip in an attempt at a last hurrah before she flies the coop. That trip hits a bit of a road bump, however, when a robot uprising threatens the entire human race. One of the biggest--and funniest--set pieces of the film involves the Mitchell family having to fight a horde of Furby dolls.

When Vic Gundotra left Google in 2014, he thought he might retire, forever. But a lingering interest in wearable technology and machine learning led him to AliveCor, which lets users monitor their heart health from their smartphones. Diving back into the fray of tech, Gundotra is now convinced that the potential of wearables and machine learning is just starting to be unlocked. AliveCor's portable EKG sensor, Kardia, alerts users if their heartbeats are irregular -- and now, the Mayo Clinic, an AliveCor investor, has begun identifying other signals in an EKG reading that a human might miss. "No human doctor can look at your EKG and tell you with a high degree of accuracy what your potassium level is," Gundotra said.