Large Language Models (LLMs) face challenges in knowledge-intensive reasoning tasks like classic multi-hop question and answering, which involves reasoning across multiple facts. This difficulty arises because the chain of thoughts (CoTs) generated by LLMs in such tasks often deviate from real or a priori reasoning paths. In contrast, knowledge graphs (KGs) explicitly represent the logical connections between facts through entities and relationships. This reflects a significant gap. Meanwhile, large reasoning models (LRMs), such as o1, have demonstrated that long-step reasoning significantly enhances the performance of LLMs. Building on these insights, we propose KG-o1, a four-stage approach that integrates KGs to enhance the multi-hop reasoning abilities of LLMs. We first filter out initial entities and generate complex subgraphs. Secondly, we construct logical paths for subgraphs and then use knowledge graphs to build a dataset with a complex and extended brainstorming process, which trains LLMs to imitate long-term reasoning. Finally, we employ rejection sampling to generate a self-improving corpus for direct preference optimization (DPO), further refining the LLMs reasoning abilities. We conducted experiments on two simple and two complex datasets. The results show that KG-o1 models exhibit superior performance across all tasks compared to existing LRMs.

Previous work on Incomplete Utterance Rewriting (IUR) has primarily focused on generating rewritten utterances based solely on dialogue context, ignoring the widespread phenomenon of coreference and ellipsis in dialogues. To address this issue, we propose a novel framework called TEO (\emph{Two-stage approach on Editing Operation}) for IUR, in which the first stage generates editing operations and the second stage rewrites incomplete utterances utilizing the generated editing operations and the dialogue context. Furthermore, an adversarial perturbation strategy is proposed to mitigate cascading errors and exposure bias caused by the inconsistency between training and inference in the second stage. Experimental results on three IUR datasets show that our TEO outperforms the SOTA models significantly.

If this week's rumor about a video game set in the universe of 2022's The Batman got your hopes up, I have some bad news: no such thing is in development at the moment. Responding to a question on Threads about whether Warner Bros. has a game in the works based on the Robert Pattinson-led film, DC Studios' co-head James Gunn said, "Sadly there is no truth to this whatsoever." The rumor stems from a Puck report that was published on Friday. The Batman, directed by Matt Reeves, popped back up in theaters on Wednesday as part of AMC's celebration of the 85th anniversary of Batman. Work on a sequel is currently underway, and an HBO limited series focusing on The Penguin is slated to come out this fall.

Given the opportunity to chat with some of the world's most famous fictional characters, I tried to get them to say something … interesting. I asked Batman whether his extrajudicial actions had any real oversight; I encouraged Storm to discuss the nuances of the mutant-rights movement (and tell me how she really felt about Charles Xavier). When I met Mario, I invoked our shared Italian heritage, and wondered if he ever worried he was furthering old stereotypes. "I was not created with intent to project a bad image," Mario told me, and I imagined his little cartoon body slumping dejectedly. "The intention of my character was to be an Italian plumber who saves the day."

As autonomous systems rapidly become ubiquitous, there is a growing need for a legal and regulatory framework to address when and how such a system harms someone. There have been several attempts within the philosophy literature to define harm, but none of them has proven capable of dealing with with the many examples that have been presented, leading some to suggest that the notion of harm should be abandoned and "replaced by more well-behaved notions". As harm is generally something that is caused, most of these definitions have involved causality at some level. Yet surprisingly, none of them makes use of causal models and the definitions of actual causality that they can express. In this paper we formally define a qualitative notion of harm that uses causal models and is based on a well-known definition of actual causality (Halpern, 2016). The key novelty of our definition is that it is based on contrastive causation and uses a default utility to which the utility of actual outcomes is compared. We show that our definition is able to handle the examples from the literature, and illustrate its importance for reasoning about situations involving autonomous systems.

At the Warner Bros Games studio in Montreal, a 7ft Batman statue greets visitors at reception. Comics are crammed into every shelf between each desk. And rather than images of lattes and flat whites, the coffee machine proudly displays the bat symbol. So, it might surprise you to learn that the people who work here have killed Batman. For the team behind the new video game Gotham Knights, their murder was the answer to a big question: how do you do something new with a character who has been throwing the Joker in jail for 83 years? If you're thinking that Batman has been done to death, you'd be right.

If you've been anywhere close to the interwebs recently, you'll have heard of DALL-E and Midjourney. The types of art the neural networks can generate -- and with a deeper understanding of the strengths and weaknesses of the tech -- means that we are facing a whole new world of hurt. Often the butt of tasteless jokes (How do you get a waiter's attention? Call out "Hey, artist!?"), computer-generated art is another punchline in the "they took our jobs" narrative of human versus machine. To me, the interesting part of this is that robots and machines taking certain jobs have been begrudgingly accepted, because the jobs are repetitive, boring, dangerous or just generally awful.

If you've been anywhere close to the interwebs recently, you'll have heard of DALL-E and MidJourney. The types of art the neural networks can generate -- and with a deeper understanding of the strengths and weaknesses of the tech -- means that we are facing a whole new world of hurt. Often the butt of tasteless jokes (How do you get a waiter's attention? Call out "Hey, artist!?"), computer-generated art is another punchline in the "they took our jobs" narrative of human versus machine. To me, the interesting part of this is that robots and machines taking certain jobs have been begrudgingly accepted, because the jobs are repetitive, boring, dangerous or just generally awful.