Although LLMs have been widely adopted for creative content generation, a single-pass process often struggles to produce high-quality long narratives. How to effectively revise and improve long narrative scripts like scriptwriters remains a significant challenge, as it demands a comprehensive understanding of the entire context to identify global structural issues and local detailed flaws, as well as coordinating revisions at multiple granularities and locations. Direct modifications by LLMs typically introduce inconsistencies between local edits and the overall narrative requirements. To address these issues, we propose Dramaturge, a task and feature oriented divide-and-conquer approach powered by hierarchical multiple LLM agents. It consists of a Global Review stage to grasp the overall storyline and structural issues, a Scene-level Review stage to pinpoint detailed scene and sentence flaws, and a Hierarchical Coordinated Revision stage that coordinates and integrates structural and detailed improvements throughout the script. The top-down task flow ensures that high-level strategies guide local modifications, maintaining contextual consistency. The review and revision workflow follows a coarse-to-fine iterative process, continuing through multiple rounds until no further substantive improvements can be made. Comprehensive experiments show that Dra-maturge significantly outperforms all baselines in terms of script-level overall quality and scene-level details. Our approach is plug-and-play and can be easily integrated into existing methods to improve the generated scripts.

The advanced role-playing capabilities of Large Language Models (LLMs) have paved the way for developing Role-Playing Agents (RPAs). However, existing benchmarks in social interaction such as HPD and SocialBench have not investigated hallucination and face limitations like poor generalizability and implicit judgments for character fidelity. To address these issues, we propose a generalizable, explicit and effective paradigm to unlock the interactive patterns in diverse worldviews. Specifically, we define the interactive hallucination based on stance transfer and construct a benchmark, SHARP, by extracting relations from a general commonsense knowledge graph and leveraging the inherent hallucination properties of RPAs to simulate interactions across roles. Extensive experiments validate the effectiveness and stability of our paradigm. Our findings further explore the factors influencing these metrics and discuss the trade-off between blind loyalty to roles and adherence to facts in RPAs.

The recent success of large language models (LLMs) has attracted widespread interest to develop role-playing conversational agents personalized to the characteristics and styles of different speakers to enhance their abilities to perform both general and special purpose dialogue tasks. However, the ability to personalize the generated utterances to speakers, whether conducted by human or LLM, has not been well studied. To bridge this gap, our study introduces a novel evaluation challenge: speaker verification in agent-generated conversations, which aimed to verify whether two sets of utterances originate from the same speaker. To this end, we assemble a large dataset collection encompassing thousands of speakers and their utterances. We also develop and evaluate speaker verification models under experiment setups. We further utilize the speaker verification models to evaluate the personalization abilities of LLM-based role-playing models. Comprehensive experiments suggest that the current role-playing models fail in accurately mimicking speakers, primarily due to their inherent linguistic characteristics.

Large language models (LLMs) can be used to serve as agents to simulate human behaviors, given the powerful ability to understand human instructions and provide high-quality generated texts. Such ability stimulates us to wonder whether LLMs can simulate a person in a higher form than simple human behaviors. Therefore, we aim to train an agent with the profile, experience, and emotional states of a specific person instead of using limited prompts to instruct ChatGPT API. In this work, we introduce Character-LLM that teach LLMs to act as specific people such as Beethoven, Queen Cleopatra, Julius Caesar, etc. Our method focuses on editing profiles as experiences of a certain character and training models to be personal simulacra with these experiences. To assess the effectiveness of our approach, we build a test playground that interviews trained agents and evaluates whether the agents \textit{memorize} their characters and experiences. Experimental results show interesting observations that help build future simulacra of humankind.

As a Harry Potter fan and a lover of writing, I was curious to see what would happen if I asked ChatGPT (Generative Pretrained Transformer) to write a Harry Potter fan fiction. So, I fed ChatGPT a few prompts and let it do its magic. The result was a piece of fan fiction titled "The Lost Diadem of Ravenclaw", which follows the story of Harry, Ron, and Hermione as they embark on a quest to find the lost diadem of Ravenclaw. The diadem, which is said to enhance the intelligence of its wearer, has been missing for centuries and is believed to be hidden in the Forbidden Forest. As they journey through the forest, the trio encounters a number of obstacles and challenges, including an encounter with a pack of werewolves and a showdown with the infamous Death Eater Bellatrix Lestrange. Despite the challenges they face, Harry, Ron, and Hermione persevere and eventually find the lost diadem.

We have embarked into a new phase in the field of AI/ML. On 29th June 2021, a novel and productive tool -- GitHub Copilot was developed by Microsoft subsidiary GitHub which has taken the internet by storm and has created a great deal of excitement and hype in the developer community. Though the tool isn't publicly available for everyone, there is a lot of buzz and excitement among people to gain access to the technical preview and really see if the is worth the hype that has been created around it! You might be wondering about the title of this blog . I am sure the title might have captivated your attention and brought you here.

CNNs was popularized mostly thanks to the effort of Yann LeCun, now the Director of AI Research at Facebook. In the early 1990s, LeCun worked at Bell Labs, one of the most prestigious research labs in the world at that time, and built a check-recognition system to read handwritten digits. There's a very cool video dated back in 1993 that LeCun showed how the system work right here. This system was actually an entire process for doing end-to-end image recognition. The resulting paper, in which he co-authored with Leon Bottou, Patrick Haffner, and Yoshua Bengio in 1998, introduces convolutional nets as well as the full end-to-end system they built.

It's hard to imagine one Death Eater kissing another one on the cheek while more of Voldemort's supporters gather around them and applaud -- unless you're a computer. Botnik Studios, a company that uses algorithms to train computers to behave in certain ways, has produced a brand new chapter from a new Harry Potter book. While a computer can certainly mimic elements of the famous series, though, it can hardly capture J.K. Rowling's magic -- which is why the result, called Harry Potter and the Portrait of What Looked Like a Large Pile of Ash, is so strange and funny that fans are begging for more. Too funny: Botnik Studios used predictive keyboards to write a new chapter in a new Harry Potter book. It's called Harry Potter and the Portrait of What Looked Like a Large Pile of Ash Has that computer been Confunded?

I trained an LSTM Recurrent Neural Network (a deep learning algorithm) on the first four Harry Potter books. I then asked it to produce a chapter based on what it learned. He looked like Madame Maxime. When she strode up the wrong staircase to visit himself. "I'm afraid I've definitely been suspended from power, no chance -- indeed?" said Snape.