Generative AI has demonstrated unprecedented creativity in the field of computer vision, yet such phenomena have not been observed in natural language processing. In particular, large language models (LLMs) can hardly produce written works at the level of human experts due to the extremely high complexity of literature writing. In this paper, we present HoLLMwood, an automated framework for unleashing the creativity of LLMs and exploring their potential in screenwriting, which is a highly demanding task. Mimicking the human creative process, we assign LLMs to different roles involved in the real-world scenario. In addition to the common practice of treating LLMs as Writer, we also apply LLMs as Editor, who is responsible for providing feedback and revision advice to Writer. Besides, to enrich the characters and deepen the plots, we introduce a role-playing mechanism and adopt LLMs as Actors that can communicate and interact with each other. Evaluations on automatically generated screenplays show that HoLLMwood substantially outperforms strong baselines in terms of coherence, relevance, interestingness and overall quality.

Data annotation is expensive in Task-Oriented Dialogue (TOD) systems. New Intent Discovery (NID) is a task aims to identify novel intents while retaining the ability to recognize known intents. It is essential for expanding the intent base of task-based dialogue systems. Previous works relying on external datasets are hardly extendable. Meanwhile, the effective ones are generally depends on the power of the Large Language Models (LLMs). To address the limitation of model extensibility and take advantages of LLMs for the NID task, we propose LANID, a framework that leverages LLM’s zero-shot capability to enhance the performance of a smaller text encoder on the NID task. LANID employs KNN and DBSCAN algorithms to select appropriate pairs of utterances from the training set. The LLM is then asked to determine the relationships between them. The collected data are then used to construct finetuning task and the small text encoder is optimized with a triplet loss. Our experimental results demonstrate the efficacy of the proposed method on three distinct NID datasets, surpassing all strong baselines in both unsupervised and semi-supervised settings. Our code can be found in https://github.com/floatSDSDS/LANID.

The use of modern Large Language Models (LLMs) as chatbots still has some problems such as hallucinations and lack of empathy. Identifying these issues can help improve chatbot performance. The community has been continually iterating on reference-free dialogue evaluation methods based on large language models (LLMs) that can be readily applied. However, many of these LLM-based metrics require selecting specific datasets and developing specialized training tasks for different evaluation dimensions (e.g., coherence, informative). The developing step can be time-consuming and may need to be repeated for new evaluation dimensions. To enable efficient and flexible adaptation to diverse needs of dialogue evaluation, we propose a dimension-agnostic scoring method that leverages the in-context learning (ICL) capability of LLMs to learn from human scoring to the fullest extent. Our method has three key features. To begin with, rather than manual prompt crafting, we propose automatically generating prompts, allowing the LLM to observe human labels and summarize the most suitable prompt. Additionally, since the LLM has a token limit and ICL is sensitive to demonstration variations, we train a selector to finely customize demonstrations and prompts for each dialogue input. Finally, during inference, we propose to request the LLM multiple times with a subgraph of demonstrations and prompts that are diverse and suitable to maximize ICL from various human scoring. We validate the efficacy of our method on five datasets, even with a small amount of annotated data, our method outperforms all strong baselines. Code is available at https://github.com/iamlxb3/EMNLP2023-ADOROR.

Lyrics generation is a well-known application in natural language generation research, with several previous studies focusing on generating accurate lyrics using precise control such as keywords, rhymes, etc. However, lyrics imitation, which involves writing new lyrics by imitating the style and content of the source lyrics, remains a challenging task due to the lack of a parallel corpus. In this paper, we introduce Sudowoodo, a Chinese lyrics imitation system that can generate new lyrics based on the text of source lyrics. To address the issue of lacking a parallel training corpus for lyrics imitation, we propose a novel framework to construct a parallel corpus based on a keyword-based lyrics model from source lyrics. Then the pairs (new lyrics, source lyrics) are used to train the lyrics imitation model. During the inference process, we utilize a post-processing module to filter and rank the generated lyrics, selecting the highest-quality ones. We incorporated audio information and aligned the lyrics with the audio to form the songs as a bonus. The human evaluation results show that our framework can perform better lyric imitation. Meanwhile, the Sudowoodo system and demo video of the system is available at Sudowoodo and https://youtu.be/u5BBT\_j1L5M

Improving the coherence of long text generation is an important but challenging task. Existing models still struggle to generate a logical and coherent sentence sequence. It is difficult for a model to plan long text generation and avoid generating incoherent texts from a high-level semantic perspective. We speculate that this is due to two factors: (1) current training methods mainly rely on maximum likelihood estimation computed from token-level probability prediction; (2) the role of incoherent texts has been largely under-explored, thus the noised generated texts with errors are out-of-distribution for the model. To address these issues, in this paper, we propose a Contrastive Soft Prompt (CSP) model for improving the coherence of long text generation. It learns text representations in the hidden space for better planning long text generation. To this end, it jointly learns to generate a text representation close to representations of coherent texts and away from incoherent ones, and then generate long text taking this representation as the soft prompt. We conduct experiments on two public story generation datasets, and experiment results show that our method can generate more coherent stories than the state-of-the-art model.

Simile interpretation (SI) and simile generation (SG) are challenging tasks for NLP because models require adequate world knowledge to produce predictions. Previous works have employed many hand-crafted resources to bring knowledge-related into models, which is time-consuming and labor-intensive. In recent years, pre-trained language models (PLMs) based approaches have become the de-facto standard in NLP since they learn generic knowledge from a large corpus. The knowledge embedded in PLMs may be useful for SI and SG tasks. Nevertheless, there are few works to explore it. In this paper, we probe simile knowledge from PLMs to solve the SI and SG tasks in the unified framework of simile triple completion for the first time. The backbone of our framework is to construct masked sentences with manual patterns and then predict the candidate words in the masked position. In this framework, we adopt a secondary training process (Adjective-Noun mask Training) with the masked language model (MLM) loss to enhance the prediction diversity of candidate words in the masked position. Moreover, pattern ensemble (PE) and pattern search (PS) are applied to improve the quality of predicted words. Finally, automatic and human evaluations demonstrate the effectiveness of our framework in both SI and SG tasks.

As neural Text Generation Models (TGM) have become more and more capable of generating text indistinguishable from human-written ones, the misuse of text generation technologies can have serious ramifications. Although a neural classifier often achieves high detection accuracy, the reason for it is not well studied. Most previous work revolves around studying the impact of model structure and the decoding strategy on ease of detection, but little work has been done to analyze the forms of artifacts left by the TGM. We propose to systematically study the forms and scopes of artifacts by corrupting texts, replacing them with linguistic or statistical features, and applying the interpretable method of Integrated Gradients. Comprehensive experiments show artifacts a) primarily relate to token co-occurrence, b) feature more heavily at the head of vocabulary, c) appear more in content word than stopwords, d) are sometimes detrimental in the form of number of token occurrences, e) are less likely to exist in high-level semantics or syntaxes, f) manifest in low concreteness values for higher-order n-grams.

Fake news has become a hotly debated topic in journalism. In this paper, we present our entry to the 2017 Fake News Challenge which models the detection of fake news as a stance classification task that finished in 11th place on the leader board. Our entry is an ensemble system of classifiers developed by students in the context of their coursework. We show how we used the stacking ensemble method for this purpose and obtained improvements in classification accuracy exceeding each of the individual models’ performance on the development data. Finally, we discuss aspects of the experimental setup of the challenge.