In this paper, we present HuatuoGPT, a Large Language Model (LLM) for medical consultation. The core recipe of HuatuoGPT is to leverage both distilled data from **ChatGPT** and real-world data from **doctors** in the supervised fine-tuning stage. This is not only because purely using **ChatGPT**-distilled data might cause ‘model collapse’, but also because real-world data from **doctors** would be complementary to **ChatGPT**-distilled data. The responses from ChatGPT are usually detailed, well-presented, fluent, and instruction-followed, but it cannot perform like a doctor in many aspects, e.g. for interactive diagnosis. Therefore, the extra doctors’ data could tame a distilled language model to perform like doctors. To synergize the strengths of both data sources, we introduce RLMF (Reinforcement Learning from Mixed Feedback) where a reward model is trained to align the language model with the merits that both sources (ChatGPT and doctors) bring. Experimental results (in GPT-4 evaluation, human evaluation, and medical benchmark datasets) demonstrate that HuatuoGPT achieves state-of-the-art results in performing medical consultation among open-source LLMs. It is worth noting that by using additional real-world data and RLMF, the distilled language model (i.e., HuatuoGPT) outperforms its teacher model (i.e., ChatGPT) in most cases.
论文检索
输入标题、作者或关键词，从 12,319 篇学术成果中精准定位
Image and Text: Fighting the same Battle? Super Resolution Learning for Imbalanced Text Classification
PDF ↗In this paper, we propose SRL4NLP, a new approach for data augmentation by drawing an analogy between image and text processing: Super-resolution learning. This method is based on using high-resolution images to overcome the problem of low resolution images. While this technique is a common usage in image processing when images have a low resolution or are too noisy, it has never been used in NLP. We therefore propose the first adaptation of this method for text classification and evaluate its effectiveness on urgency detection from tweets posted in crisis situations, a very challenging task where messages are scarce and highly imbalanced. We show that this strategy is efficient when compared to competitive state-of-the-art data augmentation techniques on several benchmarks datasets in two languages.
Existing text summarization systems have made significant progress in recent years, but typically generate summaries in a single step. The one-shot summarization setting is sometimes inadequate, however, as the generated summary may contain hallucinations or overlook important details related to the reader’s interests. In this paper, we address this limitation by proposing SummIt, an iterative text summarization framework based on large language models like ChatGPT. Our framework enables the model to refine the generated summary iteratively through self-evaluation and feedback, closely resembling the iterative process humans undertake when drafting and revising summaries. Furthermore, we explore the potential benefits of integrating knowledge and topic extractors into the framework to enhance summary faithfulness and controllability. We evaluate the performance of our framework on three benchmark summarization datasets through empirical and qualitative analyses. We also conduct a human evaluation to validate the effectiveness of the model’s refinements and find a potential issue of over-correction.
MEGClass: Extremely Weakly Supervised Text Classification via Mutually-Enhancing Text Granularities
PDF ↗Text classification is essential for organizing unstructured text. Traditional methods rely on human annotations or, more recently, a set of class seed words for supervision, which can be costly, particularly for specialized or emerging domains. To address this, using class surface names alone as extremely weak supervision has been proposed. However, existing approaches treat different levels of text granularity (documents, sentences, or words) independently, disregarding inter-granularity class disagreements and the context identifiable exclusively through joint extraction. In order to tackle these issues, we introduce MEGClass, an extremely weakly-supervised text classification method that leverages Mutually-Enhancing Text Granularities. MEGClass utilizes coarse- and fine-grained context signals obtained by jointly considering a document’s most class-indicative words and sentences. This approach enables the learning of a contextualized document representation that captures the most discriminative class indicators. By preserving the heterogeneity of potential classes, MEGClass can select the most informative class-indicative documents as iterative feedback to enhance the initial word-based class representations and ultimately fine-tune a pre-trained text classifier. Extensive experiments on seven benchmark datasets demonstrate that MEGClass outperforms other weakly and extremely weakly supervised methods.
The dialogue systems in customer services have been developed with neural models to provide users with precise answers and round-the-clock support in task-oriented conversations by detecting customer intents based on their utterances. Existing intent detection approaches have highly relied on adaptively pre-training language models with large-scale datasets, yet the predominant cost of data collection may hinder their superiority. In addition, they neglect the information within the conversational responses of the agents, which have a lower collection cost, but are significant to customer intent as agents must tailor their replies based on the customers’ intent. In this paper, we propose RSVP, a self-supervised framework dedicated to task-oriented dialogues, which utilizes agent responses for pre-training in a two-stage manner. Specifically, we introduce two pre-training tasks to incorporate the relations of utterance-response pairs: 1) Response Retrieval by selecting a correct response from a batch of candidates, and 2) Response Generation by mimicking agents to generate the response to a given utterance. Our benchmark results for two real-world customer service datasets show that RSVP significantly outperforms the state-of-the-art baselines by 4.95% for accuracy, 3.4% for MRR@3, and 2.75% for MRR@5 on average. Extensive case studies are investigated to show the validity of incorporating agent responses into the pre-training stage.
CCEval: A Representative Evaluation Benchmark for the Chinese-centric Multilingual Machine Translation
PDF ↗The Chinese-centric Multilingual Machine Translation (MMT) has gained more importance recently due to increasing demands from international business development and cross-cultural exchanges. However, an important factor that limits the progress of this area is the lack of highly representative and high-quality evaluation benchmarks. To fill this gap, we propose CCEval, an impartial and representative Chinese-centric MMT evaluation dataset. This benchmark dataset consists of 2500 Chinese sentences we meticulously selected and processed, and covers more diverse linguistic features as compared to other MMT evaluation benchmarks. These sentences have been translated into 11 languages of various resource levels by professional translators via a rigorously controlled process pipeline to ensure their high quality. We conduct experiments to demonstrate our sampling methodology’s effectiveness in constructing evaluation datasets strongly correlated with human evaluations. The resulting dataset enables better assessments of the Chinese-centric MMT quality. Our CCEval benchmark dataset is available at https://bright.pcl.ac.cn/en/offlineTasks.
Multimodal manga analysis focuses on enhancing manga understanding with visual and textual features, which has attracted considerable attention from both natural language processing and computer vision communities. Currently, most comics are hand-drawn and prone to problems such as missing pages, text contamination, and text aging, resulting in missing comic text content and seriously hindering human comprehension. In other words, the Multimodal Manga Complement (M2C) task has not been investigated, which aims to handle the aforementioned issues by providing a shared semantic space for vision and language understanding. To this end, we first propose the Multimodal Manga Complement task by establishing a new M2C benchmark dataset covering two languages. First, we design a manga argumentation method called MCoT to mine event knowledge in comics with large language models. Then, an effective baseline FVP-M^{2} using fine-grained visual prompts is proposed to support manga complement. Extensive experimental results show the effectiveness of FVP-M^{2} method for Multimodal Mange Complement.
Conspiracy theories, as a type of misinformation, are narratives that explains an event or situation in an irrational or malicious manner. While most previous work examined conspiracy theory in social media short texts, limited attention was put on such misinformation in long news documents. In this paper, we aim to identify whether a news article contains conspiracy theories. We observe that a conspiracy story can be made up by mixing uncorrelated events together, or by presenting an unusual distribution of relations between events. Achieving a contextualized understanding of events in a story is essential for detecting conspiracy theories. Thus, we propose to incorporate an event relation graph for each article, in which events are nodes, and four common types of event relations, coreference, temporal, causal, and subevent relations, are considered as edges. Then, we integrate the event relation graph into conspiracy theory identification in two ways: an event-aware language model is developed to augment the basic language model with the knowledge of events and event relations via soft labels; further, a heterogeneous graph attention network is designed to derive a graph embedding based on hard labels. Experiments on a large benchmark dataset show that our approach based on event relation graph improves both precision and recall of conspiracy theory identification, and generalizes well for new unseen media sources.
Text embedding models have significantly contributed to advancements in natural language processing by adeptly capturing semantic properties of textual data. However, the ability of these models to generalize across a wide range of syntactic contexts remains under-explored. In this paper, we first develop an evaluation set, named SR, to scrutinize the capability for syntax understanding of text embedding models from two crucial syntactic aspects: Structural heuristics, and Relational understanding among concepts, as revealed by the performance gaps in previous studies. Our findings reveal that existing text embedding models have not sufficiently addressed these syntactic understanding challenges, and such ineffectiveness becomes even more apparent when evaluated against existing benchmark datasets. Furthermore, we conduct rigorous analysis to unearth factors that lead to such limitations and examine why previous evaluations fail to detect such ineffectiveness. Lastly, we propose strategies to augment the generalization ability of text embedding models in diverse syntactic scenarios. This study serves to highlight the hurdles associated with syntactic generalization and provides pragmatic guidance for boosting model performance across varied syntactic contexts.
Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems
PDF ↗Recent advancements in Large Language Models empower them to follow freeform instructions, including imitating generic or specific demographic personas in conversations. We define generic personas to represent demographic groups, such as “an Asian person”, whereas specific personas may take the form of specific popular Asian names like “Yumi”. While the adoption of personas enriches user experiences by making dialogue systems more engaging and approachable, it also casts a shadow of potential risk by exacerbating social biases within model responses, thereby causing societal harm through interactions with users. In this paper, we systematically study “persona biases”, which we define to be the sensitivity of dialogue models’ harmful behaviors contingent upon the personas they adopt. We categorize persona biases into biases in harmful expression and harmful agreement, and establish a comprehensive evaluation framework to measure persona biases in five aspects: Offensiveness, Toxic Continuation, Regard, Stereotype Agreement, and Toxic Agreement. Additionally, we propose to investigate persona biases by experimenting with UNIVERSALPERSONA, a systematically constructed persona dataset encompassing various types of both generic and specific model personas. Through benchmarking on four different models- including Blender, ChatGPT, Alpaca, and Vicuna- our study uncovers significant persona biases in dialogue systems. Our findings also underscore the pressing need to revisit the use of personas in dialogue agents to ensure safe application.
Topical Text Classification (TTC) is an ancient, yet timely research area in natural language processing, with many practical applications. The recent dramatic advancements in large LMs raise the question of how well these models can perform in this task in a zero-shot scenario. Here, we share a first comprehensive study, comparing the zero-shot performance of a variety of LMs over TTC23, a large benchmark collection of 23 publicly available TTC datasets, covering a wide range of domains and styles. In addition, we leverage this new TTC benchmark to create LMs that are specialized in TTC, by fine-tuning these LMs over a subset of the datasets and evaluating their performance over the remaining, held-out datasets. We show that the TTC-specialized LMs obtain the top performance on our benchmark, by a significant margin. Our code and model are made available for the community. We hope that the results presented in this work will serve as a useful guide for practitioners interested in topical text classification.
Continual Relation Extraction (CRE) aims to continuously train a model to learn new relations while preserving its ability on previously learned relations. Similar to other continual learning problems, in CRE, models experience representation shift, where learned deep space changes in the continual learning process, which leads to the downgrade in the performance of the old tasks. In this work, we will provide an insight into this phenomenon under the spectral viewpoint. Our key argument is that, for each class shape, if its eigenvectors (or spectral components) do not change much, the shape is well-preserved. We then conduct a spectral experiment and show that, for the shape of each class, the eigenvectors with larger eigenvalue are more preserved after learning new tasks which means these vectors are good at keeping class shapes. Based on this analysis, we propose a simple yet effective class-wise regularization that improve the eigenvalues in the representation learning. We observe that our proposed regularization leads to an increase in the eigenvalues. Extensive experiments on two benchmark datasets, FewRel and TACRED, show the effectiveness of our proposed method with significant improvement in performance compared to the state-of-the-art models. Further analyses also verify our hypothesis that larger eigenvalues lead to better performance and vice versa.
Intent detection is a major task in Natural Language Understanding (NLU) and is the component of dialogue systems for interpreting users’ intentions based on their utterances. Many works have explored detecting intents by assuming that each utterance represents only a single intent. Such systems have achieved very good results; however, intent detection is a far more challenging task in typical real-world scenarios, where each user utterance can be highly complex and express multiple intents. Therefore, in this paper, we propose PCMID, a novel Multi-Intent Detection framework enabled by Prototypical Contrastive Learning under a supervised setting. The PCMID model can learn multiple semantic representations of a given user utterance under the context of different intent labels in an optimized semantic space. Our experiments show that PCMID achieves the current state-of-the-art performance on both multiple public benchmark datasets and a private real-world dataset for the multi-intent detection task.
Multimodal question answering (MMQA), which aims to derive the answer from multiple knowledge modalities (e.g., text, tables, and images), has received increasing attention due to its board applications. Current approaches to MMQA often rely on single-modal or bi-modal QA models, which limits their ability to effectively integrate information across all modalities and leverage the power of pre-trained language models. To address these limitations, we propose a novel framework called UniMMQA, which unifies three different input modalities into a text-to-text format by employing position-enhanced table linearization and diversified image captioning techniques. Additionally, we enhance cross-modal reasoning by incorporating a multimodal rationale generator, which produces textual descriptions of cross-modal relations for adaptation into the text-to-text generation process. Experimental results on three MMQA benchmark datasets show the superiority of UniMMQA in both supervised and unsupervised settings.
Despite the remarkable success of large-scale Language Models (LLMs) such as GPT-3, their performances still significantly underperform fine-tuned models in the task of text classification.This is due to (1) the lack of reasoning ability in addressing complex linguistic phenomena (e.g., intensification, contrast, irony etc); (2) limited number of tokens allowed in in-context learning. In this paper, we introduce Clue And Reasoning Prompting (CARP). CARP adopts a progressive reasoning strategy tailored to addressing the complex linguistic phenomena involved in text classification: CARP first prompts LLMs to find superficial clues (e.g., keywords, tones, semantic relations, references, etc), based on which a diagnostic reasoning process is induced for final decisions. To further address the limited-token issue, CARP uses a fine-tuned model on the supervised dataset for kNN demonstration search in the in-context learning, allowing the model to take the advantage of both LLM’s generalization ability and the task-specific evidence provided by the full labeled dataset. Remarkably, CARP yields new SOTA performances on 4 out of 5 widely-used text-classification benchmarks, 97.39 (+1.24) on SST-2, 96.40 (+0.72) on AGNews, 98.78 (+0.25) on R8 and 96.95 (+0.6) on R52, and a performance comparable to SOTA on MR (92.39 v.s. 93.3). More importantly, we find that CARP delivers impressive abilities on low-resource and domain-adaptation setups. Specifically, using 16 examples per class, CARP achieves comparable performances to supervised models with 1,024 examples per class.
Knowledge Graph Completion (KGC) is crucial for addressing knowledge graph incompleteness and supporting downstream applications. Many models have been proposed for KGC and they can be categorized into two main classes, including triple-based and test-based approaches. Triple-based methods struggle with long-tail entities due to limited structural information and imbalanced distributions of entities. Text-based methods alleviate this issue but require costly training for language models and specific finetuning for knowledge graphs, which limits their efficiency. To alleviate the limitations in the two approaches, in this paper, we propose KICGPT, a framework that integrates a large language model (LLM) and a triple-based KGC retriever, to alleviate the long-tail problem without incurring additional training overhead. In the proposed KICGPT model, we propose an in-context learning strategy called Knowledge Prompt, which encodes structural knowledge into demonstrations to guide LLM. Empirical results on benchmark datasets demonstrate the effectiveness of the proposed KICGPT model with lighter training overhead and no finetuning.
Offensive and toxic text on social media platforms can lead to polarization and divisiveness within online communities and hinders constructive dialogue. Text detoxification is a crucial task in natural language processing to ensure the generation of non-toxic and safe text. Text detoxification is a special case of the Text Style Transfer (TST) problem, where an input text is rephrased to an output text that preserves its content while modifying the style (in this case to a more neutral, non-toxic style). State-of-the-art methods for detoxification use supervised training of encoder-decoder models to produce gold-standard outputs with a standard likelihood-based objective. However, it can be hard for these models to deviate from their pretrained auto-encoder identity mapping. While previous methods have used unlikelihood-based losses to penalize input-to-output copying of toxic content, these methods also unfortunately penalize non-toxic content in the input that would be fine to preserve in the output. To address these issues, we introduce a novel contrastive unlikelihood objective (COUNT) that directly contrasts the gold standard rephrasing with the identity input-to-output mapping to effectively isolate and focus learning on non-toxic style transfer. We benchmark COUNT on two parallel datasets, ParaDetox and APPDIA, showing that it achieves significant improvements in jointly combined fluency, content preservation, and detoxification (i.e., the highest “J” score).
Vision-language (VL) understanding tasks evaluate models’ comprehension of complex visual scenes through multiple-choice questions. However, we have identified two dataset biases that models can exploit as shortcuts to resolve various VL tasks correctly without proper understanding. The first type of dataset bias is Unbalanced Matching bias, where the correct answer overlaps the question and image more than the incorrect answers. The second type of dataset bias is Distractor Similarity bias, where incorrect answers are overly dissimilar to the correct answer but significantly similar to other incorrect answers within the same sample. To address these dataset biases, we first propose Adversarial Data Synthesis (ADS) to generate synthetic training and debiased evaluation data. We then introduce Intra-sample Counterfactual Training (ICT) to assist models in utilizing the synthesized training data, particularly the counterfactual data, via focusing on intra-sample differentiation. Extensive experiments demonstrate the effectiveness of ADS and ICT in consistently improving model performance across different benchmarks, even in domain-shifted scenarios.
Large Language Models Meet Harry Potter: A Dataset for Aligning Dialogue Agents with Characters
PDF ↗In recent years, Dialogue-style Large Language Models (LLMs) such as ChatGPT and GPT4 have demonstrated immense potential in constructing open-domain dialogue agents. However, aligning these agents with specific characters or individuals remains a considerable challenge due to the complexities of character representation and the lack of comprehensive annotations. In this paper, we introduce the Harry Potter Dialogue (HPD) dataset, designed to advance the study of dialogue agents and character alignment. The dataset encompasses all dialogue sessions (in both English and Chinese) from the Harry Potter series and is annotated with vital background information, including dialogue scenes, speakers, character relationships, and attributes. These extensive annotations may empower LLMs to unlock character-driven dialogue capabilities. Furthermore, it can serve as a universal benchmark for evaluating how well can a LLM aligning with a specific character. We benchmark LLMs on HPD using both fine-tuning and in-context learning settings. Evaluation results reveal that although there is substantial room for improvement in generating high-quality, character-aligned responses, the proposed dataset is valuable in guiding models toward responses that better align with the character of Harry Potter.
Representation learning on graph has been demonstrated to be a powerful tool for solving real-world problems. Text-attributed graph carries both semantic and structural information among different types of graphs. Existing works have paved the way for knowledge extraction of this type of data by leveraging language models or graph neural networks or combination of them. However, these works suffer from issues like underutilization of relationships between nodes or words or unaffordable memory cost. In this paper, we propose a Node Representation Update Pre-training Architecture based on Co-modeling Text and Graph (NRUP). In NRUP, we construct a hierarchical text-attributed graph that incorporates both original nodes and word nodes. Meanwhile, we apply four self-supervised tasks for different level of constructed graph. We further design the pre-training framework to update the features of nodes during training epochs. We conduct the experiment on the benchmark dataset ogbn-arxiv. Our method achieves outperformance compared to baselines, fully demonstrating its validity and generalization.