Large language models (LLMs) have shown excellent capability for solving reasoning problems. Existing approaches do not differentiate the question difficulty when designing prompting methods for them. Clearly, a simple method cannot elicit sufficient knowledge from LLMs to answer a hard question. Meanwhile, a sophisticated one will force the LLM to generate redundant or even inaccurate intermediate steps toward a simple question. Consequently, the performance of existing methods fluctuates among various questions.In this work, we propose Adaption-of-Thought (AdoT), an adaptive method to improve LLMs for the reasoning problem, which first measures the question difficulty and then tailors demonstration set construction and difficulty-adapted retrieval strategies for the adaptive demonstration construction. Experimental results on three reasoning tasks prove the superiority of our proposed method, showing an absolute improvement of up to 5.5% on arithmetic reasoning, 7.4% on symbolic reasoning, and 2.3% on commonsense reasoning. Our codes and implementation details are available at: https://github.com/NLPGM/AdoT

Toxicity detection plays a crucial role in maintaining the peace of the society. Existing methods can be roughly categorized as small language model (SLM) based and large language model (LLM) based. However, due to the limitation of SLMs on general knowledge and the potential embedded bias in LLMs despite their large amount of knowledge, it is not a good idea to detect toxicity only with either SLM or LLM based method.In this work, we propose to implant LLM’s knowledge into SLM based methods such that we can stick to both types of models’ strengths. To this end, we develop a reading comprehension (RC) tree to transfer knowledge between two models. Specifically, we first construct the RC tree, from an extensive to intensive reading perspective, to capture the local and global information in the text. We then model samples encoded by SLM and knowledge extracted from LLM as two distributions using the constructed RT tree. We finally transfer knowledge via optimal transportation between two distributions. Extensive experiments prove the effectiveness of our method on real-world and machine-generated datasets.

Continual relation extraction (CRE) aims to continuously learn relations in new tasks without forgetting old relations in previous tasks.Current CRE methods are all rehearsal-based which need to store samples and thus may encounter privacy and security issues.This paper targets rehearsal-free continual relation extraction for the first time and decomposes it into task identification and within-task prediction sub-problems. Existing rehearsal-free methods focus on training a model (expert) for within-task prediction yet neglect to enhance models’ capability of task identification.In this paper, we propose an Ensemble-of-Experts (EoE) framework for rehearsal-free continual relation extraction. Specifically, we first discriminatively train each expert by augmenting analogous relations across tasks to enhance the expert’s task identification ability. We then propose a cascade voting mechanism to form an ensemble of experts for effectively aggregating their abilities.Extensive experiments demonstrate that our method outperforms current rehearsal-free methods and is even better than rehearsal-based CRE methods.

Large language models (LLMs) have achieved satisfactory performance in counterfactual generation. However, confined by the stochastic generation process of LLMs, there often are misalignments between LLMs and humans which hinder LLMs from handling complex tasks like relation extraction. As a result, LLMs may generate commonsense-violated counterfactuals like ‘eggs were produced by a box’. To bridge this gap, we propose to mimick the episodic memory retrieval, the working mechanism of human hippocampus, to align LLMs’ generation process with that of humans. In this way, LLMs can derive experience from their extensive memory, which keeps in line with the way humans gain commonsense. We then implement two central functions in the hippocampus, i.e., pattern separation and pattern completion, to retrieve the episodic memory from LLMs and generate commonsense counterfactuals for relation extraction. Experimental results demonstrate the improvements of our framework over existing methods in terms of the quality of counterfactuals.

Large language models (LLMs) have made remarkable progress in a wide range of natural language understanding and generation tasks. However, their ability to generate counterfactuals has not been examined systematically. To bridge this gap, we present a comprehensive evaluation framework on various types of NLU tasks, which covers all key factors in determining LLMs’ capability of generating counterfactuals. Based on this framework, we 1) investigate the strengths and weaknesses of LLMs as the counterfactual generator, and 2) disclose the factors that affect LLMs when generating counterfactuals, including both the intrinsic properties of LLMs and prompt designing. The results show that, though LLMs are promising in most cases, they face challenges in complex tasks like RE since they are bounded by task-specific performance, entity constraints, and inherent selection bias. We also find that alignment techniques, e.g., instruction-tuning and reinforcement learning from human feedback, may potentially enhance the counterfactual generation ability of LLMs. On the contrary, simply increasing the parameter size does not yield the desired improvements. Besides, from the perspective of prompt designing, task guidelines unsurprisingly play an important role. However, the chain-of-thought approach does not always help due to inconsistency issues.

Depression is a widespread mental health disorder affecting millions globally. Clinical interviews are the gold standard for assessing depression, but they heavily rely on scarce professional clinicians, highlighting the need for automated detection systems. However, existing methods only capture part of the relevant elements in clinical interviews, unable to incorporate all depressive cues. Moreover, the scarcity of participant data, due to privacy concerns and collection challenges, intrinsically constrains interview modeling. To address these limitations, in this paper, we propose a structural element graph (SEGA), which transforms the clinical interview into an expertise-inspired directed acyclic graph for comprehensive modeling. Additionally, we further empower SEGA by devising novel principle-guided data augmentation with large language models (LLMs) to supplement high-quality synthetic data and enable graph contrastive learning. Extensive evaluations on two real-world clinical datasets, in both English and Chinese, show that SEGA significantly outperforms baseline methods and powerful LLMs like GPT-3.5 and GPT-4.

Recent studies on counterfactual augmented data have achieved great success in the coarse-grained natural language processing tasks. However, existing methods encounter two major problems when dealing with the fine-grained relation extraction tasks. One is that they struggle to accurately identify causal terms under the invariant entity constraint. The other is that they ignore the commonsense constraint. To solve these problems, we propose a novel framework to generate commonsense counterfactuals for stable relation extraction. Specifically, to identify causal terms accurately, we introduce an intervention-based strategy and leverage a constituency parser for correction. To satisfy the commonsense constraint, we introduce the concept knowledge base WordNet and design a bottom-up relation expansion algorithm on it to uncover commonsense relations between entities. We conduct a series of comprehensive evaluations, including the low-resource, out-of-domain, and adversarial-attack settings. The results demonstrate that our framework significantly enhances the stability of base relation extraction models.

Generative models have achieved great success in aspect sentiment triplet extraction tasks. However, existing methods ignore the mutual informative clues between aspect and opinion terms and may generate false paired triplets. Furthermore, the inherent limitations of generative models, i.e., the token-by-token decoding and the simple structured prompt, prevent models from handling complex structures especially multi-word terms and multi-triplet sentences. To address these issues, we propose a sequence labeling enhanced generative model. Firstly, we encode the dependency between aspect and opinion into two bidirectional templates to avoid false paired triplets. Secondly, we introduce a marker-oriented sequence labeling module to improve generative models’ ability of tackling complex structures. Specifically, this module enables the generative model to capture the boundary information of aspect/opinion spans and provides hints to decode multiple triplets with the shared marker. Experimental results on four datasets prove that our model yields a new state-of-art performance. Our code and data are available at https://github.com/NLPWM-WHU/SLGM.

Despite the recent success achieved by several two-stage prototypical networks in few-shot named entity recognition (NER) task, the over-detected false spans at span detection stage and the inaccurate and unstable prototypes at type classification stage remain to be challenging problems. In this paper, we propose a novel Type-Aware Decomposed framework, namely TadNER, to solve these problems. We first present a type-aware span filtering strategy to filter out false spans by removing those semantically far away from type names. We then present a type-aware contrastive learning strategy to construct more accurate and stable prototypes by jointly exploiting support samples and type names as references. Extensive experiments on various benchmarks prove that our proposed TadNER framework yields a new state-of-the-art performance.

Conversational Recommender System (CRS) aims to deliver personalized recommendations through interactive dialogues. Recent advances in prompt learning have shed light on this task. However, the performance of existing methods is confined by the limited context within ongoing conversations. Moreover, these methods utilize training samples only for prompt parameter training. The constructed prompt lacks the ability to refer to the training data during inference, which exacerbates the problem of limited context. To solve this problem, we propose a novel Dynamic Open-book Prompt approach, where the open book stores users’ experiences in historical data, and we dynamically construct the prompt to memorize the user’s current utterance and selectively retrieve relevant contexts from the open book. Specifically, we first build an item-recommendation graph from the open book and convolute on the graph to form a base prompt which contains more information besides the finite dialogue. Then, we enhance the representation learning process of the prompt by tailoring similar contexts in the graph into the prompt to meet the user’s current need. This ensures the prompt provides targeted suggestions that are both informed and contextually relevant. Extensive experimental results on the ReDial dataset demonstrate the significant improvements achieved by our proposed model over the state-of-the-art methods. Our code and data are available at https://github.com/NLPWM-WHU/DOP.

Few-shot relation extraction (FSRE) has been a challenging problem since it only has a handful of training instances. Existing models follow a ‘one-for-all’ scheme where one general large model performs all individual N-way-K-shot tasks in FSRE, which prevents the model from achieving the optimal point on each task. In view of this, we propose a model generation framework that consists of one general model for all tasks and many tiny task-specific models for each individual task. The general model generates and passes the universal knowledge to the tiny models which will be further fine-tuned when performing specific tasks. In this way, we decouple the complexity of the entire task space from that of all individual tasks while absorbing the universal knowledge.Extensive experimental results on two public datasets demonstrate that our framework reaches a new state-of-the-art performance for FRSE tasks. Our code is available at: https://github.com/NLPWM-WHU/GM_GEN.

As a fine-grained task, the annotation cost of aspect term extraction is extremely high. Recent attempts alleviate this issue using domain adaptation that transfers common knowledge across domains. Since most aspect terms are domain-specific, they cannot be transferred directly. Existing methods solve this problem by associating aspect terms with pivot words (we call this passive domain adaptation because the transfer of aspect terms relies on the links to pivots). However, all these methods need either manually labeled pivot words or expensive computing resources to build associations. In this paper, we propose a novel active domain adaptation method. Our goal is to transfer aspect terms by actively supplementing transferable knowledge. To this end, we construct syntactic bridges by recognizing syntactic roles as pivots instead of as links to pivots. We also build semantic bridges by retrieving transferable semantic prototypes. Extensive experiments show that our method significantly outperforms previous approaches.

Aspect-based sentiment analysis (ABSA) involves three subtasks, i.e., aspect term extraction, opinion term extraction, and aspect-level sentiment classification. Most existing studies focused on one of these subtasks only. Several recent researches made successful attempts to solve the complete ABSA problem with a unified framework. However, the interactive relations among three subtasks are still under-exploited. We argue that such relations encode collaborative signals between different subtasks. For example, when the opinion term is “delicious”, the aspect term must be “food” rather than “place”. In order to fully exploit these relations, we propose a Relation-Aware Collaborative Learning (RACL) framework which allows the subtasks to work coordinately via the multi-task learning and relation propagation mechanisms in a stacked multi-layer network. Extensive experiments on three real-world datasets demonstrate that RACL significantly outperforms the state-of-the-art methods for the complete ABSA task.

Aspect term extraction (ATE) aims to extract aspect terms from a review sentence that users have expressed opinions on. Existing studies mostly focus on designing neural sequence taggers to extract linguistic features from the token level. However, since the aspect terms and context words usually exhibit long-tail distributions, these taggers often converge to an inferior state without enough sample exposure. In this paper, we propose to tackle this problem by correlating words with each other through soft prototypes. These prototypes, generated by a soft retrieval process, can introduce global knowledge from internal or external data and serve as the supporting evidence for discovering the aspect terms. Our proposed model is a general framework and can be combined with almost all sequence taggers. Experiments on four SemEval datasets show that our model boosts the performance of three typical ATE methods by a large margin.

The state-of-the-art methods in aspect-level sentiment classification have leveraged the graph based models to incorporate the syntactic structure of a sentence. While being effective, these methods ignore the corpus level word co-occurrence information, which reflect the collocations in linguistics like “nothing special”. Moreover, they do not distinguish the different types of syntactic dependency, e.g., a nominal subject relation “food-was” is treated equally as an adjectival complement relation “was-okay” in “food was okay”. To tackle the above two limitations, we propose a novel architecture which convolutes over hierarchical syntactic and lexical graphs. Specifically, we employ a global lexical graph to encode the corpus level word co-occurrence information. Moreover, we build a concept hierarchy on both the syntactic and lexical graphs for differentiating various types of dependency relations or lexical word pairs. Finally, we design a bi-level interactive graph convolution network to fully exploit these two graphs. Extensive experiments on five bench- mark datasets show that our method outperforms the state-of-the-art baselines.

Aspect-level sentiment classification aims to determine the sentiment polarity of a sentence towards an aspect. Due to the high cost in annotation, the lack of aspect-level labeled data becomes a major obstacle in this area. On the other hand, document-level labeled data like reviews are easily accessible from online websites. These reviews encode sentiment knowledge in abundant contexts. In this paper, we propose a Transfer Capsule Network (TransCap) model for transferring document-level knowledge to aspect-level sentiment classification. To this end, we first develop an aspect routing approach to encapsulate the sentence-level semantic representations into semantic capsules from both the aspect-level and document-level data. We then extend the dynamic routing approach to adaptively couple the semantic capsules with the class capsules under the transfer learning framework. Experiments on SemEval datasets demonstrate the effectiveness of TransCap.

In aspect level sentiment classification, there are two common tasks: to identify the sentiment of an aspect (category) or a term. As specific instances of aspects, terms explicitly occur in sentences. It is beneficial for models to focus on nearby context words. In contrast, as high level semantic concepts of terms, aspects usually have more generalizable representations. However, conventional methods cannot utilize the information of aspects and terms at the same time, because few datasets are annotated with both aspects and terms. In this paper, we propose a novel deep memory network with auxiliary memory to address this problem. In our model, a main memory is used to capture the important context words for sentiment classification. In addition, we build an auxiliary memory to implicitly convert aspects and terms to each other, and feed both of them to the main memory. With the interaction between two memories, the features of aspects and terms can be learnt simultaneously. We compare our model with the state-of-the-art methods on four datasets from different domains. The experimental results demonstrate the effectiveness of our model.

Spam detection has long been a research topic in both academic and industry due to its wide applications. Previous studies are mainly focused on extracting linguistic or behavior features to distinguish the spam and legitimate reviews. Such features are either ineffective or take long time to collect and thus are hard to be applied to cold-start spam review detection tasks. Recent advance leveraged the neural network to encode the textual and behavior features for the cold-start problem. However, the abundant attribute information are largely neglected by the existing framework. In this paper, we propose a novel deep learning architecture for incorporating entities and their inherent attributes from various domains into a unified framework. Specifically, our model not only encodes the entities of reviewer, item, and review, but also their attributes such as location, date, price ranges. Furthermore, we present a domain classifier to adapt the knowledge from one domain to the other. With the abundant attributes in existing entities and knowledge in other domains, we successfully solve the problem of data scarcity in the cold-start settings. Experimental results on two Yelp datasets prove that our proposed framework significantly outperforms the state-of-the-art methods.