Large language models (LLMs) have shown impressive multilingual capabilities through pretraining on diverse corpora. While these models show strong reasoning abilities, their performance varies significantly across languages due to imbalanced training data distribution. Existing approaches using sample-level translation for extensive multilingual pretraining and cross-lingual tuning face scalability challenges and often fail to capture nuanced reasoning processes across languages. In this paper, we introduce **AdaMCoT** (Adaptive Multilingual Chain-of-Thought), a framework that enhances multilingual factual reasoning by dynamically routing thought processes in intermediary “thinking languages” before generating target-language responses. AdaMCoT leverages a language-agnostic core and incorporates an adaptive, reward-based mechanism for selecting optimal reasoning pathways without requiring additional pretraining. Our comprehensive evaluation across multiple benchmarks demonstrates substantial improvements in both factual reasoning quality and cross-lingual consistency, with particularly strong performance gains in low-resource language settings. An in-depth analysis of the model’s hidden states and semantic space further elucidates the underlying mechanism of our method. The results suggest that adaptive reasoning paths can effectively bridge the performance gap between high- and low-resource languages while maintaining cultural and linguistic nuances.

Visual questions are often ambiguous: the same image-question pair may admit multiple valid answers depending on which region is referenced.However, current Visual Question Answering (VQA) systems typically collapse this ambiguity, committing to a single interpretation during decoding and evaluation.In this work, we study visual question ambiguity from a grounded, region-centric perspective.We operationalize ambiguity as the existence of multiple distinct answer-supporting regions in an image, each independently yielding a valid answer.This formulation makes ambiguity observable without requiring exhaustive multi-answer annotations.Based on this definition, we conduct a systematic empirical study of state-of-the-art Visual Large Language Models (VLLMs).We find that, under default decoding, VLLMs consistently under-report ambiguity-even when multiple valid visual groundings are present.Importantly, probing model hidden states reveals that ambiguity-related signals are already encoded in their internal representations, despite not being reliably expressed in outputs.Finally, we show that selectively activating multi-focus answering based on these signals can recover additional valid answers while avoiding excessive hallucination.Together, our results suggest that ambiguity in VQA is not merely an annotation artifact or capability limitation, but a property that VLLMs internally recognize yet often fail to surface under standard decoding assumptions.

Weihua Zheng, Zhengyuan Liu, Tanmoy Chakraborty, Weiwen Xu, Xiaoxue Gao, Bryan Chen Zhengyu Tan, Bowei Zou, Chang Liu, Yujia Hu, Xing Xie, Xiaoyuan Yi, Jing Yao, Chaojun Wang, Long Li, Rui Liu, Huiyao Liu, Koji Inoue, Ryuichi Sumida, Tatsuya Kawahara, Fan Xu, Lingyu Ye, Wei Tian, Dongjun Kim, Jimin Jung, Jaehyung Seo, Nadya Yuki Wangsajaya, Pham Minh Duc, Ojasva Saxena, Palash Nandi, Xiyan Tao, Wiwik Karlina, Tuan Luong, Keertana Arun Vasan, Roy Ka-Wei Lee, Nancy F. Chen. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

This paper tackles the challenges of clustering news articles by main events (MEs) and summarizing these clusters, focusing on diverse languages and localized contexts.Our approach consists of four key contributions.First, we investigate the role of dynamic clustering and the integration of various ME references, including event attributions extracted by language models (LMs), in enhancing event-centric clustering.Second, we propose a data-sharpening framework that optimizes the balance between information volume and entropy in input texts, thereby optimizing generated summaries on multiple indicators.Third, we fine-tune LMs with local news articles for cross-lingual temporal question-answering and text summarization, achieving notable improvements in capturing localized contexts.Lastly, we present the first cross-lingual dataset and comprehensive evaluation metrics tailored for the event-centric news cluster summarization pipeline.Our findings enhance the understanding of news summarization across N-gram, event-level coverage, and faithfulness, providing new insights into leveraging LMs for large-scale cross-lingual and localized news analysis.

Automatic fact-checking systems that employ large language models (LLMs) have achieved human-level performance in combating widespread misinformation. However, current LLM-based fact-checking systems fail to reveal the reasoning principles behind their decision-making for the claim verdict. In this work, we propose Correlation-Enhanced Explainable Fact-Checking (CorXFact), an LLM-based fact-checking system that simulates the reasoning principle of human fact-checkers for evidence-based claim verification: assessing and weighing the correlations between the claim and each piece of evidence. Following this principle, CorXFact enables efficient claim verification and transparent explanation generation. Furthermore, we contribute the CorFEVER test set to comprehensively evaluate the CorXFact system in claim-evidence correlation identification and claim verification in both closed-domain and real-world fact-checking scenarios. Experimental results show that our proposed CorXFact significantly outperforms four strong fact-checking baselines in claim authenticity prediction and verdict explanation.

In an era where rumors can propagate rapidly across social media platforms such as Twitter and Weibo, automatic rumor detection has garnered considerable attention from both academia and industry. Existing multimodal rumor detection models often overlook the intricacies of sample difficulty, e.g., text-level difficulty, image-level difficulty, and multimodal-level difficulty, as well as their order when training. Inspired by the concept of curriculum learning, we propose the Curriculum Learning and Fine-grained Fusion-driven multimodal Rumor Detection (CLFFRD) framework, which employs curriculum learning to automatically select and train samples according to their difficulty at different training stages. Furthermore, we introduce a fine-grained fusion strategy that unifies entities from text and objects from images, enhancing their semantic cohesion. We also propose a novel data augmentation method that utilizes linear interpolation between textual and visual modalities to generate diverse data. Additionally, our approach incorporates deep fusion for both intra-modality (e.g., text entities and image objects) and inter-modality (e.g., CLIP and social graph) features. Extensive experimental results demonstrate that CLFFRD outperforms state-of-the-art models on both English and Chinese benchmark datasets for rumor detection in social media.

The study delves into the construction of entailment trees for science question answering (SQA), employing a novel framework termed Tree-structured Entailment Reasoning (TER). Current research on entailment tree construction presents significant challenges, primarily due to the ambiguities and similarities among candidate science facts, which considerably complicate the fact retrieval process. Moreover, the existing models exhibit limitations in effectively modeling the sequence of reasoning states, understanding the intricate relations between neighboring entailment tree nodes, and generating intermediate conclusions. To this end, we explore enhancing the TER performance from three aspects: First, improving retrieval capabilities by modeling and referring to the chained reasoning states; Second, enhancing TER by infusing knowledge that bridges the gap between reasoning types and rhetorical relations. Third, exploring a task-specific large language model tuning scheme to mitigate deficiencies in intermediate conclusion generation. Experiments on the English EntailmentBank demonstrate the effectiveness of the proposed methods in augmenting the quality of tree-structured entailment reasoning to a certain extent.

For inductive power transfer (IPT) systems, the loosely coupled transformer (LCT) is a crucial component. Variations in the air gap can lead to fluctuations in the parameters of the LCT, such as self-inductance and mutual inductance, caused by positional deviations of the ferrite cores on both sides. However, such variable LCT parameters can damage the resonant tank, thus impacting transmission efficiency and output stability. To address this issue, this paper proposes a self-tuning S/S IPT system based on switch-controlled capacitors (SCCs). The system utilizes gradient descent methods independently on double-side to achieve decoupled tuning control. This approach effectively mitigates the impact of LCT parameter fluctuations without requiring wireless communication. Furthermore, all switches in the system operate at fixed frequencies and implement soft switching. Finally, a prototype is constructed to validate the effectiveness of the proposed system.

Xuan Long Do, Bowei Zou, Shafiq Joty, Tran Tai, Liangming Pan, Nancy Chen, Ai Ti Aw. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Conversational Question Answering (CQA) aims to provide natural language answers to users in information-seeking dialogues.Existing CQA benchmarks often evaluate models using pre-collected human-human conversations.However, replacing the model-predicted dialogue history with ground truth compromises the naturalness and sustainability of CQA evaluation.While previous studies proposed using predicted history and rewriting techniques to address unresolved coreferences and incoherencies, this approach renders the question self-contained from the conversation.In this paper, we propose a novel automatic evaluation approach, interview evaluation.Specifically, ChatGPT acts as the interviewer (Q agent) with a set of carefully designed prompts, and the CQA model under test serves as the interviewee (A agent).During the interview evaluation, questions are dynamically generated by the Q agent to guide the A agent in predicting the correct answer through an interactive process.We evaluated four different models on QuAC and two models on CoQA in our experiments.The experiment results demonstrate that our interview evaluation has advantages over previous CQA evaluation approaches, particularly in terms of naturalness and coherence.The source code is made publicly available.

This paper presents a passive control method utilizing an auxiliary protection circuit for LCC-S compensated converters. The proposed method effectively addresses the challenges of over-load and over-aligned conditions, which can cause excessive inverter output current and higher-than-required system output voltage. By incorporating the auxiliary protection circuit, complex compensated circuits and wireless communication are eliminated, providing a simple and reliable solution. Experimental validation was performed in a 48 V wireless charging prototype to demonstrate the efficacy of the protection strategy in promptly safeguarding the primary circuit against device damage.

We tackle Multi-party Dialogue Reading Comprehension (abbr., MDRC). MDRC stands for an extractive reading comprehension task grounded on a batch of dialogues among multiple interlocutors. It is challenging due to the requirement of understanding cross-utterance contexts and relationships in a multi-turn multi-party conversation. Previous studies have made great efforts on the utterance profiling of a single interlocutor and graph-based interaction modeling. The corresponding solutions contribute to the answer-oriented reasoning on a series of well-organized and thread-aware conversational contexts. However, the current MDRC models still suffer from two bottlenecks. On the one hand, a pronoun like “it” most probably produces multi-skip reasoning throughout the utterances of different interlocutors. On the other hand, an MDRC encoder is potentially puzzled by fuzzy features, i.e., the mixture of inner linguistic features in utterances and external interactive features among utterances. To overcome the bottlenecks, we propose a coreference-aware attention modeling method to strengthen the reasoning ability. In addition, we construct a two-channel encoding network. It separately encodes utterance profiles and interactive relationships, so as to relieve the confusion among heterogeneous features. We experiment on the benchmark corpora Molweni and FriendsQA. Experimental results demonstrate that our approach yields substantial improvements on both corpora, compared to the fine-tuned BERT and ELECTRA baselines. The maximum performance gain is about 2.5%$F\mathbf{1}-\mathbf{score}$. Besides, our MDRC models outperform the state-of-the-art in most cases.

Generative commonsense question answering (GenCQA) is a task of automatically generating a list of answers given a question. The answer list is required to cover all reasonable answers. This presents the considerable challenges of producing diverse answers and ranking them properly. Incorporating a variety of closely-related background knowledge into the encoding of questions enables the generation of different answers. Meanwhile, learning to distinguish positive answers from negative ones potentially enhances the probabilistic estimation of plausibility, and accordingly, the plausibility-based ranking. Therefore, we propose a Knowledge Enhancement and Plausibility Ranking (KEPR) approach grounded on the Generate-Then-Rank pipeline architecture. Specifically, we expand questions in terms of Wiktionary commonsense knowledge of keywords, and reformulate them with normalized patterns. Dense passage retrieval is utilized for capturing relevant knowledge, and different PLM-based (BART, GPT2 and T5) networks are used for generating answers. On the other hand, we develop an ELECTRA-based answer ranking model, where logistic regression is conducted during training, with the aim of approximating different levels of plausibility in a polar classification scenario. Extensive experiments on the benchmark ProtoQA show that KEPR obtains substantial improvements, compared to the strong baselines. Within the experimental models, the T5-based GenCQA with KEPR obtains the best performance, which is up to 60.91% at the primary canonical metric Inc@3. It outperforms the existing GenCQA models on the current leaderboard of ProtoQA.

Leveraging external knowledge to enhance the reasoning ability is crucial for commonsense question answering. However, the existing knowledge bases heavily rely on manual annotation which unavoidably causes deficiency in coverage of world-wide commonsense knowledge. Accordingly, the knowledge bases fail to be flexible enough to support the reasoning over diverse questions. Recently, large-scale language models (LLMs) have dramatically improved the intelligence in capturing and leveraging knowledge, which opens up a new way to address the issue of eliciting knowledge from language models. We propose a Unified Facts Obtaining (UFO) approach. UFO turns LLMs into knowledge sources and produces relevant facts (knowledge statements) for the given question. We first develop a unified prompt consisting of demonstrations that cover different aspects of commonsense and different question styles. On this basis, we instruct the LLMs to generate question-related supporting facts for various commonsense questions via prompting. After facts generation, we apply a dense retrieval-based fact selection strategy to choose the best-matched fact. This kind of facts will be fed into the answer inference model along with the question. Notably, due to the design of unified prompts, UFO can support reasoning in various commonsense aspects (including general commonsense, scientific commonsense, and social commonsense). Extensive experiments on CommonsenseQA 2.0, OpenBookQA, QASC, and Social IQA benchmarks show that UFO significantly improves the performance of the inference model and outperforms manually constructed knowledge sources.

Conversational question generation (CQG) serves as a vital task for machines to assist humans, such as interactive reading comprehension, through conversations. Compared to traditional single-turn question generation (SQG), CQG is more challenging in the sense that the generated question is required not only to be meaningful, but also to align with the provided conversation. Previous studies mainly focus on how to model the flow and alignment of the conversation, but do not thoroughly study which parts of the context and history are necessary for the model. We believe that shortening the context and history is crucial as it can help the model to optimise more on the conversational alignment property. To this end, we propose CoHS-CQG, a two-stage CQG framework, which adopts a novel CoHS module to shorten the context and history of the input. In particular, it selects the top-p sentences and history turns by calculating the relevance scores of them. Our model achieves state-of-the-art performances on CoQA in both the answer-aware and answer-unaware settings.

We tackle Open-Domain Conversational Question Answering (abbr., ODCQA), a task of answering questions in multi-turn conversations by mining clues from a large passage collection. Recent progress in deep learning and large-scale Pre-trained Language Model (PLM) is driving fast-paced advances in ODCQA. However, the typical retriever-reranker-reader (3R) pipeline framework of the existing ODCQA systems suffers from a potential flaw, which is referred to the unavoidable interference from the reader to reranker. Briefly, there are a large number of shareable parameters between the reader and reranker because they share the same PLM-based encoder. During the gradient backpropagation, their directions of updating PLM parameters are most probably inconsistent, which leads to interference in seeking for the optimal solution. In addition, the recent retriever in 3R framework merely utilizes dense representation. Though, dense retrievers are generally weaker than sparse retrievers in lexical matching for rare entities. To address the aforementioned two issues, we first propose to utilize a weak reader to alleviate the interference, and explore three different methods to pursue the goal, including (1) masking gradient, (2) dropping inputs and (3) early stopping. Besides, we propose to hybridize a semantic-sensitive dense retriever and a keyword -sensitive sparse retriever, so as to enhance the robustness of retriever in dealing with rare entities. We conduct extensive experiments on the benchmark corpus OR-QUAC. Experimental results show that our approach outperforms the State-of-The-Art (SoTA) models, yeilding an improvement of 6.1 % F1-score.

In inductive power transfer (IPT) systems, the coils with multiple parallel branches can effectively solve the spatial problem caused by the coil thickness. Traditional compensation methods take the multiple parallel branches as a whole and uses a single capacitor to compensate the reactive power. Current unbalance between the multiple parallel branches has not yet been solved. This paper illustrates the reason for the current imbalance, proposes a current balance compensation method, details the compensation parameter design, and experimentally validate the method and design.

The current aspect extraction methods suffer from boundary errors.These errors lead to a relatively minor difference between the extracted aspects and the ground-truth.However, they hurt the performance severely.In this paper, we propose to utilize a pointer network for repositioning the boundaries.Recycling mechanism is used which enables the training data to be collected without manual intervention.We conduct the experiments on the benchmark datasets SE14 of laptop and SE14-16 of restaurant.Experimental results show that our method achieves substantial improvements over the baseline, and outperforms stateof-the-art methods.

In contrast with the traditional single-grained word segmentation (SWS), where a sentence corresponds to a single word sequence, multi-grained Chinese word segmentation (MWS) aims to segment a sentence into multiple word sequences to preserve all words of different granularities.Due to the lack of manually annotated MWS data, previous work train and tune MWS models only on automatically generated pseudo MWS data.In this work, we further take advantage of the rich word boundary information in existing SWS data and naturally annotated data from dictionary example (DictEx) sentences, to advance the state-of-the-art MWS model based on the idea of weak supervision.Particularly, we propose to accommodate two types of weakly labeled data for MWS, i.e., SWS data and DictEx data by employing a simple yet competitive graph-based parser with local loss.Besides, we manually annotate a high-quality MWS dataset according to our newly compiled annotation guideline, consisting of over 9,000 sentences from two types of texts, i.e., canonical newswire (NEWS) and non-canonical web (BAIKE) data for better evaluation.Detailed evaluation shows that our proposed model with weakly labeled data significantly outperforms the state-of-the-art MWS model by 1.12 and 5.97 on NEWS and BAIKE data in F1.

Reading comprehension (RC) on social media such as Twitter is a critical and challenging task due to its noisy, informal, but informative nature. Most existing RC models are developed on formal datasets such as news articles and Wikipedia documents, which severely limit their performances when directly applied to the noisy and informal texts in social media. Moreover, these models only focus on a certain type of RC, extractive or generative, but ignore the integration of them. To well address these challenges, we come up with a noisy user-generated text-oriented RC model. In particular, we first introduce a set of text normalizers to transform the noisy and informal texts to the formal ones. Then, we integrate the extractive and the generative RC model by a multi-task learning mechanism and an answer selection module. Experimental results on TweetQA demonstrate that our NUT-RC model significantly outperforms the state-of-the-art social media-oriented RC models.

Longxiang Shen, Bowei Zou, Yu Hong, Guodong Zhou, Qiaoming Zhu, AiTi Aw. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Event relation recognition is a challenging language processing task. It is required to determine the relation class of a pair of query events, such as causality, under the condition that there isn’t any reliable clue for use. We follow the traditional statistical approach in this paper, speculating the relation class of the target events based on the relation-class distributions on the similar events. There is minimal supervision used during the speculation process. In particular, we incorporate image processing into the acquisition of similar event instances, including the utilization of images for visually representing event scenes, and the use of the neural network based image matching for approximate calculation between events. We test our method on the ACE-R2 corpus and compared our model with the fully-supervised neural network models. Experimental results show that we achieve a comparable performance to CNN while slightly better than LSTM.

Relation Classification aims to classify the semantic relationship between two marked entities in a given sentence. It plays a vital role in a variety of natural language processing applications. Most existing methods focus on exploiting mono-lingual data, e.g., in English, due to the lack of annotated data in other languages. In this paper, we come up with a feature adaptation approach for cross-lingual relation classification, which employs a generative adversarial network (GAN) to transfer feature representations from one language with rich annotated data to another language with scarce annotated data. Such a feature adaptation approach enables feature imitation via the competition between a relation classification network and a rival discriminator. Experimental results on the ACE 2005 multilingual training corpus, treating English as the source language and Chinese the target, demonstrate the effectiveness of our proposed approach, yielding an improvement of 5.7% over the state-of-the-art.

Bowei Zou, Qiaoming Zhu, Guodong Zhou. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2015.

Due to the commonality in natural language, negation focus plays a critical role in deep understanding of context.However, existing studies for negation focus identification major on supervised learning which is timeconsuming and expensive due to manual preparation of annotated corpus.To address this problem, we propose an unsupervised word-topic graph model to represent and measure the focus candidates from both lexical and topic perspectives.Moreover, we propose a document-sensitive biased Pag-eRank algorithm to optimize the ranking scores of focus candidates.Evaluation on the *SEM 2012 shared task corpus shows that our proposed method outperforms the state of the art on negation focus identification.

Negative expressions are common in natural language text and play a critical role in information extraction. However, the performances of current systems are far from satisfaction, largely due to its focus on intrasentence information and its failure to consider inter-sentence information. In this paper, we propose a graph model to enrich intrasentence features with inter-sentence features from both lexical and topic perspectives. Evaluation on the *SEM 2012 shared task corpus indicates the usefulness of contextual discourse information in negation focus identification and justifies the effectiveness of our graph model in capturing such global information.

Scope detection is a key task in information extraction.This paper proposes a new approach for tree kernel-based scope detection by using the structured syntactic parse information.In addition, we have explored the way of selecting compatible features for different part-of-speech cues.Experiments on the BioScope corpus show that both constituent and dependency structured syntactic parse features have the advantage in capturing the potential relationships between cues and their scopes.Compared with the state of the art scope detection systems, our system achieves substantial improvement.