Naoya Inoue

Phuong Minh Nguyen, Tien Huu Dang, Naoya Inoue

Recent studies have shown that Large Language Models (LLMs) can achieve strong reasoning performance by incorporating functional symbolic representations that abstractly describe graph traversal algorithms and step-by-step reasoning in few-shot learning settings. However, it remains unclear how LLMs genuinely understand the abstract meaning of each reasoning step and the overall algorithm from only a limited number of demonstrations. This work aims to localize the attention heads responsible for individual reasoning steps and characterize the types of information transferred among them. We first align constituent reasoning steps with their corresponding token logits under a symbolic-aided Chain-of-Thought (CoT) prompting framework. Our analysis shows that token positions that steer the reasoning process are associated with low confidence scores caused by constraints on satisfying reasoning behavior patterns in demonstrations. We then adopt causal mediation analysis techniques to identify the attention heads responsible for these patterns. In addition, our findings indicate that LLMs retrieve factual and rule-based information for individual sub-reasoning tasks through specialized attention heads (approximately 3% total heads), whereas higher layers predominantly facilitate information integration and the emergence of global reasoning strategies (e.g., graph traversal algorithms) that coordinate multiple intermediate reasoning steps to solve the overall task.

Camélia Guerraoui, Paul Reisert, Naoya Inoue et al.

The use of argumentation in education has been shown to improve critical thinking skills for end-users such as students, and computational models for argumentation have been developed to assist in this process. Although these models are useful for evaluating the quality of an argument, they oftentimes cannot explain why a particular argument is considered poor or not, which makes it difficult to provide constructive feedback to users to strengthen their critical thinking skills. In this survey, we aim to explore the different dimensions of feedback (Richness, Visualization, Interactivity, and Personalization) provided by the current computational models for argumentation, and the possibility of enhancing the power of explanations of such models, ultimately helping learners improve their critical thinking skills.

Farjana Sultana Mim, Naoya Inoue, Shoichi Naito et al.

In argumentative discourse, persuasion is often achieved by refuting or attacking others arguments. Attacking is not always straightforward and often comprise complex rhetorical moves such that arguers might agree with a logic of an argument while attacking another logic. Moreover, arguer might neither deny nor agree with any logics of an argument, instead ignore them and attack the main stance of the argument by providing new logics and presupposing that the new logics have more value or importance than the logics present in the attacked argument. However, no existing studies in the computational argumentation capture such complex rhetorical moves in attacks or the presuppositions or value judgements in them. In order to address this gap, we introduce LPAttack, a novel annotation scheme that captures the common modes and complex rhetorical moves in attacks along with the implicit presuppositions and value judgements in them. Our annotation study shows moderate inter-annotator agreement, indicating that human annotation for the proposed scheme is feasible. We publicly release our annotated corpus and the annotation guidelines.

Nguyen Minh Phuong, Dang Huu Tien, Naoya Inoue

Modern logical reasoning with LLMs primarily relies on employing complex interactive frameworks that decompose the reasoning process into subtasks solved through carefully designed prompts or requiring external resources (e.g., symbolic solvers) to exploit their strong logical structures. While interactive approaches introduce additional overhead, hybrid approaches depend on external components, which limit their scalability. A non-interactive, end-to-end framework enables reasoning to emerge within the model itself -- improving generalization while preserving analyzability without any external resources. In this work, we introduce a non-interactive, end-to-end framework for reasoning tasks. We show that introducing structural information into the few-shot prompt activates a subset of attention heads that patterns aligned with logical reasoning operators. Building on this insight, we propose Attention-Aware Intervention (AAI), an inference-time intervention method that reweights attention scores across selected heads identified by their logical patterns. AAI offers an efficient way to steer the model's reasoning toward leveraging prior knowledge through attention modulation. Extensive experiments show that AAI enhances logical reasoning performance across diverse benchmarks and model architectures, while incurring negligible additional computational overhead. Code is available at https://github.com/phuongnm94/aai_for_logical_reasoning.

Dang Huu-Tien, Minh-Phuong Nguyen, Naoya Inoue

Label noise in datasets could significantly damage the performance and robustness of deep neural networks (DNNs) trained on these datasets. As the size of modern DNNs grows, there is a growing demand for automated tools for detecting such errors. In this paper, we propose post-hoc, model-agnostic noise detection and rectification methods utilizing the penultimate feature from a DNN. Our idea is based on the observation that the similarity between the penultimate feature of a mislabeled data point and its true class data points is higher than that for data points from other classes, making the probability of label occurrence within a tight, similar cluster informative for detecting and rectifying errors. Through theoretical and empirical analyses, we demonstrate that our approach achieves high detection performance across diverse, realistic noise scenarios and can automatically rectify these errors to improve dataset quality. Our implementation is available at https://anonymous.4open.science/r/noise-detection-and-rectification-AD8E.

Hakaze Cho, Yoshihiro Sakai, Mariko Kato et al.

In-Context Learning (ICL) typically utilizes classification criteria from output probabilities of manually selected label tokens. However, we argue that such token-based classification criteria lead to suboptimal decision boundaries, despite delicate calibrations through translation and constrained rotation applied. To address this problem, we propose Hidden Calibration, which renounces token probabilities and uses the nearest centroid classifier on the LM's last hidden states. In detail, we assign the label of the nearest centroid previously estimated from a calibration set to the test sample as the predicted label. Our experiments on 6 models and 10 classification datasets indicate that Hidden Calibration consistently outperforms current token-based baselines by about 20%~50%, achieving a strong state-of-the-art in ICL. Our further analysis demonstrates that Hidden Calibration finds better classification criteria with less inter-class overlap, and LMs provide linearly separable intra-class clusters with the help of demonstrations, which supports Hidden Calibration and gives new insights into the principle of ICL. Our official code implementation can be found at https://github.com/hc495/Hidden_Calibration.

Qin Dai, Naoya Inoue, Ryo Takahashi et al.

This paper explores how the Distantly Supervised Relation Extraction (DS-RE) can benefit from the use of a Universal Graph (UG), the combination of a Knowledge Graph (KG) and a large-scale text collection. A straightforward extension of a current state-of-the-art neural model for DS-RE with a UG may lead to degradation in performance. We first report that this degradation is associated with the difficulty in learning a UG and then propose two training strategies: (1) Path Type Adaptive Pretraining, which sequentially trains the model with different types of UG paths so as to prevent the reliance on a single type of UG path; and (2) Complexity Ranking Guided Attention mechanism, which restricts the attention span according to the complexity of a UG path so as to force the model to extract features not only from simple UG paths but also from complex ones. Experimental results on both biomedical and NYT10 datasets prove the robustness of our methods and achieve a new state-of-the-art result on the NYT10 dataset. The code and datasets used in this paper are available at https://github.com/baodaiqin/UGDSRE.

Tien Dang, The-Hai Nguyen, Dinh Mai Phuong et al.

We consider representation misdirection (RM), a class of LLM unlearning methods that achieves forgetting by manipulating the forget-representations, that is, latent representations of forget samples. Despite being important, the roles of target vectors used in RM, however, remain underexplored. Here, we approach and revisit RM through the lens of the linear representation hypothesis. Specifically, if one can somehow identify a one-dimensional representation corresponding to a high-level concept, the linear representation hypothesis enables linear operations on this concept vector within the forget-representation space. Under this view, we hypothesize that, beyond forgetting, machine unlearning elicits controllable side behaviors and stronger side capabilities corresponding to the high-level concept. Our hypothesis is empirically validated across a wide range of tasks, including behavioral control (e.g., controlling unlearned models' truth, sentiment, and refusal) and capability enhancement (e.g., improving unlearned models' in-context learning capability). Our findings reveal that this fairly attractive phenomenon could be either a hidden risk if misused or a mechanism that can be harnessed for developing models that require stronger capabilities and controllable behaviors.

Dang Huu-Tien, Trung-Tin Pham, Hoang Thanh-Tung et al.

Representation Misdirection for Unlearning (RMU), which steers model representation in the intermediate layer to a target random representation, is an effective method for large language model (LLM) unlearning. Despite its high performance, the underlying cause and explanation remain underexplored. In this paper, we theoretically demonstrate that steering forget representations in the intermediate layer reduces token confidence, causing LLMs to generate wrong or nonsense responses. We investigate how the coefficient influences the alignment of forget-sample representations with the random direction and hint at the optimal coefficient values for effective unlearning across different network layers. We show that RMU unlearned models are robust against adversarial jailbreak attacks. Furthermore, our empirical analysis shows that RMU is less effective when applied to the middle and later layers in LLMs. To resolve this drawback, we propose Adaptive RMU--a simple yet effective alternative method that makes unlearning effective with most layers. Extensive experiments demonstrate that Adaptive RMU significantly improves the unlearning performance compared to prior art while incurring no additional computational cost.

Yufeng Zhao, Yoshihiro Sakai, Naoya Inoue

In-Context Learning (ICL) is suffering from unsatisfactory performance and under-calibration due to high prior bias and unfaithful confidence. Some previous works fine-tuned language models for better ICL performance with enormous datasets and computing costs. In this paper, we propose NoisyICL, simply perturbing the model parameters by random noises to strive for better performance and calibration. Our experiments on two models and 12 downstream datasets show that NoisyICL can help ICL produce more accurate predictions. Our further analysis indicates that NoisyICL enables the model to provide more fair predictions, and also with more faithful confidence. Therefore, we believe that NoisyICL is an effective calibration of ICL. Our experimental code is uploaded to Github.

Tao Jin, Phuong Minh Nguyen, Naoya Inoue

Speculative decoding accelerates large language model inference by drafting multiple candidate tokens and verifying them in a single forward pass. Candidates are organized as a tree: deeper trees accept more tokens per step, but adding depth requires sacrificing breadth (fallback options) under a fixed verification budget. Existing training-free methods draft from a single token source and shape their trees without distinguishing candidate quality across origins. We observe that two common training-free token sources - n-gram matches copied from the input context, and statistical predictions from prior forward passes - differ dramatically in acceptance rate (~6x median gap, range 2-18x across five models and five benchmarks). We prove that when such a quality gap exists, the optimal tree is anisotropic (asymmetric): reliable tokens should form a deep chain while unreliable tokens spread as wide branches, breaking through the depth limit of balanced trees. We realize this structure in GOOSE, a training-free framework that builds an adaptive spine tree - a deep chain of high-acceptance context-matched tokens with wide branches of low-acceptance alternatives at each node. We prove that the number of tokens accepted per step is at least as large as that of either source used alone. On five LLMs (7B-33B) and five benchmarks, GOOSE achieves 1.9-4.3x lossless speedup, outperforming balanced-tree baselines by 12-33% under the same budget.

Haolin Yang, Hakaze Cho, Yiqiao Zhong et al.

The unusual properties of in-context learning (ICL) have prompted investigations into the internal mechanisms of large language models. Prior work typically focuses on either special attention heads or task vectors at specific layers, but lacks a unified framework linking these components to the evolution of hidden states across layers that ultimately produce the model's output. In this paper, we propose such a framework for ICL in classification tasks by analyzing two geometric factors that govern performance: the separability and alignment of query hidden states. A fine-grained analysis of layer-wise dynamics reveals a striking two-stage mechanism: separability emerges in early layers, while alignment develops in later layers. Ablation studies further show that Previous Token Heads drive separability, while Induction Heads and task vectors enhance alignment. Our findings thus bridge the gap between attention heads and task vectors, offering a unified account of ICL's underlying mechanisms.

Dang Huu-Tien, Hoang Thanh-Tung, Anh Bui et al.

Here, we show that current state-of-the-art LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the retain-query. Toward understanding underlying causes, we propose a novel theoretical framework that reframes the unlearning process as backdoor attacks and defenses: forget-tokens act as backdoor triggers that, when activated in retain-queries, cause disruptions in unlearned models' behaviors, similar to successful backdoor attacks. The sense that, LLM unlearning methods themselves poison the model, make it more vulnerable to forget-tokens, and hide rather than erase target knowledge, describes their true mechanism. To mitigate the vulnerability caused by the forgetting process, we reinterpret the retaining process as a backdoor defense and propose Random Noise Augmentation (RNA), a lightweight, model and method-agnostic approach with theoretical guarantees for improving the robustness of models. Extensive experiments demonstrate that RNA significantly improves the robustness of unlearned models while preserving forget and retain performances. This backdoor attack-defense framework offers insights into the mechanism of unlearning that can shed light on future research directions for improving unlearning robustness.

Hakaze Cho, Naoya Inoue

Classification tasks are widely investigated in the In-Context Learning (ICL) paradigm. However, current efforts are evaluated on disjoint benchmarks and settings, while their performances are significantly influenced by some trivial variables, such as prompt templates, data sampling, instructions, etc., which leads to significant inconsistencies in the results reported across various literature, preventing fair comparison or meta-analysis across different papers. Therefore, this paper proposes a standardized and easy-to-use evaluation toolkit (StaICC) for in-context classification. Including, for the normal classification task, we provide StaICC-Normal, selecting 10 widely used datasets, and generating prompts with a fixed form, to mitigate the variance among the experiment implementations. To enrich the usage of our benchmark, we also provide a sub-benchmark StaICC-Diag for diagnosing ICL from several aspects, aiming for a more robust inference processing.

Houjing Wei, Yuting Shi, Naoya Inoue

Vision Large Language Models (VLLMs) usually take input as a concatenation of image token embeddings and text token embeddings and conduct causal modeling. However, their internal behaviors remain underexplored, raising the question of interaction among two types of tokens. To investigate such multimodal interaction during model inference, in this paper, we measure the contextualization among the hidden state vectors of tokens from different modalities. Our experiments uncover a four-phase inference dynamics of VLLMs against the depth of Transformer-based LMs, including (I) Alignment: In very early layers, contextualization emerges between modalities, suggesting a feature space alignment. (II) Intra-modal Encoding: In early layers, intra-modal contextualization is enhanced while inter-modal interaction is suppressed, suggesting a local encoding within modalities. (III) Inter-modal Encoding: In later layers, contextualization across modalities is enhanced, suggesting a deeper fusion across modalities. (IV) Output Preparation: In very late layers, contextualization is reduced globally, and hidden states are aligned towards the unembedding space.

Daichi Haraguchi, Kiyoaki Shirai, Naoya Inoue et al.

Shortcut reasoning is an irrational process of inference, which degrades the robustness of an NLP model. While a number of previous work has tackled the identification of shortcut reasoning, there are still two major limitations: (i) a method for quantifying the severity of the discovered shortcut reasoning is not provided; (ii) certain types of shortcut reasoning may be missed. To address these issues, we propose a novel method for identifying shortcut reasoning. The proposed method quantifies the severity of the shortcut reasoning by leveraging out-of-distribution data and does not make any assumptions about the type of tokens triggering the shortcut reasoning. Our experiments on Natural Language Inference and Sentiment Analysis demonstrate that our framework successfully discovers known and unknown shortcut reasoning in the previous work.

Haolin Yang, Hakaze Cho, Kaize Ding et al.

Large Language Models (LLMs) can perform new tasks from in-context demonstrations, a phenomenon known as in-context learning (ICL). Recent work suggests that these demonstrations are compressed into task vectors (TVs), compact task representations that LLMs exploit for predictions. However, prior studies typically extract TVs from model outputs or hidden states using cumbersome and opaque methods, and they rarely elucidate the mechanisms by which TVs influence computation. In this work, we address both limitations. First, we propose directly training Learned Task Vectors (LTVs), which surpass extracted TVs in accuracy and exhibit superior flexibility-acting effectively at arbitrary layers, positions, and even with ICL prompts. Second, through systematic analysis, we investigate the mechanistic role of TVs, showing that at the low level they steer predictions primarily through attention-head OV circuits, with a small subset of "key heads" most decisive. At a higher level, we find that despite Transformer nonlinearities, TV propagation is largely linear: early TVs are rotated toward task-relevant subspaces to improve logits of relevant labels, while later TVs are predominantly scaled in magnitude. Taken together, LTVs not only provide a practical approach for obtaining effective TVs but also offer a principled lens into the mechanistic foundations of ICL.

Haolin Yang, Hakaze Cho, Naoya Inoue

We investigate the mechanistic underpinnings of in-context learning (ICL) in large language models by reconciling two dominant perspectives: the component-level analysis of attention heads and the holistic decomposition of ICL into Task Recognition (TR) and Task Learning (TL). We propose a novel framework based on Task Subspace Logit Attribution (TSLA) to identify attention heads specialized in TR and TL, and demonstrate their distinct yet complementary roles. Through correlation analysis, ablation studies, and input perturbations, we show that the identified TR and TL heads independently and effectively capture the TR and TL components of ICL. Using steering experiments with geometric analysis of hidden states, we reveal that TR heads promote task recognition by aligning hidden states with the task subspace, while TL heads rotate hidden states within the subspace toward the correct label to facilitate prediction. We further show how previous findings on ICL mechanisms, including induction heads and task vectors, can be reconciled with our attention-head-level analysis of the TR-TL decomposition. Our framework thus provides a unified and interpretable account of how large language models execute ICL across diverse tasks and settings.

Hakaze Cho, Haolin Yang, Gouki Minegishi et al.

In-context Learning (ICL) is an emerging few-shot learning paradigm based on modern Language Models (LMs), yet its inner mechanism remains unclear. In this paper, we investigate the mechanism through a novel perspective of information removal. Specifically, we demonstrate that in the zero-shot scenario, LMs encode queries into non-selective representations in hidden states containing information for all possible tasks, leading to arbitrary outputs without focusing on the intended task, resulting in near-zero accuracy. Meanwhile, we find that selectively removing specific information from hidden states by a low-rank filter effectively steers LMs toward the intended task. Building on these findings, by measuring the hidden states on carefully designed metrics, we observe that few-shot ICL effectively simulates such task-oriented information removal processes, selectively removing the redundant information from entangled non-selective representations, and improving the output based on the demonstrations, which constitutes a key mechanism underlying ICL. Moreover, we identify essential attention heads inducing the removal operation, termed Denoising Heads, which enables the ablation experiments blocking the information removal operation from the inference, where the ICL accuracy significantly degrades, especially when the correct label is absent from the few-shot demonstrations, confirming both the critical role of the information removal mechanism and denoising heads.

Hakaze Cho, Haolin Yang, Brian M. Kurkoski et al.

Existing works are dedicated to untangling atomized numerical components (features) from the hidden states of Large Language Models (LLMs) for interpreting their mechanism. However, they typically rely on autoencoders constrained by some implicit training-time regularization on single training instances (i.e., $L_1$ normalization, top-k function, etc.), without an explicit guarantee of global sparsity among instances, causing a large amount of dense (simultaneously inactive) features, harming the feature sparsity and atomization. In this paper, we propose a novel autoencoder variant that enforces minimal entropy on minibatches of hidden activations, thereby promoting feature independence and sparsity across instances. For efficient entropy calculation, we discretize the hidden activations to 1-bit via a step function and apply gradient estimation to enable backpropagation, so that we term it as Binary Autoencoder (BAE) and empirically demonstrate two major applications: (1) Feature set entropy calculation. Entropy can be reliably estimated on binary hidden activations, which we empirically evaluate and leverage to characterize the inference dynamics of LLMs and In-context Learning. (2) Feature untangling. Similar to typical methods, BAE can extract atomized features from LLM's hidden states. To robustly evaluate such feature extraction capability, we refine traditional feature-interpretation methods to avoid unreliable handling of numerical tokens, and show that BAE avoids dense features while producing the largest number of interpretable ones among baselines, which confirms the effectiveness of BAE serving as a feature extractor.

Hinata Tezuka, Naoya Inoue

Recent studies have suggested a processing framework for multilingual inputs in decoder-based LLMs: early layers convert inputs into English-centric and language-agnostic representations; middle layers perform reasoning within an English-centric latent space; and final layers generate outputs by transforming these representations back into language-specific latent spaces. However, the internal dynamics of such transformation and the underlying mechanism remain underexplored. Towards a deeper understanding of this framework, we propose and empirically validate The Transfer Neurons Hypothesis: certain neurons in the MLP module are responsible for transferring representations between language-specific latent spaces and a shared semantic latent space. Furthermore, we show that one function of language-specific neurons, as identified in recent studies, is to facilitate movement between latent spaces. Finally, we show that transfer neurons are critical for reasoning in multilingual LLMs.

Phuong Minh Nguyen, Tien Huu Dang, Naoya Inoue

This work introduces Symbolic-Aided Chain-of-Thought (CoT), an improved approach to standard CoT, for logical reasoning in large language models (LLMs). The key idea is to integrate lightweight symbolic representations into few-shot prompts, structuring the inference steps with a consistent strategy to make reasoning patterns more explicit within a non-interactive reasoning process. By incorporating these symbolic structures, Symbolic-Aided CoT preserves the generalizability of standard prompting techniques while enhancing the transparency, interpretability, and analyzability of LLM logical reasoning. Extensive experiments on four well-known logical reasoning benchmarks -- ProofWriter, FOLIO, ProntoQA, and LogicalDeduction, which cover diverse reasoning tasks and scenarios -- demonstrate the effectiveness of the proposed approach, particularly in complex reasoning tasks that require navigating multiple constraints or rules. Notably, Symbolic-Aided CoT consistently improves LLMs' reasoning capabilities across various model sizes and significantly outperforms conventional CoT on three out of four datasets, ProofWriter, ProntoQA, and LogicalDeduction.

Hakaze Cho, Peng Luo, Mariko Kato et al.

In-context Learning (ICL) utilizes structured demonstration-query inputs to induce few-shot learning on Language Models (LMs), which are not originally pre-trained on ICL-style data. To bridge the gap between ICL and pre-training, some approaches fine-tune LMs on large ICL-style datasets by an end-to-end paradigm with massive computational costs. To reduce such costs, in this paper, we propose Attention Behavior Fine-Tuning (ABFT), utilizing the previous findings on the inner mechanism of ICL, building training objectives on the attention scores instead of the final outputs, to force the attention scores to focus on the correct label tokens presented in the context and mitigate attention scores from the wrong label tokens. Our experiments on 9 modern LMs and 8 datasets empirically find that ABFT outperforms in performance, robustness, unbiasedness, and efficiency, with only around 0.01% data cost compared to the previous methods. Moreover, our subsequent analysis finds that the end-to-end training objective contains the ABFT objective, suggesting the implicit bias of ICL-style data to the emergence of induction heads. Our work demonstrates the possibility of controlling specific module sequences within LMs to improve their behavior, opening up the future application of mechanistic interpretability.

Mariko Kato, Hakaze Cho, Yoshihiro Sakai et al.

The performance of In-Context Learning (ICL) is highly sensitive to the selected demonstrations. Existing approaches to demonstration selection optimize different objectives, yielding inconsistent results. To address this, we propose a unified metric--affinity and diversity--that leverages ICL model's internal representations. Our experiments show that both affinity and diversity strongly correlate with test accuracies, indicating their effectiveness for demonstration selection. Moreover, we show that our proposed metrics align well with various previous works to unify the inconsistency.

Irfan Robbani, Paul Reisert, Naoya Inoue et al.

Prior research in computational argumentation has mainly focused on scoring the quality of arguments, with less attention on explicating logical errors. In this work, we introduce four sets of explainable templates for common informal logical fallacies designed to explicate a fallacy's implicit logic. Using our templates, we conduct an annotation study on top of 400 fallacious arguments taken from LOGIC dataset and achieve a high agreement score (Krippendorf's alpha of 0.54) and reasonable coverage (0.83). Finally, we conduct an experiment for detecting the structure of fallacies and discover that state-of-the-art language models struggle with detecting fallacy templates (0.47 accuracy). To facilitate research on fallacies, we make our dataset and guidelines publicly available.

Hakaze Cho, Yoshihiro Sakai, Kenshiro Tanaka et al.

In this paper, we investigate the output token probability information in the output embedding of language models. We find an approximate common log-linear encoding of output token probabilities within the output embedding vectors and empirically demonstrate that it is accurate and sparse. As a causality examination, we steer the encoding in output embedding to modify the output probability distribution accurately. Moreover, the sparsity we find in output probability encoding suggests that a large number of dimensions in the output embedding do not contribute to causal language modeling. Therefore, we attempt to delete the output-unrelated dimensions and find more than 30% of the dimensions can be deleted without significant movement in output distribution and sequence generation. Additionally, in the pre-training dynamics of language models, we find that the output embeddings capture the corpus token frequency information in early steps, even before an obvious convergence of parameters starts.

Shohei Higashiyama, Hiroki Ouchi, Hiroki Teranishi et al.

Geoparsing is a fundamental technique for analyzing geo-entity information in text. We focus on document-level geoparsing, which considers geographic relatedness among geo-entity mentions, and presents a Japanese travelogue dataset designed for evaluating document-level geoparsing systems. Our dataset comprises 200 travelogue documents with rich geo-entity information: 12,171 mentions, 6,339 coreference clusters, and 2,551 geo-entities linked to geo-database entries.

Hiroki Ouchi, Hiroyuki Shindo, Shoko Wakamiya et al.

We have constructed NAIST Academic Travelogue Dataset (ATD) and released it free of charge for academic research. This dataset is a Japanese text dataset with a total of over 31 million words, comprising 4,672 Japanese domestic travelogues and 9,607 overseas travelogues. Before providing our dataset, there was a scarcity of widely available travelogue data for research purposes, and each researcher had to prepare their own data. This hinders the replication of existing studies and fair comparative analysis of experimental results. Our dataset enables any researchers to conduct investigation on the same data and to ensure transparency and reproducibility in research. In this paper, we describe the academic significance, characteristics, and prospects of our dataset.

Shoichi Naito, Shintaro Sawada, Chihiro Nakagawa et al.

Providing feedback on the argumentation of the learner is essential for developing critical thinking skills, however, it requires a lot of time and effort. To mitigate the overload on teachers, we aim to automate a process of providing feedback, especially giving diagnostic comments which point out the weaknesses inherent in the argumentation. It is recommended to give specific diagnostic comments so that learners can recognize the diagnosis without misinterpretation. However, it is not obvious how the task of providing specific diagnostic comments should be formulated. We present a formulation of the task as template selection and slot filling to make an automatic evaluation easier and the behavior of the model more tractable. The key to the formulation is the possibility of creating a template set that is sufficient for practical use. In this paper, we define three criteria that a template set should satisfy: expressiveness, informativeness, and uniqueness, and verify the feasibility of creating a template set that satisfies these criteria as a first trial. We will show that it is feasible through an annotation study that converts diagnostic comments given in a text to a template format. The corpus used in the annotation study is publicly available.

Keshav Singh, Naoya Inoue, Farjana Sultana Mim et al.

Most of the existing work that focus on the identification of implicit knowledge in arguments generally represent implicit knowledge in the form of commonsense or factual knowledge. However, such knowledge is not sufficient to understand the implicit reasoning link between individual argumentative components (i.e., claim and premise). In this work, we focus on identifying the implicit knowledge in the form of argumentation knowledge which can help in understanding the reasoning link in arguments. Being inspired by the Argument from Consequences scheme, we propose a semi-structured template to represent such argumentation knowledge that explicates the implicit reasoning in arguments via causality. We create a novel two-phase annotation process with simplified guidelines and show how to collect and filter high-quality implicit reasonings via crowdsourcing. We find substantial inter-annotator agreement for quality evaluation between experts, but find evidence that casts a few questions on the feasibility of collecting high-quality semi-structured implicit reasoning through our crowdsourcing process. We release our materials(i.e., crowdsourcing guidelines and collected implicit reasonings) to facilitate further research towards the structured representation of argumentation knowledge.

Allen Kim, Charuta Pethe, Naoya Inoue et al.

Substantial amounts of work are required to clean large collections of digitized books for NLP analysis, both because of the presence of errors in the scanned text and the presence of duplicate volumes in the corpora. In this paper, we consider the issue of deduplication in the presence of optical character recognition (OCR) errors. We present methods to handle these errors, evaluated on a collection of 19,347 texts from the Project Gutenberg dataset and 96,635 texts from the HathiTrust Library. We demonstrate that improvements in language models now enable the detection and correction of OCR errors without consideration of the scanning image itself. The inconsistencies found by aligning pairs of scans of the same underlying work provides training data to build models for detecting and correcting errors. We identify the canonical version for each of 17,136 repeatedly-scanned books from 58,808 scans. Finally, we investigate methods to detect and correct errors in single-copy texts. We show that on average, our method corrects over six times as many errors as it introduces. We also provide interesting analysis on the relation between scanning quality and other factors such as location and publication year.

Naoya Inoue, Harsh Trivedi, Steven Sinha et al.

How can we generate concise explanations for multi-hop Reading Comprehension (RC)? The current strategies of identifying supporting sentences can be seen as an extractive question-focused summarization of the input text. However, these extractive explanations are not necessarily concise i.e. not minimally sufficient for answering a question. Instead, we advocate for an abstractive approach, where we propose to generate a question-focused, abstractive summary of input paragraphs and then feed it to an RC system. Given a limited amount of human-annotated abstractive explanations, we train the abstractive explainer in a semi-supervised manner, where we start from the supervised model and then train it further through trial and error maximizing a conciseness-promoted reward function. Our experiments demonstrate that the proposed abstractive explainer can generate more compact explanations than an extractive explainer with limited supervision (only 2k instances) while maintaining sufficiency.

Keshav Singh, Paul Reisert, Naoya Inoue et al.

Explicating implicit reasoning (i.e. warrants) in arguments is a long-standing challenge for natural language understanding systems. While recent approaches have focused on explicating warrants via crowdsourcing or expert annotations, the quality of warrants has been questionable due to the extreme complexity and subjectivity of the task. In this paper, we tackle the complex task of warrant explication and devise various methodologies for collecting warrants. We conduct an extensive study with trained experts to evaluate the resulting warrants of each methodology and find that our methodologies allow for high-quality warrants to be collected. We construct a preliminary dataset of 6,000 warrants annotated over 600 arguments for 3 debatable topics. To facilitate research in related downstream tasks, we release our guidelines and preliminary dataset.

Takaki Otake, Sho Yokoi, Naoya Inoue et al.

Events in a narrative differ in salience: some are more important to the story than others. Estimating event salience is useful for tasks such as story generation, and as a tool for text analysis in narratology and folkloristics. To compute event salience without any annotations, we adopt Barthes' definition of event salience and propose several unsupervised methods that require only a pre-trained language model. Evaluating the proposed methods on folktales with event salience annotation, we show that the proposed methods outperform baseline methods and find fine-tuning a language model on narrative texts is a key factor in improving the proposed methods.

Farjana Sultana Mim, Naoya Inoue, Paul Reisert et al.

Existing approaches for automated essay scoring and document representation learning typically rely on discourse parsers to incorporate discourse structure into text representation. However, the performance of parsers is not always adequate, especially when they are used on noisy texts, such as student essays. In this paper, we propose an unsupervised pre-training approach to capture discourse structure of essays in terms of coherence and cohesion that does not require any discourse parser or annotation. We introduce several types of token, sentence and paragraph-level corruption techniques for our proposed pre-training approach and augment masked language modeling pre-training with our pre-training method to leverage both contextualized and discourse information. Our proposed unsupervised approach achieves new state-of-the-art result on essay Organization scoring task.

Pride Kavumba, Naoya Inoue, Benjamin Heinzerling et al.

Pretrained language models, such as BERT and RoBERTa, have shown large improvements in the commonsense reasoning benchmark COPA. However, recent work found that many improvements in benchmarks of natural language understanding are not due to models learning the task, but due to their increasing ability to exploit superficial cues, such as tokens that occur more often in the correct answer than the wrong one. Are BERT's and RoBERTa's good performance on COPA also caused by this? We find superficial cues in COPA, as well as evidence that BERT exploits these cues. To remedy this problem, we introduce Balanced COPA, an extension of COPA that does not suffer from easy-to-exploit single token cues. We analyze BERT's and RoBERTa's performance on original and Balanced COPA, finding that BERT relies on superficial cues when they are present, but still achieves comparable performance once they are made ineffective, suggesting that BERT learns the task to a certain degree when forced to. In contrast, RoBERTa does not appear to rely on superficial cues.

Naoya Inoue, Pontus Stenetorp, Kentaro Inui

Recent studies have revealed that reading comprehension (RC) systems learn to exploit annotation artifacts and other biases in current datasets. This prevents the community from reliably measuring the progress of RC systems. To address this issue, we introduce R4C, a new task for evaluating RC systems' internal reasoning. R4C requires giving not only answers but also derivations: explanations that justify predicted answers. We present a reliable, crowdsourced framework for scalably annotating RC datasets with derivations. We create and publicly release the R4C dataset, the first, quality-assured dataset consisting of 4.6k questions, each of which is annotated with 3 reference derivations (i.e. 13.8k derivations). Experiments show that our automatic evaluation metrics using multiple reference derivations are reliable, and that R4C assesses different skills from an existing benchmark.

Paul Reisert, Benjamin Heinzerling, Naoya Inoue et al.

Constructive feedback is an effective method for improving critical thinking skills. Counter-arguments (CAs), one form of constructive feedback, have been proven to be useful for critical thinking skills. However, little work has been done for constructing a large-scale corpus of them which can drive research on automatic generation of CAs for fallacious micro-level arguments (i.e. a single claim and premise pair). In this work, we cast providing constructive feedback as a natural language processing task and create Riposte!, a corpus of CAs, towards this goal. Produced by crowdworkers, Riposte! contains over 18k CAs. We instruct workers to first identify common fallacy types and produce a CA which identifies the fallacy. We analyze how workers create CAs and construct a baseline model based on our analysis.

Paul Reisert, Naoya Inoue, Naoaki Okazaki et al.

In this paper, we compose a new task for deep argumentative structure analysis that goes beyond shallow discourse structure analysis. The idea is that argumentative relations can reasonably be represented with a small set of predefined patterns. For example, using value judgment and bipolar causality, we can explain a support relation between two argumentative segments as follows: Segment 1 states that something is good, and Segment 2 states that it is good because it promotes something good when it happens. We are motivated by the following questions: (i) how do we formulate the task?, (ii) can a reasonable pattern set be created?, and (iii) do the patterns work? To examine the task feasibility, we conduct a three-stage, detailed annotation study using 357 argumentative relations from the argumentative microtext corpus, a small, but highly reliable corpus. We report the coverage of explanations captured by our patterns on a test set composed of 270 relations. Our coverage result of 74.6% indicates that argumentative relations can reasonably be explained by our small pattern set. Our agreement result of 85.9% shows that a reasonable inter-annotator agreement can be achieved. To assist with future work in computational argumentation, the annotated corpus is made publicly available.