Naoya Inoue

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.

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.

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.

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.

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.

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.

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.

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.

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.