INTERPRETABILITY

CausalNLP Tutorial: An Introduction to Causality for Natural Language Processing (2022.emnlp-tutorials)

Challenge:	Existing approaches to generalize from labeled and unlabeled data are difficult to explain and behave unreliably.
Approach:	They propose a framework for automatic discovery and integration of symbolic rules into pretrained transformer models by using an attention mechanism.
Outcome:	The proposed framework can improve state-of-the-art methods with no manual effort and minimal computational overhead.

Copied to clipboard

Zhijing Jin, Amir Feder, Kun Zhang

Challenge:	Establishing causal relationships is a fundamental goal of scientific research . lack of clear definitions, notations, benchmark datasets, and challenges remains .
Approach:	They introduce the fundamentals of causal discovery and causal effect estimation to the natural language processing audience and provide an overview of causal perspectives to NLP problems.
Outcome:	This tutorial introduces the fundamentals of causal discovery and causal effect estimation to the natural language processing audience and provides an overview of causal perspectives to NLP problems.

Contrastive Data and Learning for Natural Language Processing (2022.naacl-tutorials)

Copied to clipboard

Rui Zhang, Yangfeng Ji, Yue Zhang, Rebecca J. Passonneau

Eidos, INDRA, & Delphi: From Free Text to Executable Causal Models (N19-4)

Challenge:	Current NLP models heavily rely on effective representation learning algorithms.
Approach:	This tutorial introduces contrastive learning and provides an introduction to the techniques.
Outcome:	This tutorial provides an introduction to the fundamentals of contrastive learning approaches and the theory behind them.

Copied to clipboard

Rebecca Sharp, Adarsh Pyarelal, Benjamin Gyori, Keith Alcock, Egoitz Laparra, Marco A. Valenzuela-Escárcega, Ajay Nagesh, Vikas Yadav, John Bachman, Zheng Tang, Heather Lent, Fan Luo, Mithun Paul, Steven Bethard, Kobus Barnard, Clayton Morrison, Mihai Surdeanu

Challenge:	a paper proposes a method for building probabilistic models of complex phenomena such as food insecurity . currently, these models are hand-built for each new situation and require months to construct .
Approach:	They propose an approach that builds executable probabilistic models from raw, free text.
Outcome:	The proposed approach builds executable probabilistic models from raw, free text.

Improve Interpretability of Neural Networks via Sparse Contrastive Coding (2022.findings-emnlp)

Copied to clipboard

Junhong Liu, Yijie Lin, Liang Jiang, Jia Liu, Zujie Wen, Xi Peng

Improving LLM Reasoning through Interpretable Role-Playing Steering (2025.findings-emnlp)

Challenge:	XAI has achieved remarkable advances, but few efforts have been devoted to solving the problem.
Approach:	They propose a model-agnostic explanation method termed Sparse Contrastive Coding . they use model-based explanations to explain the black-box in a more model-oriented way .
Outcome:	The proposed method outperforms five state-of-the-art methods in interpretability and classification metrics.

Copied to clipboard

Anyi Wang, Dong Shu, Yifan Wang, Yunpu Ma, Mengnan Du

Unseen Entity Handling in Complex Question Answering over Knowledge Base via Language Generation (2021.findings-emnlp)

Challenge:	Existing methods for role-playing rely on prompt engineering, which lacks stability and interpretability.
Approach:	They propose a framework that extracts latent representations from role-play prompts and constructs a steering vector that can be injected into the model's residual stream with controllable intensity.
Outcome:	The proposed framework extracts latent representations from role-play prompts, selects the most relevant features based on activation patterns, and constructs a steering vector that can be injected into the model’s residual stream with controllable intensity.

Copied to clipboard

Xin Huang, Jung-Jae Kim, Bowei Zou

Natural Language Interfaces

Challenge:	Existing methods for complex question answering are limited in the search space of all possible relation paths.
Approach:	They propose a method that directly generates an executable SPARQL query without simplification.
Outcome:	The proposed method significantly outperforms the previous methods and has higher interpretability and computational efficiency than the previous ones.

E-VarM: Enhanced Variational Word Masks to Improve the Interpretability of Text Classification Models (2022.coling-1)

Copied to clipboard

Ling Ge, ChunMing Hu, Guanghui Ma, Junshuang Wu, Junfan Chen, JiHong Liu, Hong Zhang, Wenyi Qin, Richong Zhang

Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering (2020.emnlp-main)

Challenge:	Empirical studies show that our approach outperforms the SOTA methods in improving the interpretability of text classification models.
Approach:	They propose an enhanced variational word masks approach that exploits the Variational Information Bottleneck to obtain task-specific words.
Outcome:	Empirical results show that the proposed method outperforms the SOTA methods in improving the interpretability of the model.

Copied to clipboard

Yanlin Feng, Xinyue Chen, Bill Yuchen Lin, Peifeng Wang, Jun Yan, Xiang Ren

Question Answering

Challenge:	Existing work on augmenting question answering models with external knowledge (e.g., knowledge graphs) lacks transparency into the model’s prediction rationale.
Approach:	They propose a knowledge-aware approach that equips pre-trained language models with a multi-hop relational reasoning module that performs multi-relational reasoning over subgraphs extracted from external knowledge graphs.
Outcome:	The proposed model performs multi-hop, multi-relational reasoning over subgraphs extracted from external knowledge graphs.

Infinite SCAN: An Infinite Model of Diachronic Semantic Change (2022.emnlp-main)

Copied to clipboard

Seiichi Inoue, Mamoru Komachi, Toshinobu Ogiso, Hiroya Takamura, Daichi Mochihashi

Topic Modeling

Challenge:	Existing methods for capturing semantic changes using word embeddings cannot account for existence of each sense and its relative importance.
Approach:	They propose a Bayesian model that can estimate the number of senses of words and their changes through time using a dynamic topic model and a logistic stick-breaking process.
Outcome:	The proposed model outperforms the baseline model and investigates the semantic changes of several well-known target words using the CCOHA corpus.

Self-Supervised Rule Learning to Link Text Segments to Relational Elements of Structured Knowledge (2023.findings-emnlp)

Copied to clipboard

Shajith Ikbal, Udit Sharma, Hima Karanam, Sumit Neelam, Ronny Luss, Dheeraj Sreedhar, Pavan Kapanipathi, Naweed Khan, Kyle Erwin, Ndivhuwo Makondo, Ibrahim Abdelaziz, Achille Fokoue, Alexander Gray, Maxwell Crouse, Subhajit Chaudhury, Chitra Subramanian

Coordinating Search-Informed Reasoning and Reasoning-Guided Search in Claim Verification (2026.acl-long)

Challenge:	Various approaches have been tried to map predicate components of a natural language (NL) text segment onto their corresponding predicates within a knowledge base (KB).
Approach:	They propose a neuro-symbolic approach to self-learn rules that serve as interpretable knowledge to perform relation linking in knowledge base question answering systems.
Outcome:	The proposed approach achieves an average performance gain of 17% on CLUTRR and relation linking in a KBQA system.

Copied to clipboard

Qisheng Hu, Quanyu Long, Wenya Wang

OPERA: Operation-Pivoted Discrete Reasoning over Text (2022.naacl-main)

Challenge:	Existing methods for multi-hop claim verification require multi-step reasoning to construct verification chains while iterating for information to uncover hidden bridging facts.
Approach:	They propose a hierarchical agent reasoning and information search model that integrates reasoning and search-informed reasoning.
Outcome:	Experimental results show that HARIS improves multi-hop claim verification accuracy and interpretability.

Copied to clipboard

Yongwei Zhou, Junwei Bao, Chaoqun Duan, Haipeng Sun, Jiahui Liang, Yifan Wang, Jing Zhao, Youzheng Wu, Xiaodong He, Tiejun Zhao

REARANK: Reasoning Re-ranking Agent via Reinforcement Learning (2025.emnlp-main)

Challenge:	Existing methods to predict logical forms ignore the utilization of symbolic operations and lack reasoning ability and interpretability.
Approach:	They propose an operation-pivoted discrete reasoning framework that uses symbolic operations as neural modules to facilitate reasoning ability and interpretability.
Outcome:	Extensive experiments on DROP and RACENum datasets show the reasoning ability of OPERA.

Copied to clipboard

Le Zhang, Bo Wang, Xipeng Qiu, Siva Reddy, Aishwarya Agrawal

Language Models

Challenge:	REARANK is a large language model-based listwise reasoning reranking agent . it explicitly reasons be- fore reranked results, significantly improving performance and interpretability.
Approach:	They propose a large language model-based listwise reasoning reranking agent that explicitly reasons be- fore reranked lists.
Outcome:	The proposed agent outperforms GPT-4 on reasoning-intensive benchmarks and surpasses GPL-4 on BRIGHT benchmarks.

Chinese Live-Streaming E-Commerce Morph Resolution: Datasets and Methods (2026.findings-acl)

Copied to clipboard

Jipeng Qiang, Jiahao Zhu, Yi Zhu, Chaowei Zhang

Discrete Opinion Tree Induction for Aspect-based Sentiment Analysis (2022.acl-long)

Challenge:	Live-stream E-commerce faces significant challenges from morphs, deliberate linguistic variants used to evade real-time voice filters and amplify product claims illegally.
Approach:	They propose a framework that resolves morphs and generates structured explanations . they propose morph-aware dual-output refinement framework that detects inconsistencies .
Outcome:	The proposed framework improves morph resolution accuracy and interpretability.

Copied to clipboard

Chenhua Chen, Zhiyang Teng, Zhongqing Wang, Yue Zhang

Sentiment Analysis

Challenge:	Dependency trees are used for aspect-based sentiment classification but are not optimized for aspect classification.
Approach:	They propose an aspect-specific and language-agnostic discrete latent opinion tree model as an alternative structure to explicit dependency trees.
Outcome:	The proposed model can achieve competitive performance and interpretability on six English benchmarks and one Chinese dataset.

Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis (2021.naacl-main)

Copied to clipboard

Xiao Liu, Da Yin, Yansong Feng, Yuting Wu, Dongyan Zhao

Structured Data in NLP

Challenge:	Existing studies focus on analyzing structured data, while mining causal relationship among factors from unstructured data is of great importance.
Approach:	They propose a graph-based causal inference framework which builds causal graphs from fact descriptions without much human involvement.
Outcome:	The proposed framework can capture nuance from fact descriptions among confusing charges and provide explainable discrimination in few-shot settings.

TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors (2026.acl-long)

Copied to clipboard

Ido Andrew Atad, Itamar Zimerman, Shahar Katz, Lior Wolf

Language Models

Challenge:	Existing attention-aggregation methods focus on individual attention heads or layers, failing to account for the model’s global behavior.
Approach:	They propose a unified attention representation that captures the entire transformer as a single, input-dependent linear operator expressed through a high-order attention-interaction tensor.
Outcome:	The proposed model encapsulates the entire transformer as a single, input-dependent linear operator expressed through a high-order attention-interaction tensor.

Improving Grammar-based Sequence-to-Sequence Modeling with Decomposition and Constraints (2023.acl-short)

Copied to clipboard

Chao Lou, Kewei Tu

Language Models

Challenge:	Neural QCFG excels in interpretability and generalization but suffers from expensive inference.
Approach:	They propose to use a symbolic grammar to create QCFGs with a quasisynchronous context-free grammar that is parameterized by neural networks to perform faster inference.
Outcome:	The proposed models outperform vanilla Neural QCFG in most settings.

LLM-XTM: Enhancing Cross-Lingual Topic Models with Large Language Models (2026.acl-long)

Copied to clipboard

Minh Chu Xuan, Tien-Phat Nguyen, Linh Ngo Van, Dinh Viet Sang, Nguyen Thi Ngoc Diep, Trung Le

Multilinguality

Challenge:	Existing cross-lingual topic models depend on sparse bilingual resources and often yield incoherent or weakly aligned topics.
Approach:	They propose a framework that integrates LLM-guided topic refinement with self-consistency uncertainty quantification to enable black-box, stable, and scalable enhancement of cross-lingual topic models.
Outcome:	Experiments on multilingual corpora show that the proposed framework achieves superior topic coherence and alignment while reducing reliance on bilingual dictionaries and expensive LLM calls.

Exploring Question Guidance and Answer Calibration for Visually Grounded Video Question Answering (2024.findings-emnlp)

Copied to clipboard

Yuanxing Xu, Yuting Wei, Shuai Zhong, Xinming Chen, Jinsheng Qi, Bin Wu

Visual Data in NLP

Challenge:	Existing methods for videoQA lack temporal localization labels, leading to inaccurate localization.
Approach:	They propose a Question-Guided and Answer-Calibrated TRansformer which guides and calibrates localization using question and option texts without localization labels.
Outcome:	The proposed model achieves comparable accuracy to large-scale pretrained models and leads in localization aspects.

Reasoning-Oriented and Analogy-Based Methods for Locating and Editing in Zero-Shot Event-Relational Reasoning (2025.coling-main)

Copied to clipboard

Jingyao Tang, Lishuang Li, Liteng Mi, Haiming Wu, Hongbin Lu

Attending via both Fine-tuning and Compressing (2021.findings-acl)

Challenge:	Existing methods for zero-shot event-relational reasoning require large computational resources and lack interpretability.
Approach:	They propose a method for Reasoning-Oriented Locating and Editing which locates and edits key modules of the language model for reasoning about event relations.
Outcome:	The proposed method improves interpretability and efficiency with reduced computational cost and achieves SOTA results in zero-shot event-relational reasoning.

Copied to clipboard

Jie Zhou, Yuanbin Wu, Qin Chen, Xuanjing Huang, Liang He

Reasoning with Trees: Faithful Question Answering over Knowledge Graph (2025.coling-main)

Challenge:	Existing studies show that attention mechanisms can improve models' interpretation, but they are not explicable.
Approach:	They propose a framework consisting of a learner and a compressor to purify attention scores . they propose to fine-tune and compress the attention mechanism to obtain a more faithful explanation .
Outcome:	The proposed framework improves performance and interpretability on eight benchmark datasets.

Copied to clipboard

Tiesunlong Shen, Jin Wang, Xuejie Zhang, Erik Cambria

Knowledge Representation

Challenge:	Recent advances in large language models (LLMs) have shown remarkable progress in reasoning capabilities, yet they still face challenges in complex, multi-step reasoning tasks.
Approach:	They propose a framework that synergistically integrates LLMs with knowledge graphs (KGs) to enhance reasoning performance and interpretability.
Outcome:	The proposed framework outperforms existing state-of-the-art methods on two benchmark KGQA datasets and improves on the MCTS process.

From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment (2021.emnlp-main)

Copied to clipboard

Xin Mao, Wenting Wang, Yuanbin Wu, Man Lan

Improving Reward Models with Synthetic Critiques (2025.findings-naacl)

Challenge:	Existing methods for cross-lingual entity alignment rely on lexical matching and probability reasoning, but they inherit poor interpretability and low efficiency from neural networks.
Approach:	They propose a simple but effective unsupervised entity alignment method without neural networks that can be used to find the equivalent entities between crosslingual KGs.
Outcome:	Extensive experiments show that the proposed method beats advanced supervised methods across all datasets while having high efficiency, interpretability, and stability.

Copied to clipboard

Zihuiwen Ye, Fraser David Greenlee, Max Bartolo, Phil Blunsom, Jon Ander Campos, Matthias Gallé

Robustness in NLP

Challenge:	a recent study shows that reward models overfit on superficial features, hindering generalization performance . prevailing approach to training preference-based reward models presents several challenges .
Approach:	They propose a method that uses synthetic natural language critiques to provide additional feedback to large language models.
Outcome:	The proposed approach improves performance and data efficiency of RMs initialized from different pretrained models, reducing the reliance on costly human annotations.

MCLE-Mol: Empowering LLM with Molecular Comprehension and Low-Cost Continual Evolution for Interpretable Property Prediction (2026.findings-acl)

Copied to clipboard

Zhili Pu, Lantian Zhang, Hao Duan, Zhixing Zhang, Keyun Zhu, Yongqi Fan, Ruihui Hou, Tong Ruan, Yun Tang

Towards Interpretable Clinical Diagnosis with Bayesian Network Ensembles Stacked on Entity-Aware CNNs (2020.acl-main)

Challenge:	Large language models (LLMs) offer a new paradigm for molecular property prediction (MPP), yet a semantic gap between natural language and molecul representations limits their ability to capture structure–activity relationships (SAR).
Approach:	They propose an ML–LLM–Rule collaborative framework for MPP that injects ML-derived substructure attribution values into LLMs and calibrates them under specific chemical contexts.
Outcome:	The proposed framework outperforms baseline models on multiple benchmark datasets and is highly interpretable.

Copied to clipboard

Jun Chen, Xiaoya Dai, Quan Yuan, Chao Lu, Haifeng Huang

DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation (2025.findings-emnlp)

Challenge:	a novel framework for text-based diagnosis of diseases requires appropriate balance between accuracy and interpretability.
Approach:	They propose a framework that stacks Bayesian Network Ensembles on top of CNN to build an accurate yet interpretable diagnosis system.
Outcome:	The proposed framework outperforms the previous automatic diagnosis methods in accuracy performance and the diagnosis explanation of the framework is reasonable.

Copied to clipboard

Abdelrahman Abdallah, Jamshid Mozafari, Bhawna Piryani, Adam Jatowt

Controllable Chest X-Ray Report Generation from Longitudinal Representations (2023.findings-emnlp)

Challenge:	DeAR is an open-source framework that decouples the tasks of LLMs with holistic cross-document analysis.
Approach:	They propose an open-source framework that decouples relevance scoring with holistic cross-document analysis.
Outcome:	The proposed framework outperforms open-source frameworks in QA and open-domain QA.

Copied to clipboard

Francesco Dalla Serra, Chaoyang Wang, Fani Deligianni, Jeff Dalton, Alison O’Neil

Learning to Judge: LLMs Designing and Applying Evaluation Rubrics (2026.findings-eacl)

Challenge:	Radiology reports are detailed text descriptions of the content of medical scans.
Approach:	They propose a method to align, concatenate and fuse the current and prior visual information into a joint longitudinal representation which can be provided to a multimodal report generation model.
Outcome:	The proposed method achieves state-of-the-art results while enabling anatomy-wise controllable report generation.

Copied to clipboard

Clemencia Siro, Pourya Aliannejadi, Mohammad Aliannejadi

Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications (N19-1)

Challenge:	Large language models are increasingly used as evaluators for natural language generation . human rubrics are often static and misaligned with how models internally represent language quality.
Approach:	They propose to use large language models to generate interpretable and task-aware evaluation dimensions and apply them within models.
Outcome:	The proposed model improves the semantic coherence and scoring reliability of LLM-defined criteria and their alignment with human criteria.

Copied to clipboard

Pouya Pezeshkpour, Yifan Tian, Sameer Singh

Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers (2020.emnlp-main)

Challenge:	Existing approaches focus on improving accuracy and overlook other aspects such as robustness and interpretability.
Approach:	They propose adversarial modifications for link prediction models that identify influential facts and evaluate their sensitivity to addition of fake facts.
Outcome:	The proposed model evaluates the robustness of the model to the addition of fake facts and the interpretability of the models.

Copied to clipboard

Hanjie Chen, Yangfeng Ji

A Knowledge Graph Reasoning-Based Model for Computerized Adaptive Testing (2025.coling-main)

Challenge:	Existing methods for improving model interpretability require prior information or human annotations as additional inputs.
Approach:	They propose a variational word mask method to automatically learn task-specific important words and reduce irrelevant information on classification, which ultimately improves model interpretability.
Outcome:	The proposed method improves model prediction accuracy and interpretability on seven datasets.

Copied to clipboard

Xinyi Qiu, Zhiyun Chen

Towards Structure-aware Paraphrase Identification with Phrase Alignment Using Sentence Encoders (2022.coling-1)

Challenge:	Existing studies have failed to account for the differences in concept relevance when a question involves multiple concepts .
Approach:	They propose a Knowledge Graph Reasoning-Based Model for CAT that captures semantic and relational information between concepts and questions and incorporates multiple evaluation objectives.
Outcome:	The proposed model outperforms existing methods on three authentic educational datasets.

Copied to clipboard

Qiwei Peng, David Weir, Julie Weeds

Disentangled Code Representation Learning for Multiple Programming Languages (2021.findings-acl)

Challenge:	Existing paraphrase identification datasets exhibit high correlation between positive pairs and the degree of their lexical overlap.
Approach:	They propose to combine sentence encoders with an alignment component by representing each sentence as a list of predicate-argument spans and decomposing the sentence-level meaning comparison into the alignment between their spans.
Outcome:	The proposed approach improves performance and interpretability for various sentence encoders.

Copied to clipboard

Jingfeng Zhang, Haiwen Hong, Yin Zhang, Yao Wan, Ye Liu, Yulei Sui

Video Question Answering: Datasets, Algorithms and Challenges (2022.emnlp-main)

Challenge:	Developing effective distributed representations of source code is challenging . current code embedding approaches that represent the semantic and syntax of code are less interpretable .
Approach:	They propose a disentangled code representation learning approach to separate the semantic from the syntax of source code under a multi-programming-language setting.
Outcome:	The proposed approach achieves better interpretability and generalizability over existing methods.

Copied to clipboard

Yaoyao Zhong, Wei Ji, Junbin Xiao, Yicong Li, Weihong Deng, Tat-Seng Chua

Dual Capsule Attention Mask Network with Mutual Learning for Visual Question Answering (2022.coling-1)

Challenge:	Recent advances in video question answering have led to a surge in popularity . despite the popularity, VideoQA remains one of the greatest challenges .
Approach:	They categorize the video question-answer datasets into normal VideoQA, multi-modal VideoQA and knowledge-based VideoQA according to the modalities invoked in the question-announcement pairs.
Outcome:	The proposed methods are mainly designed for Factoid QA and inference VideoQA . the proposed methods have been compared with other methods and are robust and interpretable.

Copied to clipboard

Weidong Tian, Haodong Li, Zhong-Qiu Zhao

UniRPG: Unified Discrete Reasoning over Table and Text as Program Generation (2022.emnlp-main)

Challenge:	Visual Question Answering (VQA) models extract features from images and questions independently, but these methods fail to capture fine-grained key features and include much unnecessary information.
Approach:	They propose a dual capsule attention mask network with mutual learning for visual question answering (VQA) it contains two branches processing coarse-grained features and fine-grain features, respectively.
Outcome:	The proposed model outperforms baselines in terms of performance and interpretability and achieves new SOTA performance on the VQA-v2 dataset.

Copied to clipboard

Yongwei Zhou, Junwei Bao, Chaoqun Duan, Youzheng Wu, Xiaodong He, Tiejun Zhao

Praetor: A Fine-Grained Generative LLM Evaluator with Instance-Level Customizable Evaluation Criteria (2025.acl-long)

Challenge:	Existing methods for question answering using knowledge resources are mixed-of-experts and semantic parsing-based.
Approach:	They propose a semantic-parsing-based approach to perform Unified discrete Reasoning over heterogeneous knowledge resources as Program Generation.
Outcome:	The proposed approach improves interpretability and scalability over table and text . it achieves promising performance on the TAT-QA dataset without annotation .

Copied to clipboard

Yongqi Leng, Renren Jin, Yue Chen, Zhuowen Han, Ling Shi, Jianxiang Peng, Lei Yang, Juesi Xiao, Deyi Xiong

Challenge:	Existing evaluation methods are inadequate to evaluate large language models (LLMs).
Approach:	They propose a fine-grained generative LLM evaluator with instance-level customazable evaluation criteria that can be used to evaluate large language models.
Outcome:	The proposed model outperforms existing LLM evaluators and instruction-tuned LLMs on multiple benchmarks and sets new SOTA results.

Reason first, then respond: Modular Generation for Knowledge-infused Dialogue (2022.findings-emnlp)

Copied to clipboard

Leonard Adolphs, Kurt Shuster, Jack Urbanek, Arthur Szlam, Jason Weston

Natural Language Interfaces

Challenge:	Large language models can produce fluent dialogue but often hallucinate factual inaccuracies.
Approach:	They propose a modular model for incorporating knowledge into conversational agents that generates a knowledge sequence and then attends to its own generated knowledge sequence.
Outcome:	The proposed model hallucinates less in knowledge-grounded dialogue tasks and has advantages in terms of interpretability and modularity.

GuessArena: Guess Who I Am? A Self-Adaptive Framework for Evaluating LLMs in Domain-Specific Knowledge and Reasoning (2025.acl-long)

Copied to clipboard

Qingchen Yu, Zifan Zheng, Ding Chen, Simin Niu, Bo Tang, Feiyu Xiong, Zhiyu Li

DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering (2023.acl-long)

Challenge:	Existing evaluation methods for large language models rely on static benchmarks and standardized evaluation protocols.
Approach:	They propose an adaptive evaluation framework that integrates dynamic domain knowledge modeling with progressive reasoning assessment to improve evaluation fidelity.
Outcome:	Empirical results show that the framework distinguishes LLMs in terms of domain knowledge coverage and reasoning chain completeness.

Copied to clipboard

Pei Ke, Fei Huang, Fei Mi, Yasheng Wang, Qun Liu, Xiaoyan Zhu, Minlie Huang

Fuzzy Reasoning Chain (FRC): An Innovative Reasoning Framework from Fuzziness to Clarity (2025.findings-emnlp)

Challenge:	Existing evaluation metrics for natural language generation (NLG) tasks face the challenges on generalization ability and interpretability.
Approach:	They propose a metric that evaluates natural language generation tasks as an instruction-style question answering task and utilizes instruction-tuned pre-trained language models without training on evaluation datasets.
Outcome:	The proposed metric achieves state-of-the-art performance in untrained metrics for evaluating text summarization and dialogue generation, which exhibits strong dimension-level / task-level generalization ability and interpretability.

Copied to clipboard

Ping Chen, Xiang Liu, Zhaoxiang Liu, Zezhou Chen, Xingpeng Zhang, Huan Hu, Zipeng Wang, Kai Wang, Shuming Shi, Shiguo Lian

EROS:Entity-Driven Controlled Policy Document Summarization (2024.lrec-main)

Challenge:	ambiguity, polysemy, or uncertainty remain significant challenges in natural language processing.
Approach:	They introduce a framework that integrates LLM semantic priors with continuous fuzzy membership degrees to create an explicit interaction between probability-based reasoning and fuzzy membership reasoning.
Outcome:	The proposed framework integrates semantic priors with continuous fuzzy membership degrees . it allows ambiguous inputs to be gradually transformed into clear and interpretable decisions .

Copied to clipboard

Joykirat Singh, Sehban Fazili, Rohan Jain, Md. Shad Akhtar

Information Extraction & Text Mining

Challenge:	a privacy policy is a crucial component of any organization that allows it to legally collect, process, store, and/or distribute personal data.
Approach:	They propose to use a policy-document summarization dataset to enforce the summaries to include critical privacy-related entities and organization’s rationale in collecting those entities.
Outcome:	The proposed model improves over baselines and qualitatively evaluates the proposed model on human and qualitative data.

Language (Re)modelling: Towards Embodied Language Understanding (2020.acl-main)

Copied to clipboard

Ronen Tamari, Chen Shani, Tom Hope, Miriam R L Petruck, Omri Abend, Dafna Shahaf

Cognitive Modeling

Challenge:	Despite the rapid progress in NLU, current systems lack the rich mental representations that people use for language understanding.
Approach:	They propose an approach to representation and learning based on the tenets of embodied cognitive linguistics (ECL) they propose a system architecture along with a roadmap towards realizing this vision.
Outcome:	The proposed approach will improve the performance of existing systems and provide a roadmap towards realizing this vision.

Capability Decomposition for Unified Information Extraction via Hierarchical Mixture-of-Experts (2026.acl-long)

Copied to clipboard

Jing Zhou, Peng Wang, Wenjun Ke, Jiajun Liu, Yao He

VDebugger: Harnessing Execution Feedback for Debugging Visual Programs (2024.findings-emnlp)

Challenge:	Existing methods for IE tasks suffer from inconsistent schema representation and implicitly intermediate reasoning . UC-UIE adopts a low-rank adapted hierarchical Mixture-of-Experts adapter for UIE tasks .
Approach:	They propose a framework that decomposes IE reasoning into three universal capabilities . UC-UIE adopts a low-rank Adaptation adapter to fine-tune LLMs for IE tasks .
Outcome:	The proposed framework outperforms full-parameter tuning methods with 1.24% trainable parameters and outperformed existing methods in generalization and interpretability.

Copied to clipboard

Xueqing Wu, Zongyu Lin, Songyan Zhao, Te-Lin Wu, Pan Lu, Nanyun Peng, Kai-Wei Chang

From Form to Logic: Masked Reconstruction and Reasoning Distillation for Short Video Fake News Detection (2026.acl-long)

Challenge:	Visual programs are executable code generated by large language models to address visual reasoning problems.
Approach:	They propose a critic-refiner framework that localizes and debugs visual programs by tracking execution step by step.
Outcome:	The proposed framework detects and corrects program errors leveraging detailed execution feedback, improving interpretability and accuracy.

Copied to clipboard

Qingyan Wang, Lianwei Wu, Botao Wang, null Wangkang, Yaxiong Wang

Confidence is not Timeless: Modeling Temporal Validity for Rule-based Temporal Knowledge Graph Forecasting (2024.acl-long)

Challenge:	Existing detectors that detect short video fake news suffer from global-alignment bias and lack generative reasoning are too late.
Approach:	They propose a Perception-Cognition Dual-driven Detector that jointly observes the form and probes the logic for short video fake news detection.
Outcome:	The proposed detector outperforms baseline detectors on real-world datasets while improving interpretability and robustness in data scarcity scenarios.

Copied to clipboard

Rikui Huang, Wei Wei, Xiaoye Qu, Shengzhe Zhang, Dangyang Chen, Yu Cheng

Sentiment Interpretable Logic Tensor Network for Aspect-Term Sentiment Analysis (2022.coling-1)

Challenge:	Existing literature on temporal knowledge Graph Forecasting lacks in-depth investigation into how confidence evolves with time.
Approach:	They propose a framework to model the temporal validity of rules for Temporal Knowledge Graph Forecasting (TKGF) they propose rule-adversarial negative sampling and time-aware negative sampling strategies to facilitate TempValid learning.
Outcome:	The proposed framework outperforms state-of-the-art (SOTA) rule-based methods on six TKGF datasets.

Copied to clipboard

Bowen Zhang, Xu Huang, Zhichao Huang, Hu Huang, Baoquan Zhang, Xianghua Fu, Liwen Jing

Neuro-Symbolic Sentiment Analysis with Dynamic Word Sense Disambiguation (2023.findings-emnlp)

Challenge:	Aspect-term sentiment analysis (ATSA) is a fine-grained task that aims to infer the sentiment towards the given aspect-terms.
Approach:	They propose a novel ATSA method that is interpretable and has high accuracy . they propose SILTN, which is a neurosymbolic formalism, to improve the accuracy based on syntax knowledge distillation.
Outcome:	The proposed method is interpretable because it is a neurosymbolic formalism and a computational model that supports learning and reasoning about data with a differentiable first-order logic language.

Copied to clipboard

Xulang Zhang, Rui Mao, Kai He, Erik Cambria

ChartGaze: Enhancing Chart Understanding in LVLMs with Eye-Tracking Guided Attention Refinement (2025.emnlp-main)

Challenge:	Traditional neural network models represent word senses as vectors that are uninterpretable for humans.
Approach:	They propose a framework that incorporates word Sense Disambiguation (WSD) by identifying and paraphrasing ambiguous words to improve sentiment predictions.
Outcome:	The proposed framework improves sentiment analysis accuracy and interpretability on a downstream task without ground-truth word sense labels.

Copied to clipboard

Ali Salamatian, Amirhossein Abaskohi, Wan-Cyuan Fan, Mir Rayat Imtiaz Hossain, Leonid Sigal, Giuseppe Carenini

A Bayesian Topic Model for Human-Evaluated Interpretability (2022.lrec-1)

Challenge:	Chart question answering (CQA) is a key research challenge for large vision-language models . recent efforts focus on leveraging LVLMs directly on chart images .
Approach:	They propose a gaze-guided attention refinement that aligns image-text attention with human fixations to improve chart reasoning quality and interpretability.
Outcome:	The proposed approach improves answer accuracy and attention alignment yielding gains of up to 2.56 percentage points across multiple models.

Copied to clipboard

Justin Wood, Corey Arnold, Wei Wang

Explainable Text Classification with LLMs: Enhancing Performance through Dialectical Prompting and Explanation-Guided Training (2025.findings-emnlp)

Challenge:	Topic modeling is an effective way to analyze unstructured textual data.
Approach:	They propose to combine nonparametric and weakly-supervised topic models to produce interpretable topics.
Outcome:	The proposed model outperforms weakly-supervised models in the field of topic modeling.

Copied to clipboard

Huaming Du, Lei Yuan, Cancan Feng, Guisong Liu, Gang Kou, Carl Yang

Mapping the Circumplex of Affect: Geometric Analysis of Emotion Representations via Hyperspherical Contrastive Learning (2026.acl-long)

Challenge:	Existing explanation methods that generate keywords may be less effective due to missing critical contextual information.
Approach:	They propose a new method to generate explanations for possible labels using LLMs and a dialectical prompt.
Outcome:	The proposed method significantly improves accuracy and explanation quality over state-of-the-art methods on multiple datasets from diverse domains.

Copied to clipboard

Yusuke Yamauchi, Akiko Aizawa

Explicit Syntactic Guidance for Neural Text Generation (2023.acl-long)

Challenge:	Existing methods to induce circular emotion representations in language models are limited . elucidates trade-offs involved in applying circumplex models to deep learning architectures .
Approach:	They propose a method to induce circular emotion representations within language models via contrastive learning on a hypersphere.
Outcome:	The proposed method underperforms in high-dimensional settings and fine-grained classification.

Copied to clipboard

Yafu Li, Leyang Cui, Jianhao Yan, Yongjing Yin, Wei Bi, Shuming Shi, Yue Zhang

Syntactic Text Processing

Challenge:	Existing text generation models follow the sequence-to-sequence paradigm . generative grammar suggests humans generate language by learning language grammar .
Approach:	They propose a syntax-guided generation schema that searches the syntax tree in a top-down direction.
Outcome:	The proposed method outperforms autoregressive baselines on paraphrase generation and machine translation.

Intrinsic Subgraph Generation for Interpretable Graph Based Visual Question Answering (2024.lrec-main)

Copied to clipboard

Pascal Tilli, Ngoc Thang Vu

GeoDRL: A Self-Learning Framework for Geometry Problem Solving using Reinforcement Learning in Deductive Reasoning (2023.findings-acl)

Challenge:	Visual Question Answering (VQA) is acknowledged as a challenging multi-modal task for Machine Learning (ML).
Approach:	They propose an interpretable approach for graph-based Visual Question Answering . their model is designed to intrinsically produce a subgraph during the question-answering process as its explanation .
Outcome:	The proposed model outperforms existing explainable methods on a graph-based VQA dataset.

Copied to clipboard

Shuai Peng, Di Fu, Yijun Liang, Liangcai Gao, Zhi Tang

Enhancing Text Editing for Grammatical Error Correction: Arabic as a Case Study (2025.acl-long)

Challenge:	Existing methods for automated geometry problem solving lack labeled data.
Approach:	They propose a framework that integrates logic graph deduction and deep reinforcement learning to optimize geometry reasoning as a Markov Decision Process.
Outcome:	The proposed framework improves accuracy and interpretability in the Geometry3K dataset while maintaining correctness.

Copied to clipboard

Bashar Alhafni, Nizar Habash

Syntactic Text Processing

Challenge:	Text editing is a wellstudied problem for grammatical error correction (GEC) but it is not the most efficient for morphologically rich languages like Arabic.
Approach:	They propose a text editing approach that derives edit tags directly from data, eliminating the need for language-specific edits.
Outcome:	The proposed approach achieves SOTA results on Arabic and performs on par with SOTA on two other languages.

Retrieval over Classification: Integrating Relation Semantics for Multimodal Relation Extraction (2025.emnlp-main)

Copied to clipboard

Lei Hei, Tingjing Liao, null Peiyingxin, Yiyang Qi, Jiaqi Wang, Ruiting Li, Feiliang Ren

Information Extraction & Text Mining

Challenge:	Existing approaches to multimodal relation extraction ignore structural constraints and lack semantic expressiveness for fine-grained relation understanding.
Approach:	They propose a framework that reformulates multimodal relation extraction as a retrieval task driven by relation semantics.
Outcome:	The proposed framework achieves state-of-the-art performance on the benchmark datasets MNRE and MORE and exhibits stronger robustness and interpretability.

Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning (2026.acl-long)

Copied to clipboard

Xue Zhang, Yunlong Liang, Fandong Meng, Songming Zhang, Kaiyu Huang, Yufeng Chen, Xu Jinan, Jie Zhou

MedCoT: Medical Chain of Thought via Hierarchical Expert (2024.emnlp-main)

Challenge:	Current Large Reasoning Models exhibit two critical limitations when processing non-English languages: (1) They struggle to maintain input-output language consistency; (2) They generally perform poorly with wrong reasoning paths and lower answer accuracy compared to English.
Approach:	They propose a language-consistency reward and a cross-lingual thinking alignment reward to improve the model's interpretability and accuracy.
Outcome:	The proposed model achieves nearly 100% language consistency and superior performance on two multilingual benchmarks (MMATH and PolyMath).

Copied to clipboard

Jiaxiang Liu, Yuan Wang, Jiawei Du, Joey Zhou, Zuozhu Liu

SafetyMem: Adaptive Jailbreak Defense via Dual-Component Safety Memory (2026.acl-long)

Challenge:	Existing methods for medical visual question answering lack robustness and reasoning paths for real-world medical diagnostics.
Approach:	They propose a hierarchical expert verification reasoning chain method to enhance interpretability and accuracy in medical visual question answering.
Outcome:	The proposed method outperforms existing methods on four standard Med-VQA datasets.

Copied to clipboard

Hao Wang, Ziyi Ni, Huacan Wang, Pin Lyu, Lei Sha

Robustness in NLP

Challenge:	Existing defenses for Large Language Models suffer from a 'memory gap' parameter-modifying methods are computationally expensive and inference-time filters cannot retain or reuse defense knowledge across interactions.
Approach:	They propose a framework that secures Large Language Models through a dual-component safety memory system.
Outcome:	The proposed framework significantly reduces attack success rates while preserving interpretability and efficiency.

Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates (2025.emnlp-main)

Copied to clipboard

Hy Dang, Tianyi Liu, Zhuofeng Wu, Jingfeng Yang, Haoming Jiang, Tao Yang, Pei Chen, Zhengyang Wang, Helen Wang, Huasheng Li, Bing Yin, Meng Jiang

Understanding GUI Agent Localization Biases through Logit Sharpness (2025.findings-emnlp)

Challenge:	Large language models (LLMs) have strong reasoning and tool-use capabilities, yet fail in real-world tool-interactions due to incorrect parameterization, poor tool selection, or misinterpretation of user intent.
Approach:	They propose a curriculum-inspired framework that leverages structured reasoning templates to guide LLMs through more deliberate step-by-step instructions for generating function calls.
Outcome:	The proposed framework reduces tool-use errors and improves interpretability and transparency of tool-using agents.

Copied to clipboard

Xingjian Tao, Yiwei Wang, Yujun Cai, Zhicheng Yang, Jing Tang

Challenge:	Multimodal large language models often exhibit hallucinations that compromise reliability . despite promising performance, these models often display systematic localization errors .
Approach:	They propose a framework that categorizes model predictions into four distinct types . they propose metric that evaluates alignment between semantic continuity and logits distribution .
Outcome:	The proposed framework categorizes model predictions into four different types . it reveals nuanced failure modes beyond traditional accuracy metrics .

StructuThink: Reasoning with Task Transition Knowledge for Autonomous LLM-Based Agents (2025.findings-emnlp)

Copied to clipboard

Haiyu Zhao, Zhenyu Guo, Chunhong Zhang, Ziyu Zhou, Zheng Hu

PRISM: A Framework for Producing Interpretable Political Bias Embeddings with Political-Aware Cross-Encoder (2025.acl-long)

Challenge:	StructuThink framework enhances LLMs' ability to ground decisions in domain-specific scenarios.
Approach:	They propose a knowledge-structured reasoning framework that enhances LLM-based agents with explicit decision constraints.
Outcome:	The proposed framework achieves higher task success rates and more efficient action sequences than baseline methods.

Copied to clipboard

Yiqun Sun, Qiang Huang, Anthony Kum Hoe Tung, Jun Yu

Towards Interpretable Tabular Reasoning: Enhancing LLM Reasoning on Tabular Data with Pre-Constructed Logic Graph (2026.acl-long)

Challenge:	Existing embedding models excel at capturing general meaning, but overlook ideological nuances, limiting their effectiveness in political bias tasks.
Approach:	They propose a framework to Produce inteRpretable polItical biaS eMbeddings.
Outcome:	The proposed framework outperforms state-of-the-art embedding models in political bias classification . the proposed framework offers highly interpretable representations for political analysis .

Copied to clipboard

Lirong Gao, Zewei Yu, Zhongrui Yin, Qi Zhang, Yuke Zhu, Bo Zheng, Haobo Wang, Junbo Zhao, Gang Chen, Sheng Guo

LLM-Guided Semantic Bootstrapping for Interpretable Text Classification with Tsetlin Machines (2026.findings-acl)

Challenge:	Tabular data is used in fields such as finance and healthcare due to its heterogeneity and complexity.
Approach:	They propose a Logic-Graph-Enhanced LLM Reasoning framework that integrates the strengths of tree-based models and LLMs to improve their interpretability.
Outcome:	The proposed framework outperforms tree-based models and state-of-the-art LLMs on tabular prediction tasks, achieving superior accuracy and interpretability.

Copied to clipboard

Jiechao Gao, Rohan Kumar Yadav, Yuangang Li, Yuandong Pan, Jie Wang, Ying Liu, Michael Lepech

Fast Retrieval and Slow Reasoning for Explainable Multimodal Sentiment Analysis (2026.findings-acl)

Challenge:	Pretrained language models (PLMs) provide strong semantic representations but are costly and opaque.
Approach:	They propose a framework that transfers pretrained language models into symbolic form and integrates them into symbolic models.
Outcome:	The proposed framework improves interpretability and accuracy across multiple text classification tasks while remaining fully symbolic and efficient.

Copied to clipboard

Aoqiang Zhu, Min Hu, Yan Xing

EvoMemKG: An Evolvable Memory Agent for Multi-hop Knowledge Graph Reasoning (2026.findings-acl)

Challenge:	Existing multimodal sentiment analysis methods rely on holistic fusion . such strategies introduce redundant information and obscure the decision process .
Approach:	They propose an interpretable framework that decomposes multimodal sentiment modeling into two cooperative pathways.
Outcome:	The proposed framework achieves competitive performance, higher efficiency, stronger robustness to noise, and clearer decision transparency than existing holistic fusion methods.

Copied to clipboard

Shiyu Tian, Shuyue Xing, Zhuoxin Han, Caixia Yuan, Xiaojie Wang

Knowledge Representation

Challenge:	Existing methods for integrating knowledge graphs with large language models lack continuous learning capabilities.
Approach:	They propose an agent framework with a dynamic, evolvable memory mechanism specifically designed for KG reasoning.
Outcome:	EvoMemKG achieves state-of-the-art performance without training or tools . it achieves improvements of up to 20% over baseline on multi-hop queries .

Self-Explaining Hate Speech Detection with Moral Rationales (2026.findings-acl)

Copied to clipboard

Francielle Vargas, Jackson Trager, Diego Alves, Matteo Guida, Surendrabikram Thapa, Berk Atıl, Daryna Dementieva, Andrew J Smart, Ameeta Agrawal

R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling (2026.acl-long)

Challenge:	Existing models for hate speech detection are opaque and rely on surface-level cues. Existing approaches often encode biases originating from training data and annotation processes.
Approach:	They propose a framework that integrates moral rationale supervision into training . they propose SMRA for self-explaining hate speech detection .
Outcome:	The proposed framework improves performance across binary hate speech detection and multi-label moral sentiment classification.

Copied to clipboard

Aijia Cheng, Kailong Wang, Ling Shi, Yongxin Zhao

Comprehensiveness Metrics for Automatic Evaluation of Factual Recall in Text Generation (2026.findings-acl)

Challenge:	Existing RL-based approaches to function calling are misaligned between reasoning processes and tool-call decisions.
Approach:	They propose a reasoning-aware RL framework for interpretable function calling . they integrate a composite reward integrating format/correctness constraints, CER, and SMV .
Outcome:	Experiments on BFCL/ACEBench show R2IF outperforms baselines by 34.62% with positive Average CoT Effectiveness.

Copied to clipboard

Adam Dejl, James Barry, Alessandra Pascale, Javier Carnerero-Cano

Text Generation

Challenge:	Large language models (LLMs) produce incomplete or selectively omit key information . omissions of key information or misrepresentation of conflicting evidence can cause harm .
Approach:	They propose a method that decomposes texts into atomic statements and uses natural language inference to identify missing facts and a Q A-based metric that extracts question-answer pairs and compares responses across sources.
Outcome:	The proposed evaluation metrics show they perform better than more complex metrics, but at a cost.

Execution as Verification: Fine-Grained Self-Correcting Reasoning for Complex KBQA (2026.acl-long)

Copied to clipboard

Minghan Zhang, Zhen Yang, Haodong Zou, Jie Chen, Zhen Duan, Shu Zhao

Retrieving Support to Rank Answers in Open-Domain Question Answering (2025.emnlp-main)

Challenge:	Existing knowledge base question answering methods are limited by syntactic constraints and are prone to structural deviations that render queries unexecutable.
Approach:	They propose a framework that reframes semantic parsing as an iterative reasoning process driven by execution feedback.
Outcome:	The proposed method achieves significant improvements in query executability and answer accuracy on the WebQSP and CWQ datasets.

Copied to clipboard

Zeyu Zhang, Alessandro Moschitti, Thuy Vu

Information Retrieval

Challenge:	a novel question answering architecture retrieves content relevant to the combined pair . previous work on automatic claim verification has shown hallucinations .
Approach:	They propose a question-answer architecture that prioritizes supporting evidence . it retrieves paragraphs that directly substantiate the correctness of a with respect to q .
Outcome:	The proposed approach can be used by large language models to retrieve explanatory paragraphs that ground their reasoning.

Policy-Guided Stepwise Action Planning for Controllable LLM Reasoning (2026.findings-acl)

Copied to clipboard

Jianpeng Zhou, Qisheng Hu, Jiahai Wang, Wenya Wang

REMIND: Memorization and Unlearning in LLMs Through the Lens of Input Loss Landscapes (2026.acl-long)

Challenge:	Existing approaches to steering large language model reasoning via high-level reasoning actions fail to outperform standard generation because planners tend to degenerate into repetitive loops or fixed patterns.
Approach:	They propose a planner-executor framework that learns to select reasoning actions dynamically while keeping the executor LLM fully frozen.
Outcome:	The proposed framework outperforms existing paradigms by preserving the executor LLM frozen . PG-HAP improves accuracy over strong baselines while producing less redundant, more adaptive trajectories.

Copied to clipboard

Liran Cohen, Yaniv Nemcovsky, Avi Mendelson