DECISION-MAKING PROCESS

GraphNarrator: Generating Textual Explanations for Graph Neural Networks (2025.acl-long)

Challenge:	Attention mechanisms play a central role in NLP systems, especially within recurrent neural network (RNN) models.
Approach:	They propose to use a simple uniform-weights baseline, a variance calibration and a diagnostic framework to determine when/whether attention can be used as explanation in RNN models.
Outcome:	The proposed tests show that even reliable adversarial distributions don't perform well on the simple diagnostic, indicating that prior work does not disprove the usefulness of attention mechanisms for explainability.

Copied to clipboard

Bo Pan, Zhen Xiong, Guanchen Wu, Zheng Zhang, Yifei Zhang, Yuntong Hu, Liang Zhao

Interpreting Predictions of NLP Models (2020.emnlp-tutorials)

Challenge:	Graph representation learning has garnered significant attention due to its broad applications in various domains, such as recommendation systems and social network analysis.
Approach:	They propose to use a generative language model to map input-output pairs to explanations reflecting the model’s decision-making process to generate a model that generates pseudo-labels that capture the model's decisions from saliency-based explanations.
Outcome:	Extensive experiments show that GraphNarrator produces human-preferred explanations that are faithful, concise, and human-like.

Copied to clipboard

Eric Wallace, Matt Gardner, Sameer Singh

LM Transparency Tool: Interactive Tool for Analyzing Transformer Language Models (2024.acl-demos)

Challenge:	This tutorial will provide a background on interpretation techniques for neural NLP models.
Approach:	This tutorial will provide a background on interpretation techniques for NLP models . it will examine saliency maps, input perturbations, adversarial attacks and influence functions .
Outcome:	This tutorial will provide a background on interpretation techniques . examples-specific interpretations include saliency maps, input perturbations, adversarial attacks, influence functions .

Copied to clipboard

Igor Tufanov, Karen Hambardzumyan, Javier Ferrando, Elena Voita

I-MCTS: Enhancing Agentic AutoML via Introspective Monte Carlo Tree Search (2026.findings-eacl)

Challenge:	Existing tools focus on isolated parts of the decision-making process, but LM-TT makes the entire prediction process transparent.
Approach:	They present an open-source toolkit for analyzing the internal workings of Transformer-based language models.
Outcome:	The LM Transparency Tool makes the entire prediction process transparent . it shows the importance of specific component at each step .

Copied to clipboard

Zujie Liang, Feng Wei, Wujiang Xu, Yuxi Qian, Lin Chen, Xinhui Wu

Justifying Recommendations using Distantly-Labeled Reviews and Fine-Grained Aspects (D19-1)

Challenge:	Existing LLM-based agents struggle with low diversity and suboptimal code generation.
Approach:	They propose an approach that iteratively expands tree nodes through an introspective process that meticulously analyzes solutions and results from parent and sibling nodes.
Outcome:	The proposed approach shows a 4% improvement in performance compared to the strong open-source AutoML agents.

Copied to clipboard

Jianmo Ni, Jiacheng Li, Julian McAuley

Challenge:	Existing approaches to generating reviews struggle to generate justifications that are relevant to users’ decision-making process.
Approach:	They propose an ‘extractive’ approach to identify review segments which justify users’ intentions and use it to distantly label massive review corpora and construct large-scale personalized recommendation justification datasets.
Outcome:	The proposed model can generate convincing and diverse justifications from massive review corpora and distantly label massive review data.

Detecting Omissions in LLM-Generated Medical Summaries (2025.emnlp-industry)

Copied to clipboard

Achir Oukelmoun, Nasredine Semmar, Gaël de Chalendar, Clement Cormi, Mariame Oukelmoun, Eric Vibert, Marc-Antoine Allard

Faithfulness Tests for Natural Language Explanations (2023.acl-short)

Challenge:	Large Language Models (LLMs) have created a number of use cases in the medical field . omissions in summaries can jeopardize the decision-making process .
Approach:	They propose a dataset to evaluate omissions in large-scale medical summaries . they propose 'embedKDECheck' method that uses embeddings generated by a third-party NLP model .
Outcome:	The proposed method is well-suited for resource-constrained environments.

Copied to clipboard

Pepa Atanasova, Oana-Maria Camburu, Christina Lioma, Thomas Lukasiewicz, Jakob Grue Simonsen, Isabelle Augenstein

HANS, are you clever? Clever Hans Effect Analysis of Neural Systems (2024.starsem-1)

Challenge:	Existing methods for explaining neural models are misleading as they often present reasons that are unfaithful to the model’s inner workings.
Approach:	They propose a counterfactual input editor for inserting reasons that lead to counterfacts but are not reflected by the NLEs.
Outcome:	The proposed model can evaluate emerging NLE models, proving a fundamental tool in the development of faithful explanations.

Copied to clipboard

Leonardo Ranaldi, Fabio Zanzotto

Reasoning

Challenge:	Large Language Models (LLMs) have been exhibiting outstanding abilities to reason around cognitive states, intentions, and reactions of all people involved, letting humans guide and comprehend day-to-day social interactions effectively.
Approach:	They propose to use multiple-choice questions (MCQ) benchmarks to assess LLMs' ability to reason around cognitive states, intentions, and reactions of all people involved to investigate their resilience abilities.
Outcome:	The proposed models exhibit exceptional abilities to reason around cognitive states, intentions, and reactions of all people involved, letting humans guide and comprehend day-to-day social interactions effectively.

Foundation Model for Biomedical Graphs: Integrating Knowledge Graphs and Protein Structures to Large Language Models (2024.acl-srw)

Copied to clipboard

Yunsoo Kim

Personal Large Language Model Agents: A Case Study on Tailored Travel Planning (2024.emnlp-industry)

Challenge:	Transformer model has been a de-facto standard in natural language processing, but it is limited to images, text, and/or sequence data.
Approach:	They propose to use a multimodal large language model architecture to handle biomedical graphs such as protein structure and chemical molecules to improve its performance.
Outcome:	The proposed architecture can handle multiple data types for biomedical graphs such as protein structure and chemical molecules.

Copied to clipboard

Harmanpreet Singh, Nikhil Verma, Yixiao Wang, Manasa Bharadwaj, Homa Fashandi, Kevin Ferreira, Chul Lee

Language Models

Challenge:	Large Language Models (LLMs) are becoming more autonomous and capable of handling real-world tasks through their access to tools, various planning strategies, and memory, referred to as LLM agents.
Approach:	They introduce a personalized version of TravelPlanner and establish baselines for personal LLM agents by comparing generic and personal plans.
Outcome:	The proposed model encapsulates user-related information, preferences, and personal concepts and provides baselines for personal LLM agents.

A Rationale-centric Counterfactual Data Augmentation Method for Cross-Document Event Coreference Resolution (2024.naacl-long)

Copied to clipboard

Bowen Ding, Qingkai Min, Shengkun Ma, Yingjie Li, Linyi Yang, Yue Zhang

Disentangling Memory and Reasoning Ability in Large Language Models (2025.acl-long)

Challenge:	Existing state-of-the-art event coreference resolution systems rely on spurious and spurious associations in the input mention pair text.
Approach:	They propose a rationale-centric counterfactual data augmentation method that leverages the debiasing capability of counterfact data haussed by LLM-in-the-loop to mitigate spurious association while emphasizing causation.
Outcome:	The proposed method achieves state-of-the-art on three popular cross-document benchmarks and demonstrates robustness in out-of domain scenarios.

Copied to clipboard

Mingyu Jin, Weidi Luo, Sitao Cheng, Xinyi Wang, Wenyue Hua, Ruixiang Tang, William Yang Wang, Yongfeng Zhang

The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metrics (2023.acl-short)

Challenge:	Existing LLMs operate as an opaque process without explicit separation between knowledge retrieval and reasoning steps, making the decision-making process unclear and disorganized.
Approach:	They propose a language model inference paradigm that decomposes the complex inference process into two distinct and clear actions: (1) memory recall: which retrieves relevant knowledge, and (2) reasoning: which performs reasoning steps based on the recalled knowledge.
Outcome:	The proposed paradigm decomposes the inference process into two distinct and clear actions, memory and reason, guiding the model to distinguish between steps that require knowledge retrieval and those that involve reasoning.

Copied to clipboard

Ricardo Rei, Nuno M. Guerreiro, Marcos Treviso, Luisa Coheur, Alon Lavie, André Martins

Multilinguality

Challenge:	Neural metrics for machine translation evaluation are considered "black boxes" lexical overlap-based metrics are popular for evaluation of translation systems and algorithms .
Approach:	They develop and compare several neural explainability methods to understand translation errors . they aim to better understand the correspondence between token-level explanations and human annotated error spans .
Outcome:	The proposed methods leverage token-level information that can be directly attributed to translation errors.

Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models (N19-1)

Copied to clipboard

Tiancheng Zhao, Kaige Xie, Maxine Eskenazi

Guide the Learner: Controlling Product of Experts Debiasing Method Based on Token Attribution Similarities (2023.eacl-main)

Challenge:	Existing approaches to define action spaces for conversational agents have limitations . end-to-end dialog systems can handle complex domains with limited action space .
Approach:	They propose a latent action framework that treats the action spaces of an end-to-end dialog agent as latent variables and develops unsupervised methods to induce its own action space from the data.
Outcome:	The proposed framework achieves better performance than word-level policy gradient methods on DealOrNoDeal and MultiWoz dialogs.

Copied to clipboard

Ali Modarressi, Hossein Amirkhani, Mohammad Taher Pilehvar

Robustness in NLP

Challenge:	Several proposals have been put forward for improving out-of-distribution performance by mitigating dataset biases.
Approach:	They propose a fine-tuning strategy that incorporates the similarity between the main and biased model attribution scores in a Product of Experts (PoE) loss function to further improve OOD performance.
Outcome:	The proposed method improves OOD performance while maintaining in-distribution performance.

Decision-Making with Deliberation: Meta-reviewing as a Document-grounded Dialogue (2026.eacl-long)

Copied to clipboard

Sukannya Purkayastha, Nils Dycke, Anne Lauscher, Iryna Gurevych

Learning to Generate Equitable Text in Dialogue from Biased Training Data (2023.acl-long)

Challenge:	Prior research on meta-reviewing has treated this as a summarization problem over review reports . prior research demonstrated that decision-makers can be effectively assisted in such scenarios via dialogue agents.
Approach:	They propose to use large-scale large-language models to generate synthetic data for meta-reviewing . they then use these data to train dialogue agents tailored for meta review .
Outcome:	The proposed method outperforms off-the-shelf dialogue agents in meta-reviewing scenarios.

Copied to clipboard

Anthony Sicilia, Malihe Alikhani

Style Detection for Free Verse Poetry from Text and Speech (C18-1)

Challenge:	Absence of equitable and inclusive principles can hinder the formation of common ground, which in turn negatively impacts the overall performance of the system.
Approach:	They propose to use theories of computational learning to study equitable text generation in dialogues using augmented data to prove formal definitions of equity in text generation and formal connections between human-likeness and learning equity.
Outcome:	The proposed model predicts relative-performance of multiple algorithms in generating equitable text as measured by human and automated evaluation.

Copied to clipboard

Timo Baumann, Hussein Hussein, Burkhard Meyer-Sickendiek

Multimodality

Challenge:	Modern and post-modern free verse poems feature a large and complex variety in their prosodies that falls along a continuum from a more fluent to a disfluent and choppy style.
Approach:	They propose a method for automatic prosodic classification of spoken free verse poetry that integrates source text and audio and predicts the assigned class.
Outcome:	The proposed method can be validated on a large corpus of German author-read post-modern poetry and achieves a weighted f-measure of 0.73 when combining textual and phonetic evidence.

A Novel Perspective to Look At Attention: Bi-level Attention-based Explainable Topic Modeling for News Classification (2022.findings-acl)

Copied to clipboard

Dairui Liu, Derek Greene, Ruihai Dong

Information Extraction & Text Mining

Challenge:	Existing deep learning models have the attention mechanism to improve performance, but the inherent characteristics of deep learning model complexity and the flexibility of the attention structure make them difficult to explain.
Approach:	They propose a two-tier attention architecture to decouple the complexity of explanation and the decision-making process by using large-scale news corpora.
Outcome:	The proposed model can achieve competitive performance with state-of-the-art models and illustrates its appropriateness from an explainability perspective.

Faithfully Explainable Recommendation via Neural Logic Reasoning (2021.naacl-main)

Copied to clipboard

Yaxin Zhu, Yikun Xian, Zuohui Fu, Gerard de Melo, Yongfeng Zhang

SenteCon: Leveraging Lexicons to Learn Human-Interpretable Language Representations (2023.findings-acl)

Challenge:	Existing models for explainable recommendation have neglected faithfulness of KG reasoning .
Approach:	They propose to draw on interpretable logical rules to guide path-reasoning process for explanation generation.
Outcome:	The proposed method delivers high-quality recommendations and ascertains the faithfulness of the derived explanation.

Copied to clipboard

Victoria Lin, Louis-Philippe Morency

Evaluating Moral Beliefs across LLMs through a Pluralistic Framework (2024.findings-emnlp)

Challenge:	In many settings, it is important to understand a model’s decision-making process.
Approach:	They propose a method for introducing human interpretability in deep language representations by encoding a passage of text as a layer of interpretable categories.
Outcome:	The proposed method outperforms existing interpretable language representations on downstream tasks and on agreement with human characterizations of the text.

Copied to clipboard

Xuelin Liu, Yanfei Zhu, Shucheng Zhu, Pengyuan Liu, Ying Liu, Dong Yu

Towards Efficient and Robust VQA-NLE Data Generation with Large Vision-Language Models (2025.coling-main)

Challenge:	Proper moral beliefs are fundamental for language models, yet assessing these beliefs poses a significant challenge.
Approach:	They propose a framework to evaluate the moral beliefs of four large language models . they use a dataset containing 472 moral choice scenarios in Chinese .
Outcome:	The proposed framework evaluates the moral beliefs of four large language models.

Copied to clipboard

Patrick Amadeus Irawan, Genta Indra Winata, Samuel Cahyawijaya, Ayu Purwarianti

PersonaX: A Recommendation Agent-Oriented User Modeling Framework for Long Behavior Sequence (2025.findings-acl)

Challenge:	Existing methods for creating a vision question-answering with natural language explanations rely on human annotations that are time-consuming and costly.
Approach:	They propose a method that generates high-quality natural language explanations using LVLMs by using visual prompts.
Outcome:	The proposed method generates high-quality synthetic VQA-NLE datasets 20x faster than human annotations with minimal decrease in qualitative metrics.

Copied to clipboard

Yunxiao Shi, Wujiang Xu, Zhang Zeqi, Xing Zi, Qiang Wu, Min Xu

Challenge:	Existing methods for user profile modeling extract only partial segments from full historical behavior sequence, resulting in incomplete modeling and suboptimal profiling.
Approach:	They propose an agent-agnostic LLM-UM framework to augment downstream recommendation agents . it segments complete historical behaviors into clustered groups and performs offline multi-persona profiling .
Outcome:	The proposed framework improves agent performance and inference efficiency by 31% and 10% using 30–50% of behavioral data.

What’s the most important value? INVP: INvestigating the Value Priorities of LLMs through Decision-making in Social Scenarios (2025.coling-main)

Copied to clipboard

Xuelin Liu, Pengyuan Liu, Dong Yu

Challenge:	Large scale language models (LLMs) have demonstrated impressive performance in various tasks and are increasingly integrated into the decision-making process.
Approach:	They propose a framework for INvestigating Value Priorities through decision-making in social scenarios and evaluate seven popular LLMs.
Outcome:	The proposed framework covers 1613 scenarios and 3226 decisions across 283 topics and focuses on Universalism and Benevolence, while Power and Hedonism are given lower priority.

STRIDE-ED: A Strategy-Grounded Stepwise Reasoning Framework for Empathetic Dialogue Systems (2026.acl-long)

Copied to clipboard

Hongru Ji, Yuyin Fan, Meng Zhao, Xianghua Li, Lianwei Wu, Chao Gao

Natural Language Interfaces

Challenge:	Empathetic dialogue requires not only recognizing a user’s emotional state but also making strategy-aware, context-sensitive decisions throughout response generation.
Approach:	They propose a STRategy-grounded, interpretable, and DEep reasoning framework that models Empathetic Dialogue through structured, strategy-conditioned reasoning.
Outcome:	The proposed framework outperforms existing methods on automatic metrics and human evaluations.

TriageAgent: Towards Better Multi-Agents Collaborations for Large Language Model-Based Clinical Triage (2024.findings-emnlp)

Copied to clipboard

Meng Lu, Brandon Ho, Dennis Ren, Xuan Wang

Language Models

Challenge:	escalation in emergency department patient visits poses challenges to efficient clinical management . Currently, hospitals rely on human experts to review clinical notes and determine case urgency .
Approach:	a team of researchers develop a multi-agent framework to enhance collaborative decision-making in clinical triage.
Outcome:	The proposed framework outperforms state-of-the-art LLM-based methods on three clinical triage test sets.

Why Should This Article Be Deleted? Transparent Stance Detection in Multilingual Wikipedia Editor Discussions (2023.emnlp-main)

Copied to clipboard

Lucie-Aimée Kaffee, Arnav Arora, Isabelle Augenstein

Reasoning

Challenge:	Currently, only 20% of the English comments explicitly mention content moderation policies, but as few as 2% of the German and Turkish comments.
Approach:	They propose to use a multilingual dataset to predict stances with existing content moderation policies and to use them to explain moderation decisions.
Outcome:	The proposed model predicts stances and corresponding reasons with high accuracy, adding transparency to the decision-making process.

Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanations (2020.acl-main)

Copied to clipboard

Oana-Maria Camburu, Brendan Shillingford, Pasquale Minervini, Thomas Lukasiewicz, Phil Blunsom

Tree Prompting: Efficient Task Adaptation without Fine-Tuning (2023.emnlp-main)

Challenge:	a promising research direction consists of designing neural models capable of generating natural language explanations for their predictions.
Approach:	They propose a framework for sanity checking models against inconsistent explanations . they apply the framework to a state-of-the-art neural natural language inference model .
Outcome:	The proposed framework can generate inconsistent explanations on a state-of-the-art model . it also addresses the problem of adversarial attacks with full target sequences .

Copied to clipboard

Chandan Singh, John Morris, Alexander Rush, Jianfeng Gao, Yuntian Deng

Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models (2023.findings-emnlp)

Challenge:	Pretrained language models (LMs) are the main interface for applying them to new tasks, but their large size makes them difficult to fine-tune with gradients for specific downstream tasks.
Approach:	They propose to use training data to form a decision tree based on prompt-LM calls, with each prompt determined by the outcomes of previous calls.
Outcome:	The proposed method improves accuracy over competing methods and is competitive with fine-tuning.

Copied to clipboard

Haoran Wang, Kai Shu

Training Simultaneous Speech Translation with Robust and Random Wait-k-Tokens Strategy (2023.emnlp-main)

Challenge:	Existing claims verification models rely on annotated data, which is expensive to create at a large scale.
Approach:	They propose a model that can verify complex claims without annotated data . they leverage the in-context learning ability of Large Language Models to translate a claim into a First-Order-Logic clause .
Outcome:	The proposed model outperforms baseline models on three datasets . it performs well on the datasets, and the results are published online.

Copied to clipboard

Linlin Zhang, Kai Fan, Jiajun Bu, Zhongqiang Huang

Text Generation

Challenge:	Simultaneous Speech Translation (SimulST) is a task focused on ensuring high-quality translation of speech in low-latency situations.
Approach:	They propose a token-level cross-modal alignment method to improve the translation of text to audio . they use audio transcription pairs to pre-train the encoder and a random wait-k-tokens strategy to optimize the task.
Outcome:	The proposed method achieves better trade-off between translation quality and latency.

ReKG-MCTS: Reinforcing LLM Reasoning on Knowledge Graphs via Training-Free Monte Carlo Tree Search (2025.findings-acl)

Copied to clipboard

Xiaozhuang Song, Shufei Zhang, Tianshu Yu

HutCRS: Hierarchical User-Interest Tracking for Conversational Recommender System (2023.emnlp-main)

Challenge:	Existing approaches to combining knowledge graphs with large language models face limitations in path exploration strategies or excessive computational overhead.
Approach:	They propose a training-free framework that synergizes Monte Carlo Tree Search with LLM capabilities to enable dynamic reasoning over KGs.
Outcome:	The proposed framework outperforms existing training-free methods and achieves competitive performance compared to fine-tuned baselines.

Copied to clipboard

Mingjie Qian, Yongsen Zheng, Jinghui Qin, Liang Lin

Natural Language Interfaces

Challenge:	Existing CRSs assume that users like all attributes of the target item and dislike those unrelated to it, which can introduce bias in attribute-level feedback and impede the system’s ability to accurately identify the target items.
Approach:	They propose a framework that allows users to explicitly acquire user preferences through natural language conversations by providing explicit answers (yes/no) for each attribute they require.
Outcome:	The proposed framework portrays the conversation as a hierarchical interest tree that consists of two stages.

D-Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agents (2026.findings-acl)

Copied to clipboard

Hongze Mi, Yibo Feng, WenJie Lu, Yuqi Wang, Jinyuan Li, Song Cao, He Cui, Tengfei Tian, Xuelin Zhang, Haotian Luo, Di Sun, Jun Fang, Hua Chai, Naiqiang Tan, Gang Pan

Challenge:	Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction.
Approach:	They propose a deliberative framework that leverages a fine-grained tip retrieval mechanism to inform its decision-making process.
Outcome:	The proposed framework achieves SOTA among open-source general models on AndroidWorld and ScreenSpot-V2 . it leverages a fine-grained, app-specific tip retrieval mechanism to inform its decision-making process .

AuriSRec: Adversarial User Intention Learning in Sequential Recommendation (2024.findings-emnlp)

Copied to clipboard

Junjie Zhang, Ruobing Xie, Wenqi Sun, Leyu Lin, Xin Zhao, Ji-Rong Wen

Flowchart-Based Decision Making with Large Language Models (2025.findings-acl)

Challenge:	Existing work focuses on capturing user implicit preferences from historical interactions and matching them with the next behavior, instead of predicting user explicit intentions.
Approach:	They propose an adversarial user intention learning approach for sequential recommendaiton . the approach explicitly predicts user current intentions by taking historical reviews as inputs .
Outcome:	The proposed approach explicitly predicts user intentions by inferring their decision-making process as explained in target reviews.

Copied to clipboard

Yuuki Yamanaka, Hiroshi Takahashi, Tomoya Yamashita

Enhancing LLM Agent Safety via Causal Influence Prompting (2025.findings-acl)

Challenge:	Large language models face significant challenges in interpretability of dialogue flow and reproducibility of expert knowledge.
Approach:	They propose a method that extracts flowcharts from dialogue data and incorporates them into large language models to improve interpretability and reproducibility.
Outcome:	The proposed method reconstructs expert decision-making paths with high precision and recall scores on dialogue datasets.

Copied to clipboard

Dongyoon Hahm, Woogyeol Jin, June Suk Choi, Sungsoo Ahn, Kimin Lee

Interpretable Short Video Rumor Detection Based on Modality Tampering (2024.lrec-main)

Challenge:	Experimental results demonstrate that our method effectively enhances safety in code execution and mobile device control tasks.
Approach:	They propose a technique that leverages causal influence diagrams to identify and mitigate risks arising from agent decision-making.
Outcome:	The proposed method enhances safety in code execution and mobile device control tasks.

Copied to clipboard

Kaixuan Wu, Yanghao Lin, Donglin Cao, Dazhen Lin

Multimodality

Challenge:	Existing methods to detect rumors from the perspective of modality tampering are labor-intensive and time-consuming.
Approach:	They propose a short video rumor detection framework that integrates modality tampering detection and inter-modal matching into a model to detect modality-tampers and interpretability mechanisms to make the results more reasonable.
Outcome:	The proposed model improves on the short video rumor dataset by 4.6%-12% compared with other models and can explain whether the short clip is a rumour or not through the perspective of modality tampering.

Measuring Association Between Labels and Free-Text Rationales (2021.emnlp-main)

Copied to clipboard

Sarah Wiegreffe, Ana Marasović, Noah A. Smith

Self-training with Few-shot Rationalization (2021.emnlp-main)

Challenge:	Existing models for extractive rationales do not work as well on reasoning tasks requiring free-text rationale.
Approach:	They propose to use pipelines to extract rationales from input words and to use them to explain reasoning tasks.
Outcome:	The proposed models exhibit desirable properties for explaining commonsense question-answering and natural language inference, indicating their potential for producing faithful free-text rationales.

Copied to clipboard

Meghana Moorthy Bhat, Alessandro Sordoni, Subhabrata Mukherjee

Language Models

Challenge:	Recent work focused on training largescale and complex neural network models, but they are opaque in terms of their decision-making process.
Approach:	They propose a multi-task teacher-student framework for self-training pre-trained language models with limited task-specific labels and annotated rationales.
Outcome:	The proposed model improves performance in low-resource settings by making it aware of its rationalized predictions.

XDetox: Text Detoxification with Token-Level Toxicity Explanations (2024.emnlp-main)

Copied to clipboard

Beomseok Lee, Hyunwoo Kim, Keon Kim, Yong Suk Choi

Alignment for Efficient Tool Calling of Large Language Models (2025.emnlp-main)

Challenge:	Existing methods for mitigating toxic content are black-box approaches, which results in limitations in modifying toxic tokens.
Approach:	They propose a method that integrates token-level toxicity explanations with the masking and infilling detoxification processes.
Outcome:	The proposed method outperforms baseline methods in fluency and toxicity reduction.

Copied to clipboard

Hongshen Xu, Zihan Wang, Zichen Zhu, Lei Pan, Xingyu Chen, Shuai Fan, Lu Chen, Kai Yu

TELLER: A Trustworthy Framework for Explainable, Generalizable and Controllable Fake News Detection (2024.findings-acl)

Challenge:	Recent advances in tool learning have enabled large language models to integrate external tools, enhancing their task performance by expanding their knowledge boundaries.
Approach:	They propose a framework that combines probabilistic knowledge boundary estimation with dynamic decision-making to allow LLMs to better assess when to invoke tools based on their confidence.
Outcome:	The proposed framework shows significant improvements in tool efficiency by reducing unnecessary tool usage.

Copied to clipboard

Hui Liu, Wenya Wang, Haoru Li, Haoliang Li

The Odyssey of Commonsense Causality: From Foundational Benchmarks to Cutting-Edge Reasoning (2024.emnlp-main)

Challenge:	Existing methods for detecting fake news are limited due to non-transparent reasoning processes and inherent risks of integration with large language models.
Approach:	They propose a framework for trustworthy fake news detection that prioritizes explainability, generalizability and controllability of models.
Outcome:	The proposed framework prioritizes explainability, generalizability and controllability of models.

Copied to clipboard

Shaobo Cui, Zhijing Jin, Bernhard Schölkopf, Boi Faltings

Reasoning

Challenge:	Despite its significance, a systematic exploration of commonsense causality is lacking.
Approach:	They focus on taxonomies, benchmarks, acquisition methods, qualitative reasoning, and quantitative measurements in commonsense causality.
Outcome:	The proposed method synthesizes insights from over 200 representative articles and provides a practical guide for beginners.

QuBE: Question-based Belief Enhancement for Agentic LLM Reasoning (2024.emnlp-main)

Copied to clipboard

Minsoo Kim, Jongyoon Kim, Jihyuk Kim, Seung-won Hwang

Information Retrieval

Challenge:	Recent advances in Large Language Models (LLMs) have led to an explosion of interest in their deployment as agents.
Approach:	They propose a method that enhances agents’ focus on task-relevant contexts by constructing a belief state via question answering.
Outcome:	The proposed method outperforms established baselines and achieves marked improvements on the BeIR zero-shot retrieval benchmark.

No Black Boxes: Interpretable and Interactable Predictive Healthcare with Knowledge-Enhanced Agentic Causal Discovery (2025.findings-emnlp)

Copied to clipboard

Xiaoxue Han, Pengfei Hu, Chang Lu, Jun-En Ding, Feng Liu, Yue Ning