Papers with prediction
Attention is not not Explanation (D19-1)
Copied to clipboard
| 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. |
Generating Diverse Translation with Perturbed kNN-MT (2024.eacl-srw)
Copied to clipboard
| Challenge: | Existing methods to generate multiple translation candidates do not address the overcorrection problem, which discourages the model from generating synonymous expressions and leans toward gold standards, reducing the diversity in the candidates. |
| Approach: | They propose to introduce perturbed k-nearest neighbor machine translation (kNN-MT) to generate more diverse translations. |
| Outcome: | The proposed methods significantly improve candidate diversity and control diversity by tuning the perturbation’s magnitude. |
Knowledge-Augmented Methods for Natural Language Processing (2022.acl-tutorials)
Copied to clipboard
| Challenge: | Knowledge in natural language processing (NLP) is a rising trend especially after the advent of large scale pre-trained models. |
| Approach: | This tutorial introduces the key steps in integrating knowledge into natural language processing (NLP) it introduces knowledge grounding from text, knowledge representation and fusing. |
| Outcome: | This tutorial introduces the key steps in integrating knowledge into natural language processing including knowledge grounding from text, knowledge representation and fusing. |
LaMI: Augmenting Large Language Models via Late Multi-Image Fusion (2026.acl-short)
Copied to clipboard
| Challenge: | Large Language Models lack visual grounding on visual reasoning, despite training on text alone. |
| Approach: | They propose a late multi-image fusion method that augments LLMs with test-time visual signals. |
| Outcome: | Using a late multi-image fusion method, the proposed model outperforms LLMs on visual reasoning and matches VLMs in vision-based tasks. |
On the Effectiveness of the Pooling Methods for Biomedical Relation Extraction with Deep Learning (D19-62)
Copied to clipboard
| Challenge: | Existing models for relation extraction use different pooling mechanisms to perform pooling for RE. |
| Approach: | They conduct a comprehensive study to evaluate the effectiveness of different pooling mechanisms for deep learning in biomedical RE. |
| Outcome: | The proposed model outperforms the previous models on two biomedical datasets. |
UKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QA (2022.aacl-demo)
Copied to clipboard
Rachneet Sachdeva, Haritz Puerto, Tim Baumgärtner, Sewin Tariverdian, Hao Zhang, Kexin Wang, Hossain Shaikh Saadi, Leonardo F. R. Ribeiro, Iryna Gurevych
| Challenge: | Question Answering (QA) systems rely on deep neural networks, which are difficult to interpret by humans. |
| Approach: | They propose an interpretable model that provides an explanation infrastructure for comparing models based on saliency maps and graph-based explanations. |
| Outcome: | The proposed methods can be used to compare models based on saliency maps and graph-based explanations. |
Explainable Recommendation with Personalized Review Retrieval and Aspect Learning (2023.acl-long)
Copied to clipboard
| Challenge: | Recent years have witnessed a growing interest in the development of explainable recommendation models. |
| Approach: | They propose a model that combines prediction and generation tasks to produce more persuasive explanations by obtaining additional information from the training sets. |
| Outcome: | The proposed model outperforms state-of-the-art models on three datasets and shows that it is more persuasive than previous models. |
Gatekeeper to save COGS and improve efficiency of Text Prediction (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) require massive amounts of computation and storage, such an approach incurs network and high execution cost. |
| Approach: | They propose a model gatekeeper to stop LLM calls that result in incorrect predictions . they show it can save 46.6% of COGS and improve user experience by not showing incorrect predictions. |
| Outcome: | The proposed model gatekeeper saves 46.6% of COGS and improves user experience . it also improves the suggestion rate of the proposed model by 73% . |
LM Transparency Tool: Interactive Tool for Analyzing Transformer Language Models (2024.acl-demos)
Copied to clipboard
| 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 . |
AdapterHub Playground: Simple and Flexible Few-Shot Learning with Adapters (2022.acl-demo)
Copied to clipboard
Tilman Beck, Bela Bohlender, Christina Viehmann, Vincent Hane, Yanik Adamson, Jaber Khuri, Jonas Brossmann, Jonas Pfeiffer, Iryna Gurevych
| Challenge: | AdapterHub Playground is an open-access tool for researchers to use pretrained language models without writing a single line of code. |
| Approach: | They propose a tool which allows researchers to leverage pretrained models without writing a single line of code for a variety of NLP tasks. |
| Outcome: | The proposed model can be used for prediction, training and analysis of textual data without writing a single line of code. |
Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations (2022.tacl-1)
Copied to clipboard
| Challenge: | Annotators may systematically disagree with one another, reflecting their individual biases and values, especially in the case of subjective tasks such as detecting affect, aggression, and hate speech. |
| Approach: | They propose to combine multi-annotator models with multi-task based approaches to resolve disagreements between annotations and derive single ground truth labels. |
| Outcome: | The proposed model outperforms majority voting and averaging methods and estimates uncertainty in predictions. |
Mediators in Determining what Processing BERT Performs First (2021.naacl-main)
Copied to clipboard
| Challenge: | Probing neural models for the ability to perform downstream tasks using their activation patterns is often used to localize what parts of the network specialize in performing which tasks. |
| Approach: | They propose to consider the prediction’s context length as a potential mediating factor and consider the length of the span whose processing is minimally required to perform the prediction. |
| Outcome: | The proposed model can get 196 different rankings when probing with seven tasks, the authors show . |
Model Agnostic Answer Reranking System for Adversarial Question Answering (2021.eacl-srw)
Copied to clipboard
| Challenge: | Existing methods for adversarial QA are often model specific and require retraining of the model . authors propose a simple method that can be applied directly to any QA model based on a model-agnostic approach . |
| Approach: | They propose a model-agnostic approach that explicitly reranks candidate answers . they use a QA model that scores candidates on the basis of content overlap with the question . |
| Outcome: | The proposed method outperforms state-of-the-art models on adversarial examples without retraining. |
GNNer: Reducing Overlapping in Span-based NER Using Graph Neural Networks (2022.acl-srw)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) uses sequence labelling and span classification to identify entities. |
| Approach: | They propose a framework that uses Graph Neural Networks to enrich the span representation to reduce the number of overlapping spans during prediction. |
| Outcome: | The proposed framework reduces the number of overlapping spans while maintaining competitive metric performance. |
Inference-Time Selective Debiasing to Enhance Fairness in Text Classification Models (2025.naacl-short)
Copied to clipboard
| Challenge: | Several studies have investigated and promoted fairness, and a variety of definitions have been proposed to address this problem. |
| Approach: | They propose a selective debiasing method that removes bias from model predictions instead of discarding them at inference time. |
| Outcome: | The proposed method achieves better results than standard uncertainty quantification methods on text classification datasets with encoder-based classification models. |
Multi-task Learning of Spoken Language Understanding by Integrating N-Best Hypotheses with Hierarchical Attention (2020.coling-industry)
Copied to clipboard
| Challenge: | Existing methods to integrate hypotheses into speech recognition systems are noisy and can cause information loss. |
| Approach: | They propose to integrate hypotheses into multi-task learning and transfer learning to improve performance. |
| Outcome: | The proposed model improves domain and intent classification by 19% and 37% compared to current methods . the proposed model could recover transcription and rewrite the query for a better understanding . |
The Effects of Surprisal across Languages: Results from Native and Non-native Reading (2022.findings-aacl)
Copied to clipboard
| Challenge: | Context-dependent predictive processes have been proposed as a core component of the human cognitive system. |
| Approach: | They extract surprisal estimates from mBERT and assess their predictive power on the MECO corpus, a cross-linguistic dataset of eye movement behavior in reading. |
| Outcome: | The proposed model is based on a cross-linguistic dataset of eye movement behavior in reading. |
Do Deep Neural Nets Display Human-like Attention in Short Answer Scoring? (2022.naacl-main)
Copied to clipboard
| Challenge: | DL-based graders often lack the ability to explain and justify how a prediction is made, which decreases their trustworthiness and hinders educators from embracing them in practice. |
| Approach: | They conducted a user study to determine whether DL-based graders align with human grader . they also ran a randomized controlled experiment to explore the impact of highlighting important words detected by DL grader. |
| Outcome: | The proposed method enables human graders to identify important words when marking short answer questions. |
CasEE: A Joint Learning Framework with Cascade Decoding for Overlapping Event Extraction (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods assume that events appear in sentences without overlaps . overlapping event extraction is a challenging task in natural language understanding . |
| Approach: | They propose a joint learning framework with cascade decoding for overlapping event extraction . they sequentially perform type detection, trigger extraction and argument extraction based on the specific former prediction . |
| Outcome: | The proposed framework improves on a public event extraction benchmark . it sequentially performs type detection, trigger extraction and argument extraction . |
BERT-Based Neural Collaborative Filtering and Fixed-Length Contiguous Tokens Explanation (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing models that learn accurate representations of users and items are based on ratings, which oversimplify user preferences and item characteristics. |
| Approach: | They propose a novel, accurate, and explainable recommender model that integrates three key elements: BERT, multilayer perceptron, and maximum subarray problem to derive contextualized review features, model user-item interactions, and generate explanations. |
| Outcome: | The proposed model outperforms state-of-the-art models by an improvement gain of nearly 7% based on the human judges’ assessment . |
How Bad are PoS Tagger in Cross-Corpora Settings? Evaluating Annotation Divergence in the UD Project. (N19-1)
Copied to clipboard
| Challenge: | Using annotation variation principles, Part-of-Speech tagging performance degrades when applied to test sentences that depart from training data. |
| Approach: | They propose to use the annotation variation principle to identify inconsistencies between annotations . they also evaluate their impact on prediction performance . |
| Outcome: | The proposed method can detect errors in gold standard annotations and improve prediction performance. |
Are self-explanations from Large Language Models faithful? (2024.findings-acl)
Copied to clipboard
| Challenge: | Instruction-tuned Large Language Models excel at many tasks and will explain their reasoning, so-called self-explanations. |
| Approach: | They propose to employ self-consistency checks to measure faithfulness to LLMs to determine if they are model-dependent and if their reasoning is convincing and wrong. |
| Outcome: | The proposed measures show that self-explanations are explanation, model, and task-dependent and should not be trusted in general. |
How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasets (2022.starsem-1)
Copied to clipboard
| Challenge: | Existing studies on the performance of pre-trained language models on natural language understanding tasks have focused on the natural language inference and textual entailment tasks. |
| Approach: | They propose to use corrupted data to fine-tune pre-trained language models to assess their language understanding capabilities. |
| Outcome: | The proposed transformations can be applied to all but one NLU task and show that understanding the meaning of utterances is not required for high performance. |
Re-Temp: Relation-Aware Temporal Representation Learning for Temporal Knowledge Graph Completion (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models ignore ability to skip irrelevant snapshots according to entity-related relations in query . TKGC is difficult and even large-scale pre-trained language models such as gist ignore explicit temporal information. |
| Approach: | They propose a model that leverages explicit temporal embedding as input to skip unnecessary information for prediction. |
| Outcome: | The proposed model outperforms all state-of-the-art models on six datasets . it incorporates skip information flow after each timestamp to skip unnecessary information . |
Adaptive Semiparametric Language Models (2021.tacl-1)
Copied to clipboard
| Challenge: | Existing language models that use a large parametric neural network with episodic memory are not efficient. |
| Approach: | They propose a language model that combines a large parametric neural network with a non-parametric episodic memory component in an integrated architecture. |
| Outcome: | The proposed model can predict local context, short-term memory, or long-term memories on an ad hoc basis depending on the context. |
CoTEVer: Chain of Thought Prompting Annotation Toolkit for Explanation Verification (2023.eacl-demo)
Copied to clipboard
| Challenge: | Chain-of-thought prompting generates an explanation before the final prediction, but its performance is affected by the factual accuracy of the explanation. |
| Approach: | They propose a toolkit for annotating the factual correctness of generated explanations and collecting revision data of wrong explanations. |
| Outcome: | The proposed toolkit is publicly available at https://github.com/SeungoneKim/CoTEVer. |
SHIELD: LLM-Driven Schema Induction for Predictive Analytics in EV Battery Supply Chain Disruptions (2024.emnlp-industry)
Copied to clipboard
Zhi-Qi Cheng, Yifei Dong, Aike Shi, Wei Liu, Yuzhi Hu, Jason O’Connor, Alexander Hauptmann, Kate Whitefoot
| Challenge: | EV battery supply chain is vulnerable to disruptions caused by natural disasters and geopolitical tensions. |
| Approach: | They propose a system integrating Large Language Models with domain expertise for EV supply chain risk assessment. |
| Outcome: | Evaluated on 12,070 paragraphs from 365 sources (2022-2023), SHIELD outperforms baseline GCNs and LLM+prompt methods in disruption prediction. |
Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures (P18-1)
Copied to clipboard
| Challenge: | Structured embeddings based on regions, densities, and orderings have gained popularity for their inductive bias towards the essential asymmetries inherent in problems such as image captioning. |
| Approach: | They propose a box lattice and accompanying probability measure to capture negative correlations over arbitrary concepts. |
| Outcome: | The proposed model can capture anti-correlation and even disjoint concepts while learning from and predicting calibrated uncertainty. |
Multimodal Relation Extraction with Cross-Modal Retrieval and Synthesis (2023.acl-short)
Copied to clipboard
| Challenge: | Existing retrieval-augmented approaches focus on modeling the retrieved textual knowledge but this may not be able to accurately identify complex relations. |
| Approach: | They propose to retrieve multimodal relation extraction information based on object, sentence, and whole image . they propose to synthesize the object-level, image-level and sentence-level information . |
| Outcome: | The proposed method outperforms state-of-the-art models on multimodal relation extraction. |
Augmenting Neural Networks with First-order Logic (P19-1)
Copied to clipboard
| Challenge: | Existing paradigms for training neural networks require large datasets, a paper argues . we present a framework for introducing declarative knowledge to neural networks . |
| Approach: | They propose a framework for introducing declarative knowledge to neural networks . they compile logical statements into graphs that augment a network without extra learnable parameters or manual redesign. |
| Outcome: | The proposed framework improves on three tasks, especially in low-data regimes. |
BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering (N19-1)
Copied to clipboard
| Challenge: | Existing datasets for question answering and machine comprehension (MC) are limited to a single paragraph, or even part of it. |
| Approach: | They propose a bi-directional Attention Entity Graph Convolutional Network (BAG) that leverages relationships between nodes in an entity graph and attention information between a query and the entity graph to generate a prediction. |
| Outcome: | Experimental results show that the proposed network achieves state-of-the-art accuracy on the QAngaroo WIKIHOP dataset. |
Identifying Implicit Quotes for Unsupervised Extractive Summarization of Conversations (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing methods of unsupervised summarization are lacking. |
| Approach: | They propose an unsupervised unsupervised extractive neural summarization model that extracts quotes as summaries from conversational texts. |
| Outcome: | The proposed model can extract quoted sentences as summaries from two email and social media datasets. |
Scale Is All You Need: Analyzing Modality Interaction and Speaker Intent Without Fine-Tuning (2026.eacl-srw)
Copied to clipboard
| Challenge: | Recent work on sarcasm and humor detection uses large multimodal Transformers, but they are computationally expensive and opaque. |
| Approach: | They propose a lightweight framework for multimodal sarcasm detection that combines frozen text, audio, and visual embeddings from pretrained encoders through compact fusion heads. |
| Outcome: | The proposed framework improves on the best unimodal baseline by combining text, audio, and visual embeddings from pretrained encoders with compact fusion heads. |
Multimodal Contrastive Learning via Uni-Modal Coding and Cross-Modal Prediction for Multimodal Sentiment Analysis (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Recent work on multimodal representation learning has focused on uni-modality pre-training or cross-modalities integration. |
| Approach: | They propose a framework for multimodal representation learning that uses uni-modal contrastive coding and an efficient unimodal feature augmentation strategy to capture intermodal dynamics. |
| Outcome: | The proposed framework surpasses state-of-the-art methods on two public datasets. |
Personalized Filled-pause Generation with Group-wise Prediction Models (2022.lrec-1)
Copied to clipboard
| Challenge: | Disfluency generation is a method to generate personalized filled pauses (FPs) compared with fluent text generation, it is difficult to predict them because of the sparsity of position and frequency difference between more and less frequently used FPs. |
| Approach: | They propose a method to generate personalized filled pauses (FPs) by group-wise prediction models. |
| Outcome: | The proposed method generates personalized filled pauses (FPs) with group-wise prediction models. |
BFClass: A Backdoor-free Text Classification Framework (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Various trigger design strategies have been explored to attack text classifiers, however, defending such attacks remains an open problem. |
| Approach: | They propose a backdoor-free training framework that poisons a subset of training data by injecting trigger patterns and setting their labels as the target labels. |
| Outcome: | The proposed framework can detect all the triggers, remove 95% of poisoned training samples with very limited false alarms, and achieve almost the same performance as the models trained on benign training data. |
CMTD: Cognitive Modeling with Traits and Distortions for Multimodal Emotion Recognition in Conversations (2026.findings-acl)
Copied to clipboard
| Challenge: | Experimental results show that traits temper negativity bias from distortions, and cognitive modeling with psychological, visual, and acoustic information can improve the performance of MERC. |
| Approach: | They propose a framework for multimodal emotion recognition in conversations that takes advantage of stable personality traits, dynamic cognitive distortions, visual and acoustic features of interlocutors to enhance the emotional intelligence of LLMs. |
| Outcome: | Experimental results show that traits temper negativity bias from distortions, and cognitive modeling with psychological, visual, and acoustic information can improve the performance of MERC. |
A Fully Hyperbolic Neural Model for Hierarchical Multi-Class Classification (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models for fine-grained entity typing have a hierarchical structure . prior work has integrated only explicit hierarchic information by formulating a hierarchy-aware loss or by representing instances and labels in a joint Euclidean embedding space. |
| Approach: | They propose a fully hyperbolic model for multi-class multi-label classification that performs all operations in hyperbolical space. |
| Outcome: | The proposed model performs all operations in hyperbolic space on two challenging datasets and shows it is comparable to state-of-the-art methods on fine-grained classification with remarkable reduction of parameter size. |
Heterogeneous Supervised Topic Models (2022.tacl-1)
Copied to clipboard
| Challenge: | Researchers in the social sciences are interested in the relationship between text and an outcome of interest. |
| Approach: | They develop a probabilistic approach to text analysis and prediction using a joint model of text and outcomes to find heterogeneous patterns. |
| Outcome: | The proposed model outperforms other methods on eight datasets and consistently outperformed other models. |
Assessing Combinational Generalization of Language Models in Biased Scenarios (2022.aacl-short)
Copied to clipboard
| Challenge: | Existing work focuses on assessing in-domain knowledge, but shedding light on what pre-trained Language Models learn is important. |
| Approach: | They propose a method to assess a PLM's generalization capacity in biased scenarios by combining component combinations where it could be easy for the PLMs to learn shortcuts from the training corpus. |
| Outcome: | The proposed model can overcome distribution shifts in the training corpus and with sufficient data. |
Dialetto, ma Quanto Dialetto? Transcribing and Evaluating Dialects on a Continuum (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent work on dialect variation in NLP treats dialects as discrete categories . dialect variation is a focus of increasing interest in the field . |
| Approach: | They examine performance differences between Italian dialects by incorporating performance data from different regions of the world. |
| Outcome: | The results show that performance disparities are due to dialects that are more similar to the standard variety. |
Meta-learning via Language Model In-context Tuning (2022.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models have reduced "task learning and prediction" to a simple sequence prediction problem. |
| Approach: | They propose a meta-learning method that recasts task adaptation and prediction as a sequence prediction problem. |
| Outcome: | The proposed method outperforms MAML on two classification tasks and improves on binaryClfs. |
Solving Data Sparsity for Aspect Based Sentiment Analysis Using Cross-Linguality and Multi-Linguality (N18-1)
Copied to clipboard
| Challenge: | Efficient word representations play an important role in solving various problems related to NLP, data mining, text mining etc. |
| Approach: | They propose to leverage bilingual word embeddings learned through a parallel corpus to minimize the effect of data sparsity. |
| Outcome: | The proposed model is tested against state-of-the-art methods in two experimental setups. |
Faithfulness Beyond Plausibility: Auditing Human Explanations in Educational Assessment (2026.acl-srw)
Copied to clipboard
| Challenge: | a gap exists between explanation components and how scores are constructed, and whether they reflect how scores were constructed . authors: explanation components are structurally inconsistent and may not be used as post-hoc justifications . |
| Approach: | They propose to use human tutor grading traces to test whether explanations are reliable . they find that removing rubric-level information leads to substantial changes in reconstructed scores . |
| Outcome: | The proposed diagnostic measures how explanation components contribute to score interpretation . removing rubric-level information leads to substantial changes in reconstructed scores . |
Prediction or Comparison: Toward Interpretable Qualitative Reasoning (2021.findings-acl)
Copied to clipboard
| Challenge: | Qualitative relationships are a significant portion of textual knowledge . current approaches use semantic parsers to transform natural language inputs into logical expressions or a "black-box" model to solve them in one step. |
| Approach: | They propose to use neural network modules to simulate qualitative reasoning tasks . they use two qualitative reasoning question answering datasets to test their methods . |
| Outcome: | Experiments on two qualitative reasoning question answering datasets show the proposed methods are general and general and interpretable. |
A Simple yet Effective Relation Information Guided Approach for Few-Shot Relation Extraction (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to introduce relation information into the model are limited by labeling and data scarcity. |
| Approach: | They propose a direct addition approach to introduce relation information into a model by concatenating two views of relations and adding them to the original prototype. |
| Outcome: | The proposed approach improves on the benchmark dataset FewRel 1.0 and shows comparable results to the state-of-the-art. |
Towards Generative Aspect-Based Sentiment Analysis (2021.acl-short)
Copied to clipboard
| Challenge: | Existing work on Aspect-based sentiment analysis ignores the rich label semantics of ABSA. |
| Approach: | They propose to tackle various ABSA tasks in a unified generative framework . they propose to use annotation-style and extraction-style modeling to enable training . |
| Outcome: | The proposed framework achieves state-of-the-art on four ABSA tasks across multiple benchmark datasets. |
ThinkSum: Probabilistic reasoning over sets using large language models (2023.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have a substantial capacity for high-level analogical reasoning, but they fail in scenarios that require reasoning over multiple objects or facts and making sequences of logical deductions. |
| Approach: | They propose a two-stage probabilistic inference paradigm, ThinkSum, which reasons over sets of objects or facts in a structured manner. |
| Outcome: | The proposed paradigm improves on the BIG-bench suite of evaluation tasks. |
Effective Use of Transformer Networks for Entity Tracking (D19-1)
Copied to clipboard
| Challenge: | Existing pre-trained language models for entity-related tasks are not able to handle the nuances of procedural text. |
| Approach: | They propose to use pre-trained transformer networks to track entities in procedural text by restructuring input to focus on a particular entity. |
| Outcome: | The proposed models outperform baseline models on ingredient detection in recipes and QA over scientific processes on two different tasks. |
Self-Training with Differentiable Teacher (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for self-training are interpreted as teacher-student frameworks, where the teacher generates pseudo-labels and the student makes predictions. |
| Approach: | They propose a differentiable self-training method that treats teacher-student as a Stackelberg game where a leader is always in a more advantageous position than a follower. |
| Outcome: | The proposed model outperforms existing methods on semi- and weakly-supervised learning tasks on semi and weak supervised tasks. |
COMMUNITYNOTES: A Dataset for Exploring the Helpfulness of Fact-Checking Explanations (2026.findings-eacl)
Copied to clipboard
| Challenge: | X, Meta, and TikTok are experimenting with community-based factchecking . community-driven verification is a way to provide explanatory notes that clarify why a post might be misleading . |
| Approach: | They propose a framework that optimizes the helpfulness of explanatory notes and the reason for this by automatically optimizing the prompt definitions. |
| Outcome: | The proposed framework improves helpfulness and reason prediction on 104k posts with user-provided notes and helpfulness labels. |
Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU models (2021.naacl-main)
Copied to clipboard
Mengnan Du, Varun Manjunatha, Rajiv Jain, Ruchi Deshpande, Franck Dernoncourt, Jiuxiang Gu, Tong Sun, Xia Hu
| Challenge: | Recent studies indicate that NLU models are prone to rely on shortcut features for prediction, without achieving true language understanding. |
| Approach: | They propose a shortcut mitigation framework to suppress NLU models from making overconfident predictions for samples with large shortcut degree. |
| Outcome: | The proposed framework suppresses the model from making overconfident predictions for samples with large shortcut degree. |
Deconfounding Legal Judgment Prediction for European Court of Human Rights Cases Towards Better Alignment with Experts (2022.emnlp-main)
Copied to clipboard
| Challenge: | Legal Judgement Prediction systems without expert-informed adjustments can be vulnerable to shallow, distracting surface signals. |
| Approach: | They propose to use domain expertise to identify statistically predictive but legally irrelevant information and adopt adversarial training to prevent it from relying on it. |
| Outcome: | The proposed model aligns better with expert rationales than baseline models . the results are compared with an existing benchmark dataset of human rights cases . |
ConnPrompt: Connective-cloze Prompt Learning for Implicit Discourse Relation Recognition (2022.coling-1)
Copied to clipboard
| Challenge: | Existing paradigms for Implicit Discourse Relation Recognition (IDRR) do not exploit linguistic evidence embedded in the pre-training process. |
| Approach: | They propose a new paradigm to detect and classify relation sense between two text segments without an explicit connective. |
| Outcome: | The proposed method significantly outperforms the state-of-the-art algorithms even with fewer training data. |
Simultaneously Self-Attending to All Mentions for Full-Abstract Biological Relation Extraction (N18-1)
Copied to clipboard
| Challenge: | Existing work in relation extraction ignores relationships expressed across sentence boundaries . document-level annotation is common in biological text . |
| Approach: | They propose a model which simultaneously predicts relationships between all mention pairs in a document. |
| Outcome: | The proposed model is larger than existing human-annotated biological information extraction datasets and more accurate than distantly supervised alternatives. |
What to Learn, and How: Toward Effective Learning from Rationales (2022.findings-acl)
Copied to clipboard
| Challenge: | Increasing interest in learning from rationales has led to the use of human-annotated explanations to inject useful inductive biases into models. |
| Approach: | They propose several novel loss functions and learning strategies to exploit human rationales to augment model prediction accuracy. |
| Outcome: | The proposed learning strategies improve on three datasets with human rationales and show that they are more efficient than baselines. |
Revisiting Multimodal Transformers for Tabular Data with Text Fields (2024.findings-acl)
Copied to clipboard
| Challenge: | Tabular data with text fields can be used in financial risk assessment and diagnosis prediction. |
| Approach: | They propose a tabular/text dual-stream Transformer network with numerical embedding schemes and an overall attention module to estimate whether a prediction is uncertain. |
| Outcome: | The proposed model can estimate whether a prediction is uncertain or not based on two well-informed modality streams . |
Sense-Aware Neural Models for Pun Location in Texts (P18-2)
Copied to clipboard
| Challenge: | Puns where the two meanings share the same pronunciation are known as homographic puns. |
| Approach: | They propose a sense-aware neural model to address the task of pun location . they first obtain several WSD results for the text and then leverage a bidirectional LSTM network to model each word senses. |
| Outcome: | The proposed model is based on a SemEval 2017 benchmark dataset showing that it can predict homographic puns. |
LangSAMP: Language-Script Aware Multilingual Pretraining (2025.acl-long)
Copied to clipboard
| Challenge: | Recent multilingual pretrained language models often avoid using language embeddings, which places a significant burden on token representations to encode all language-specific information. |
| Approach: | They propose a method that incorporates both language and script embeddings into the output of Transformer blocks before passing the final representations to the language modeling head for prediction. |
| Outcome: | The proposed method outperforms the baseline model in zero-shot crosslingual transfer across diverse downstream tasks. |
Event Pattern-Instance Graph: A Multi-Round Role Representation Learning Strategy for Document-Level Event Argument Extraction (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing role-based span selection strategies ignore interrelations between events . authors propose a multi-round role representation learning strategy for document-level event argument extraction . |
| Approach: | They propose a pattern-instance graph to capture role semantics embedded in various associations . they also propose re-inventing the role representations learned from previous analyzed documents . |
| Outcome: | The proposed model captures role semantics embedded in various associations . iteratively updates representations of role nodes and edges to enrich their semantic information . the model improves prediction performance in subsequent rounds of span selection . |
Why do you think that? Exploring Faithful Sentence-Level Rationales Without Supervision (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Large pre-trained language models, such as BERT or RoBERTa, gain impressive results on a large variety of NLP tasks, including reasoning and inference. |
| Approach: | They propose a differentiable training framework to create models which output faithful rationales on a sentence level, by solely applying supervision on the target task. |
| Outcome: | The proposed model outperforms pipeline approaches and non-differentiable models on three different datasets while exceeding pipeline counterparts. |
Issues with Entailment-based Zero-shot Text Classification (2021.acl-short)
Copied to clipboard
| Challenge: | Pre-trained BERT models with no fine-tuning can yield competitive performance against BERT fine- tuned for NLI. |
| Approach: | They propose to use any target label into a sentence of hypothesis and verify whether it could be entailed by the input. |
| Outcome: | The proposed models perform better than models fine-tuned for BERT, but the results are in general negative. |
Poetry to Prose Conversion in Sanskrit as a Linearisation Task: A Case for Low-Resource Languages (P19-1)
Copied to clipboard
| Challenge: | Obtaining the proper word ordering, called as the prose ordering, from a verse is often considered a task which requires linguistic expertise. |
| Approach: | They propose a word ordering (linearisation) task that ignores the word arrangement at the verse side. |
| Outcome: | The proposed model outperforms current models in word ordering for the translation task in Sanskrit. |
SAFR: Neuron Redistribution for Interpretability (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing studies on controlling neuron distribution for interpretability have focused on focusing on monosemanticity instead of focusing solely on feature interactions. |
| Approach: | They propose a method to regularize feature superposition by encoding representations of multiple features within a single neuron. |
| Outcome: | The proposed method improves model interpretability without compromising prediction performance. |
Sorting through the noise: Testing robustness of information processing in pre-trained language models (2021.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained language models have shown impressive performance on downstream NLP tasks, but we have yet to establish a clear understanding of their sophistication when it comes to processing, retaining, and applying information presented in their input. |
| Approach: | They examine how robustly pre-trained LMs retain and apply relevant context information in the face of distracting content. |
| Outcome: | The proposed models retain and use critical context information in the face of distracting content, while models are susceptible to factors of semantic similarity and word position. |
Improving Multi-Document Summarization through Referenced Flexible Extraction with Credit-Awareness (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing approaches to Multi-document summarization are limited due to the extremely long input length. |
| Approach: | They propose an extract-then-abstract Transformer framework to overcome the problem . they leverage pre-trained language models to construct hierarchical extractors and abstractors . |
| Outcome: | The proposed framework outperforms baseline models with comparable model sizes and achieves the best results on the Multi-News, Multi-XScience, and WikiCatSum corpora. |
Cross-Target Stance Classification with Self-Attention Networks (P18-2)
Copied to clipboard
| Challenge: | In stance classification, the target on which the stance is made defines the boundary of the task, and a classifier is usually trained for prediction on the same target. |
| Approach: | They propose a neural model that can generalize classifiers between different targets by finding useful information shared between relevant targets. |
| Outcome: | The proposed model can generalize between relevant targets and find useful information shared between relevant target domains which improves generalization in certain scenarios. |
Stop Measuring Calibration When Humans Disagree (2022.emnlp-main)
Copied to clipboard
| Challenge: | Calibration is a popular framework to evaluate whether a classifier knows when it does not know - i.e., predictive probabilities are a good indication of how likely a prediction is to be correct. |
| Approach: | They propose to measure calibration to human majority given inherent disagreements on tasks where humans inherently disagree about which class applies. |
| Outcome: | The proposed measures capture key statistical properties of human judgements including class frequency, ranking and entropy. |
Evaluating and Mitigating Inherent Linguistic Bias of African American English through Inference (2022.coling-1)
Copied to clipboard
| Challenge: | Recent studies show that NLP models trained on standard English produce biased outcomes against underrepresented English varieties. |
| Approach: | They propose a morphosyntactically-informed rule-based translation method that uses a greedy algorithm to debiase NLP models. |
| Outcome: | The proposed framework outperforms large language models while maintaining or improving the prediction performance. |
Modeling Intra and Inter-modality Incongruity for Multi-Modal Sarcasm Detection (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for sarcasm detection ignore the incongruity character in sarcasm, which is often manifested between modalities or within modalités. |
| Approach: | They propose to capture inter-modality incongruity in a text-based model by using a self-attention mechanism and a co-attention model to model the contradiction within the text. |
| Outcome: | The proposed model achieves state-of-the-art on a public multi-modal sarcasm detection dataset. |
Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining (2022.findings-emnlp)
Copied to clipboard
| Challenge: | To explain NLP models, importance measures are often used to inform input tokens are important for making a prediction. |
| Approach: | They propose a faithfulness metric that masks allegedly important tokens and retrains the model. |
| Outcome: | The proposed metric is based on LSTM-attention models and RoBERTa models. |
ACTOR: Active Learning with Annotator-specific Classification Heads to Embrace Human Label Variation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies indicate that learning from individual annotations outperforms learning from aggregated labels, though they require a considerable amount of annotation. |
| Approach: | They propose to use a multi-head model to learn from disagreements in an active learning setting to identify annotators with a single head. |
| Outcome: | The proposed model outperforms a single-head model in terms of uncertainty estimation and prediction while saving 70% of the annotation budget. |
Modeling Noisiness to Recognize Named Entities using Multitask Neural Networks on Social Media (N18-1)
Copied to clipboard
| Challenge: | Current approaches to Named Entity Recognition (NER) are effective in formal text, but they fail on informal text, where improper grammatical structures, spelling inconsistencies, and slang vocabulary prevail. |
| Approach: | They propose a multitask end-to-end bidirectional long short-term memory (BLSTM)-Conditional Random Field (CRF) network with two CRF classifiers and a feature extractor that transfers learning to a CRF for prediction. |
| Outcome: | The proposed models outperform the current state-of-the-art on the Workshop on Noisy User-generated Text 2017 dataset by 2.45% and 3.69%, establishing a more suitable approach for social media environments. |
Controlling Learned Effects to Reduce Spurious Correlations in Text Classifiers (2023.acl-long)
Copied to clipboard
| Challenge: | toxicity and IMDB review datasets show that pre-trained NLP classifiers learn spurious correlations between input features and label . |
| Approach: | They propose an algorithm to regularize the learnt effect of features on the model’s prediction to the estimated effect of a feature on label. |
| Outcome: | The proposed method minimises spurious correlations and improves minority group accuracy while improving total accuracy compared to standard training. |
What Makes Pre-trained Language Models Better Zero-shot Learners? (2023.acl-long)
Copied to clipboard
| Challenge: | Current methods for prompt learning in zero-shot scenarios rely on a development set with sufficient human-annotated data to select the best-performing prompt template. |
| Approach: | They propose a method for screening reasonable prompt templates in zero-shot text classification using language discrepancy. |
| Outcome: | The proposed method improves prediction performance in a realistic zero-shot setting, eliminating the need for labelled examples. |
Document-Level Event Argument Extraction via Optimal Transport (2022.findings-acl)
Copied to clipboard
| Challenge: | Prior work on event-level EAE models ignore syntactic structures for documents . prior work on EE is restricted to sentence-level setting where event triggers and arguments are assumed to appear in the same sentences. |
| Approach: | They propose to employ Optimal Transport to induce structures of documents based on sentence-level syntactic structures and tailored to EAE task. |
| Outcome: | The proposed model is effective in document-level EAE, with a new constraint on unrelated context words. |
Research Replication Prediction Using Weakly Supervised Learning (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to predict scientific claims’ replicability use only hand-extracted statistics features without utilizing research papers’ text information. |
| Approach: | They propose two weakly supervised learning approaches that use automatically extracted text information of research papers to improve the prediction accuracy of research replication using both labeled and unlabeled datasets. |
| Outcome: | The proposed methods achieve an accuracy of 75.76% over real-world datasets. |
Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on retrieval-augmented generation (RAG) rarely address the issue of predictive uncertainty, i.e., how likely it is that a RAG model’s prediction is incorrect. |
| Approach: | They propose a framework that induces RAG models to alter latent factors and analyzes the effect on their answers. |
| Outcome: | The proposed framework identifies two critical factors affecting RAG models' confidence in their answers and analyzes the effect on their answers. |
Calibration of Machine Reading Systems at Scale (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to calibrate open setting machine reading systems fail to scale to these settings due to various scale limitations in practical settings. |
| Approach: | They propose to extend existing calibration approaches to calibrate open-domain question answering and claim verification systems to these settings. |
| Outcome: | The proposed calibration methods can selectively predict answers when question answering systems are posed with unanswerable or out-of-the-training distribution questions. |
Less Is Better: Recovering Intended-Feature Subspace to Robustify NLU Models (2022.coling-1)
Copied to clipboard
| Challenge: | Existing approaches to debiase datasets rely on knowledge of bias attributes . current approaches focus on how to leverage kinds of supervision effectively . |
| Approach: | They propose to extend the supervision on bias by extending it into feature space. |
| Outcome: | Empirical results show that a low-dimensional subspace with intended features can represent biased datasets. |
Modality-specific Learning Rates for Effective Multimodal Additive Late-fusion (2022.findings-acl)
Copied to clipboard
| Challenge: | Multimodal machine learning uses additive late-fusion to combine feature representations from different modalities into a joint representation. |
| Approach: | They propose a Modality-Specific Learning Rate method to build late-fusion multimodal models from fine-tuned unimodal models. |
| Outcome: | The proposed method outperforms global learning rates on multiple tasks and settings and enables the models to effectively learn each modality. |
IMO: Greedy Layer-Wise Sparse Representation Learning for Out-of-Distribution Text Classification with Pre-trained Models (2024.acl-long)
Copied to clipboard
| Challenge: | IMO is a machine learning model that learns invariant features from unseen domains. |
| Approach: | They propose IMO: Invariant features Masks for Out-of-Distribution text classification to achieve OOD generalization by learning invariant feature masks. |
| Outcome: | The proposed model outperforms baseline models in various evaluation metrics and settings. |
RoR: Read-over-Read for Long Document Machine Reading Comprehension (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models for machine reading comprehension are limited to individual chunks due to encoding length constraint. |
| Approach: | They propose a read-over-read method that expands the reading field from chunk to document by predicting regional answers for each chunk. |
| Outcome: | Extensive experiments on QuAC and TriviaQA show that the proposed model performs well for long document reading. |
ConReader: Exploring Implicit Relations in Contracts for Contract Clause Extraction (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing CCE methods treat contracts as plain text, creating a barrier to understanding complex contracts. |
| Approach: | They propose a framework to model implicit relations in legal contracts to improve contract understanding . they propose Term-Definition Relation captures the relation between important terms and their definitions . |
| Outcome: | The proposed framework improves on two CCE tasks in conventional and zero-shot settings. |
Language Modeling with Editable External Knowledge (2025.findings-naacl)
Copied to clipboard
| Challenge: | Continual learning methods tackle the problem of a changing world by incrementally training on new information. |
| Approach: | They propose a retrieval-augmented generation approach that incrementally deletes or rewrites other entries in the knowledge base each time a document is added. |
| Outcome: | The proposed model improves accuracy relative to conventional retrieval-augmented generation by 7-13% and 6-10% absolute. |
Self-Supervised Position Debiasing for Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for debiasing large language models require external bias knowledge or annotated non-biased samples, which is lacking for position debiases. |
| Approach: | They propose a self-supervised position debiasing framework that leverages unsupervised responses from pre-trained LLMs for debiazing without external bias knowledge. |
| Outcome: | The proposed framework outperforms existing methods in mitigating three types of position biases on eight datasets and five tasks. |
A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning (D19-1)
Copied to clipboard
| Challenge: | Existing models for reading comprehension and question answering do not support discrete reasoning abilities. |
| Approach: | They propose a reading comprehension model that uses a multi-type answer predictor and a multiple-span extraction method to produce one or multiple text spans. |
| Outcome: | The proposed model achieves 79.9 F1 on the DROP hidden test set, creating new state-of-the-art results. |
Read Extensively, Focus Smartly: A Cross-document Semantic Enhancement Method for Visual Documents NER (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods to extract entities from visually-rich documents ignore the inherent multimodality of VRDs and thus the suboptimal results are achieved. |
| Approach: | They propose a multimodal semantic enhancement method that filters redundant information in the current document and a cross-document information awareness technique to enrich the entity-related context. |
| Outcome: | The proposed method outperforms existing methods on two documents understanding benchmarks covering eight languages. |
Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Previous studies have investigated how different factors affect faithfulness of model explanations . |
| Approach: | They find that the larger the multilingual model, the less faithful FAs are compared to its counterpart monolingual models. |
| Outcome: | The results show that the larger the multilingual model, the less faithful the FAs are compared to its counterpart monolingual models. |
Uncertainty-Aware Label Refinement for Sequence Labeling (2020.emnlp-main)
Copied to clipboard
| Challenge: | Conditional random fields (CRF) for label decoding have been a problem for many tasks. |
| Approach: | They propose a two-stage label decoding framework that model long-term label dependencies while being much more computationally efficient. |
| Outcome: | The proposed method outperforms the CRF-based methods and greatly accelerates the inference process. |
Few-shot Knowledge Graph Relational Reasoning via Subgraph Adaptation (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods to predict unseen triplets from knowledge graphs are limited by spurious information in KGs. |
| Approach: | They propose a framework that adapts contextualized graphs to subgraphs generated from support and query triplets to perform the prediction. |
| Outcome: | The proposed framework extracts more comprehensive information from support triplets while minimizing spurious information when predicting query triplet. |
Fusion: Towards Automated ICD Coding via Feature Compression (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to assign ICD codes from unstructured clinical notes are noisy and prone to errors. |
| Approach: | They propose a feature compressed ICD coding model called Fusion to address this problem. |
| Outcome: | The proposed model outperforms existing models on two widely used datasets. |
How Many and Which Training Points Would Need to be Removed to Flip this Prediction? (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing methods to find St using brute-force are intractable. |
| Approach: | They propose a fast approximation method to find St based on influence functions . they propose to identify a minimum subset of training data that one would need to remove . |
| Outcome: | The proposed method can find St based on influence functions for simple classification models. |
Neuron-Level Knowledge Attribution in Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for attribution of knowledge in large language models struggle to operate at neuron level due to computational constraints. |
| Approach: | They propose a static method for pinpointing significant neurons using three metrics . they also propose identifying "query neurons" which activate these "value neurons" |
| Outcome: | The proposed method shows superior performance across three metrics compared to seven other methods . it analyzes six types of knowledge across attention and feed-forward network layers . |
Generating Diverse Corrections with Local Beam Search for Grammatical Error Correction (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods of acquiring diverse outputs focus on revising all tokens of a sentence. |
| Approach: | They propose a beam search method to obtain diverse outputs in a local sequence transduction task where most of the tokens in the source and target sentences overlap. |
| Outcome: | The proposed method generates more diverse corrections without losing accuracy in the local sequence transduction task. |
Journey Before Destination: On the importance of Visual Faithfulness in Slow Thinking (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing evaluations for visual hallucinations are narrow. |
| Approach: | They propose a framework that decomposes reasoning chains into perception versus reasoning steps and uses off-the-shelf VLM judges for step-level faithfulness. |
| Outcome: | The proposed framework reduces Unfaithful Perception Rate while preserving final-answer accuracy. |
A Dataset of Offensive Language in Kosovo Social Media (2022.lrec-1)
Copied to clipboard
| Challenge: | Social media are a central part of people’s lives but are rife with bullying and offensive language, creating an unsafe environment for their users. |
| Approach: | They propose to use user-generated comments on Facebook and YouTube from selected Kosovo news platforms to annotate offensive language in Albanian. |
| Outcome: | The proposed system improves on Danish but not Albanian, on offensive language recognition and distinguishing targeted and untargeted offence. |
TOD-Flow: Modeling the Structure of Task-Oriented Dialogues (2023.emnlp-main)
Copied to clipboard
Sungryull Sohn, Yiwei Lyu, Anthony Liu, Lajanugen Logeswaran, Dong-Ki Kim, Dongsub Shim, Honglak Lee
| Challenge: | Recent advances in task-oriented dialogue systems have limitations regarding transparency and controllability. |
| Approach: | They propose to infer the TOD-flow graph from dialog data annotated with dialog acts and integrate it with any dialogue model to improve its prediction performance, transparency, and controllability. |
| Outcome: | The proposed approach improves dialog act classification and response generation performance in the MultiWOZ and SGD benchmarks. |
N-ary Constituent Tree Parsing with Recursive Semi-Markov Model (2021.acl-long)
Copied to clipboard
| Challenge: | Existing graph-based constituent parsing methods generate hidden nodes with the dummy label inside the n-ary nodes to transform the tree into a binary tree for prediction. |
| Approach: | They propose a graph-based constituent parsing framework that uses a 1-order semi-Markov model to predict the immediate children sequence of a constituent candidate. |
| Outcome: | The proposed framework obtains the F1 of 95.92% and 92.50% on the datasets of PTB and CTB 5.1 respectively. |
Two Examples are Better than One: Context Regularization for Gradient-based Prompt Tuning (2023.findings-acl)
Copied to clipboard
| Challenge: | Prompting has gained tremendous attention as an efficient method for the adaptation of large-scale language models. |
| Approach: | They propose a regularization method that guides a prompt to produce a task context properly. |
| Outcome: | The proposed method improves prediction performance in a zero-shot in-context learning setting without demonstration examples for in-constitu learning. |
How many data points is a prompt worth? (2021.naacl-main)
Copied to clipboard
| Challenge: | Proponents of prompting argue that they provide a method for injecting task-specific guidance, which is beneficial in low-data regimes. |
| Approach: | They aim to quantify prompting's benefit by testing prompts in a fair setting . they propose to use a generic model head or a task-specific prompt for prediction . |
| Outcome: | The proposed approach is used in T5 fine-tuning leading to state-of-the-art results on the SuperGLUE benchmark. |
MapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extraction (2021.emnlp-main)
Copied to clipboard
| Challenge: | Neural relation extraction models have shown promising results on long-tail tasks, but performance drops dramatically as the number of instances for a relation decreases. |
| Approach: | They propose a framework considering both label-agnostic and label-aligned mapping information for low resource relation extraction. |
| Outcome: | The proposed framework improves on low-resource relation extraction tasks by incorporating label-agnostic and label-based mapping information in pretraining and fine-tuning. |
Fighting Spurious Correlations in Text Classification via a Causal Learning Perspective (2025.naacl-long)
Copied to clipboard
| Challenge: | In text classification tasks, models often rely on spurious correlations for predictions, incorrectly associating irrelevant features with the target labels. |
| Approach: | They propose a Causally Calibrated Robust Classifier which integrates a causal feature selection method based on counterfactual reasoning and an unbiased inverse propensity weighting (IPW) loss function. |
| Outcome: | The proposed method achieves state-of-the-art performance among methods without group labels and can compete with the models that utilize group labels. |
A Joint Learning Framework for Restaurant Survival Prediction and Explanation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in deep learning have various models that research reviews and interactions for different kinds of tasks, such as predicting restaurant survival. |
| Approach: | They propose a joint learning framework for explainable restaurant survival prediction based on multi-modal data of user-restaurant interactions and users’ textual reviews. |
| Outcome: | The proposed framework improves on two datasets showing that it can model restaurant interactions and users’ textual reviews. |
Low-resource Taxonomy Enrichment with Pretrained Language Models (2021.emnlp-main)
Copied to clipboard
| Challenge: | Taxonomies represent hierarchical relationships between terms or entities. |
| Approach: | They propose a framework for taxonomy enrichment in low-resource settings with pretrained language models as knowledge bases to compensate for the shortage of information. |
| Outcome: | The proposed framework predicts whether inputted term pairs have hierarchical relationships and leverages implicit knowledge from the LM to generate queries efficiently. |
You Only Query Twice: Multimodal Rumor Detection via Evidential Evaluation from Dual Perspectives (2025.coling-main)
Copied to clipboard
| Challenge: | Existing rumor detectors exhibit limitations in fully exploiting responses to the source tweet as essential public opinions, and in explaining and indicating the reliability of the results obtained. Existing research mainly combats this with content and response-based detection methods. |
| Approach: | They propose a Large Language Model with both multimodal source content and the corresponding response set to extract contrasting evidence to enable maximal utilization of informative responses. |
| Outcome: | The proposed approach can indicate the model’s uncertainty (i.e., reliability) of the results. |
Emotion-Infused Models for Explainable Psychological Stress Detection (2021.naacl-main)
Copied to clipboard
| Challenge: | a new study examines the use of emotion detection for detecting psychological stress in online posts . traditional multi-task learning and emotion-based language model fine-tuning are used to improve the model . |
| Approach: | They propose to use a semantically related task, emotion detection, for detecting psychological stress in online posts . they propose multi-task learning and emotion-based language model fine-tuning to improve the model . |
| Outcome: | The proposed model is more explainable and human-like than a black-box model . the proposed model mirrors psychological components of stress, the authors show . |
Self-Adaptive Named Entity Recognition by Retrieving Unstructured Knowledge (2023.eacl-main)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is costly because of lack of training data and domain experts. |
| Approach: | They propose a self-adaptive neural model that retrieves external knowledge from unstructured text to learn the usages of entities that have not been learned well. |
| Outcome: | The proposed model outperforms strong baselines on cross-neuro-ner datasets by 2.35 points in F1 metric. |
Interactive Classification by Asking Informative Questions (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for intent classification rely on a single user input and do not interact with the user to reduce ambiguity and improve the final prediction. |
| Approach: | They propose a limited form of interaction to natural language intent classification . they add binary or multi-choice questions to the system to ask missing information . |
| Outcome: | The proposed method can be bootstrapped without interaction data and is scalable to two domains. |
Generalizable Sarcasm Detection is Just Around the Corner, of Course! (2024.naacl-long)
Copied to clipboard
| Challenge: | sarcasm can be used to hurt, criticize, or deride but also to be mocking, humorous, or to bond. |
| Approach: | They tested the robustness of sarcasm detection models by fine-tuning their behavior on four sarkasmatic datasets . they found that models performed better when fine- tuned with third-party labels than with author labels. |
| Outcome: | The proposed models performed better when fine-tuned with third-party labels than with author labels on the same dataset and across different datasets. |
Multi-Modal Sarcasm Detection in Twitter with Hierarchical Fusion Model (P19-1)
Copied to clipboard
| Challenge: | Existing methods to detect sarcasm focus on text, but they are insufficient for multi-modal messages. |
| Approach: | They propose a multi-modal hierarchical sarcasm detection model for tweets consisting of texts and images in Twitter. |
| Outcome: | The proposed model is able to detect sarcasm on twitter using three modalities . the proposed model can be used in customer service, opinion mining and harassment detection . |
Measuring and Improving Faithfulness of Attention in Neural Machine Translation (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing evidence for faithfulness of neural machine translation models is lacking. |
| Approach: | They propose a novel objective that rewards faithful behaviour by the model through probability divergence and a differentiable objective that can increase faithfulness without reducing the translation quality. |
| Outcome: | The proposed objective increases faithfulness without reducing translation quality and can even improve translation quality in some cases. |
Be Consistent! Improving Procedural Text Comprehension using Label Consistency (N19-1)
Copied to clipboard
| Challenge: | Existing systems for procedural text comprehension still struggle with this task . evaluative work shows that consistent predictions from multiple entities can improve performance . |
| Approach: | They propose a framework that leverages label consistency during training to improve prediction performance. |
| Outcome: | The proposed framework significantly improves prediction performance over previous state-of-the-art systems on a standard benchmark dataset for procedural text, ProPara. |
Multi-layer Representation Fusion for Neural Machine Translation (C18-1)
Copied to clipboard
| Challenge: | Neural machine translation systems require a number of stacked layers for deep models, but the prediction depends on the sentence representation of the top-most layer with no access to low-level representations. |
| Approach: | They propose a multi-layer representation fusion approach to fusing stacked layers to learn a better representation from the stack. |
| Outcome: | The proposed approach yields 0.92 and 0.56 BLEU points over the strong Transformer baseline on IWSLT German-English and NIST Chinese-English MT tasks respectively. |
Zero-Shot Cross-Lingual Opinion Target Extraction (N19-1)
Copied to clipboard
| Challenge: | Aspect-based sentiment analysis involves the recognition of opinion target expressions . supervised learning algorithms are usually employed to extract OTEs from text . |
| Approach: | They propose a zero-shot cross-lingual approach for the extraction of opinion target expressions . they leverage multilingual word embeddings that share a common vector space across languages . |
| Outcome: | The proposed approach can perform accurate prediction on a target language without using annotated samples. |
Incorporating Attribution Importance for Improving Faithfulness Metrics (2023.acl-long)
Copied to clipboard
| Challenge: | Feature attribution methods (FAs) are popular for providing insights into the model reasoning process of making predictions. |
| Approach: | They propose a simple yet effective criterion that randomly masks tokens proportionately to their FA importance. |
| Outcome: | The proposed method is more faithful than hard sufficiency and comprehensiveness metrics. |
Transformer Language Models Handle Word Frequency in Prediction Head (2023.findings-acl)
Copied to clipboard
| Challenge: | Prediction head is a crucial component of Transformer language models. Despite its direct impact on prediction, its characteristics have been overlooked in previous analyses. |
| Approach: | They examine the inner workings of the prediction head, specifically the bias parameters, and quantify the effect of controlling their frequency biases on text generation. |
| Outcome: | The prediction head is a crucial component of the Transformer language models. |
Value-Agnostic Conversational Semantic Parsing (2021.acl-long)
Copied to clipboard
Emmanouil Antonios Platanios, Adam Pauls, Subhro Roy, Yuchen Zhang, Alexander Kyte, Alan Guo, Sam Thomson, Jayant Krishnamurthy, Jason Wolfe, Jacob Andreas, Dan Klein
| Challenge: | Existing models rely on rich representations of dialogue history that include all previously generated components of the output. |
| Approach: | They propose a model that abstracts over values to focus prediction on type- and function-level context. |
| Outcome: | The proposed model outperforms baseline models by 7.3% and 10.6% on SMCalFlow and TreeDST datasets. |
RANCC: Rationalizing Neural Networks via Concept Clustering (2020.coling-main)
Copied to clipboard
| Challenge: | Existing models that construct explanations concurrently with classification predictions are opaque. |
| Approach: | They propose a self-explainable model for Natural Language Processing (NLP) text classification tasks . they extract a rationale from the text and use it to predict a concept of interest . |
| Outcome: | The proposed model can be compressed without complicated compression techniques. |
ECPE-2D: Emotion-Cause Pair Extraction based on Joint Two-Dimensional Representation, Interaction and Prediction (2020.acl-main)
Copied to clipboard
| Challenge: | a new task, called emotion-cause pair extraction, has emerged in text emotion analysis . a 2D representation scheme is proposed to represent the emotion-case pairs . |
| Approach: | They propose a 2D approach to represent emotion-cause pairs by a 3D representation scheme. |
| Outcome: | The proposed approach improves the state-of-the-art on the emotion cause corpus . the proposed approach is based on a two-step framework with flaws . |
Noise Correction on Subjective Datasets (2024.acl-long)
Copied to clipboard
| Challenge: | Annotator fatigue and changing opinions over time can distort dataset annotations. |
| Approach: | They propose to use multitask learning to learn a more accurate representation of diverse opinions by using loss-based label correction. |
| Outcome: | The proposed method can cleanly separate agreeing and disagreeing annotations and provides a controllable way to encourage or discourage disagreement. |
Predicting Numerals in Text Using Nearest Neighbor Language Models (2023.findings-acl)
Copied to clipboard
| Challenge: | naive language models treat numerals as string tokens, resulting in difficulty in acquiring commonsense . kNN-LM is an extension of pre-trained neural LMs with the k-nearest neighbor (kNN) search . |
| Approach: | They apply k-nearest neighbor LM to a masked numeral prediction task . they found it is effective for fine-grained predictions of numerals from context . |
| Outcome: | The retrieval-based method is effective for fine-grained numeral prediction from context . it improves accuracy for the OOV numerals, the study shows . |
Benchmarking Answer Verification Methods for Question Answering-Based Summarization Evaluation Metrics (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing QA-based summarization metrics must automatically determine whether the QA model’s prediction is correct or not. |
| Approach: | They benchmark lexical answer verification methods used by current QA-based metrics and two more sophisticated text comparison methods, BERTScore and LERC. |
| Outcome: | The proposed methods outperform the other methods in some settings while remaining statistically indistinguishable from lexical overlap in others. |
Recurrent Interaction Network for Jointly Extracting Entities and Classifying Relations (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to solve the extraction problem learn interactions between the two tasks through a shared network . |
| Approach: | They propose to use multi-task learning to address the joint extraction of entity and relation . they exploit correlation between ER and relation classification tasks to improve performance . |
| Outcome: | Empirical results show that the proposed model improves on two real-world datasets. |
Interpretable Research Replication Prediction via Variational Contextual Consistency Sentence Masking (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for predicting research replication are insufficient especially for long research papers. |
| Approach: | They propose to build an interpretable neural model which can provide sentence-level explanations and apply weakly supervised approach to leverage large corpus of unlabeled datasets. |
| Outcome: | The proposed model can provide sentence-level explanations and leverage large unlabeled datasets to boost interpretability and improve prediction performance. |
Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluation (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent studies show that NLP models are vulnerable to adversarial perturbations such as synonym substitutions or syntax-guided paraphrasing. |
| Approach: | They propose a “double perturbation” framework to uncover model weaknesses beyond the test dataset. |
| Outcome: | The proposed attack achieves high success rates on both original and robustly trained CNNs and Transformers. |
Speech-to-Speech Translation for a Real-world Unwritten Language (2023.findings-acl)
Copied to clipboard
Peng-Jen Chen, Kevin Tran, Yilin Yang, Jingfei Du, Justine Kao, Yu-An Chung, Paden Tomasello, Paul-Ambroise Duquenne, Holger Schwenk, Hongyu Gong, Hirofumi Inaguma, Sravya Popuri, Changhan Wang, Juan Pino, Wei-Ning Hsu, Ann Lee
| Challenge: | a new study examines speech-to-speech translation (S2ST) that translates speech from one language into another . the research area for unwritten languages remains a research area with little exploration due to the lack of training data. |
| Approach: | They propose a system that translates speech from one language into another . they use Taiwanese Hokkien as an example of an unwritten language . |
| Outcome: | The proposed system can be used to train models in languages without standard writing systems. |
Zoom Out and Observe: News Environment Perception for Fake News Detection (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for fake news detection "zoom in" to verify content with knowledge sources or check readers’ replies to posts but neglect information in the external news environment where a fake news post is created and disseminated. |
| Approach: | They propose a framework to capture news environment signals and a module to perceive useful signals and assist final prediction. |
| Outcome: | The proposed framework can improve the performance of basic fake news detectors by capturing the environmental signals of news posts and analyzing the results. |
SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutions (2020.acl-main)
Copied to clipboard
| Challenge: | State-of-the-art NLP models can be fooled by human-unaware transformations such as synonymous word substitution. |
| Approach: | They propose a method that constructs a stochastic ensemble by applying random word substitutions on the input sentences and leverages the statistical properties to provably certify the robustness. |
| Outcome: | The proposed method outperforms state-of-the-art methods on IMDB and Amazon text classification tasks with practically meaningful certified accuracy. |
Adapting RNN Sequence Prediction Model to Multi-label Set Prediction (N19-1)
Copied to clipboard
| Challenge: | Existing approaches to multi-label classification are based on pre-specifying the label order, or relating the sequence probability to the set probability in ad hoc ways. |
| Approach: | They propose a new training objective that maximizes this set probability and a prediction objective that finds the most probable set on a test document. |
| Outcome: | The proposed model outperforms existing methods on a set of labels for multi-label classification . the proposed model is based on 'set probability' and 'prediction objective' |
On Length Divergence Bias in Textual Matching Models (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing deep models have been successful in textual matching tasks, but it is unclear whether they understand language or measure semantic similarity of texts. |
| Approach: | They propose an adversarial evaluation scheme which invalidates the length divergence bias in TM datasets. |
| Outcome: | The proposed method improves the robustness and generalization ability of models at the same time. |
Long-Tail Crisis in Nearest Neighbor Language Models (2025.findings-naacl)
Copied to clipboard
| Challenge: | Prior studies have shown that kNN-LM can retrieve long-tail contexts, leaving the model’s performance underexplored in estimating the probabilities of long-tailed target tokens. |
| Approach: | They investigate the behavior of kNN-LM on low-frequency tokens, examining prediction probability, retrieval accuracy, and token distribution in the datastore. |
| Outcome: | The proposed model improves the perplexity of given text by directly accessing a large datastore built from any text data during inference. |
Soft Knowledge Prompt: Help External Knowledge Become a Better Teacher to Instruct LLM in Knowledge-based VQA (2024.acl-long)
Copied to clipboard
| Challenge: | Recent research focuses on improving prediction performance and reliability of LLM. |
| Approach: | They propose a method to actively extract valuable information from the knowledge to produce a latent vector as a soft prompt, which is fused with the image embedding to form a knowledge-enhanced context to instruct LLM. |
| Outcome: | The proposed method improves performance on knowledge-based VQA benchmarks. |
Prediction Improves Simultaneous Neural Machine Translation (D18-1)
Copied to clipboard
| Challenge: | Current systems for simultaneous machine translation use an AGENT to control an incremental encoder-decoder model. |
| Approach: | They propose a general-purpose prediction action which predicts future words in the input stream. |
| Outcome: | The proposed agent with prediction has better translation quality and less delay compared to an agent-based system without prediction. |
An Interpretable Neuro-Symbolic Reasoning Framework for Task-Oriented Dialogue Generation (2022.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to interpret task-oriented dialogue systems employ an implicit reasoning strategy that makes the model predictions uninterpretable to humans. |
| Approach: | They propose a neuro-symbolic approach that performs explicit reasoning that justifies model decisions by reasoning chains. |
| Outcome: | The proposed approach achieves better results and introduces an interpretable decision process. |
A Diachronic Perspective on User Trust in AI under Uncertainty (2023.emnlp-main)
Copied to clipboard
| Challenge: | Modern NLP systems are rarely calibrated and are often confidently incorrect about their predictions, which violates users’ mental model and erodes their trust. |
| Approach: | They propose to use a mental model to bet on the correctness of an NLP system and to study how trust is rebuilt as a function of time after these events. |
| Outcome: | The proposed model shows that even a few highly inaccurate confidence estimation instances damage users’ trust in the system and performance, which does not easily recover over time. |
Investigating Dynamic Routing in Tree-Structured LSTM for Sentiment Analysis (D19-1)
Copied to clipboard
| Challenge: | Existing deep neural network models such as LSTM and tree-LSTM have a bias problem where the words in the tail of a sentence are more heavily emphasized than those in the header. |
| Approach: | They propose a capsule tree-LSTM model that uses dynamic routing to build sentence representations by assigning different weights to nodes according to their contributions to prediction. |
| Outcome: | The proposed model improves on the Stanford Sentiment Treebank and EmoBank datasets. |
Multi-Aspect Transfer Learning for Detecting Low Resource Mental Disorders on Social Media (2022.lrec-1)
Copied to clipboard
| Challenge: | Mental disorders are an important and pervasive public health issue. |
| Approach: | They propose to use linguistic features to improve mental disorder detection . they propose to apply multi-aspect transfer learning to detecting disorders from social media . |
| Outcome: | The proposed methods can be used to improve mental disorder detection in the context of data scarcity and understanding the overlapping symptoms between disorders. |
Inserting Information Bottlenecks for Attribution in Transformers (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Pretrained transformers are a popular approach for understanding features important for prediction. |
| Approach: | They apply information bottlenecks to analyze attribution of features for prediction on a black-box model. |
| Outcome: | The proposed method outperforms two competing methods in degradation tests on four datasets. |
Let Modalities Teach Each Other: Modal-Collaborative Knowledge Extraction and Fusion for Multimodal Knowledge Graph Completion (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent studies have focused on missing triples in knowledge graphs, but lack correlation between modalities. |
| Approach: | They propose a framework to foster mutual guidance and collaboration in unimodal knowledge extraction and multimodal knowledge fusion. |
| Outcome: | Extensive experiments on three real-world datasets demonstrate advantages of Moodle over state-of-the-art methods. |
To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion (2023.acl-long)
Copied to clipboard
Rui Li, Xu Chen, Chaozhuo Li, Yanming Shen, Jianan Zhao, Yujing Wang, Weihao Han, Hao Sun, Weiwei Deng, Qi Zhang, Xing Xie
| Challenge: | Existing methods for embedding knowledge graphs implicitly memorize relation rules to infer missing links, but they are difficult to memorize due to the inherent deficiencies of such implicit memorization strategy. |
| Approach: | They propose a vertical learning paradigm that allows to explicitly copy target information from related factual triples for more accurate prediction. |
| Outcome: | The proposed model improves generalization ability and makes distant link prediction significantly easier. |
SciPrompt: Knowledge-augmented Prompting for Fine-grained Categorization of Scientific Topics (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have used prompt-based fine-tuning methods for text classification tasks . however, the difficulty and costs of manually selecting domain label terms for the verbalizer remain unexplored . |
| Approach: | They propose a framework to automatically retrieve scientific topic-related terms for low-resource text classification tasks. |
| Outcome: | The proposed method outperforms state-of-the-art methods on scientific text classification tasks under few and zero-shot settings. |
Knowledge Graph Pooling and Unpooling for Concept Abstraction (2025.coling-main)
Copied to clipboard
| Challenge: | Knowledge graph embedding (KGE) aims to embed entities and relations as vectors in a continuous space. |
| Approach: | They propose a framework with KG Pooling and unpooling and Contrastive Learning to abstract and encode latent concepts for better KG prediction. |
| Outcome: | The proposed framework outperforms baselines on link prediction task. |
Yeah, Un, Oh: Continuous and Real-time Backchannel Prediction with Fine-tuning of Voice Activity Projection (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for backchannel prediction relied on turn-based or artificially balanced datasets. |
| Approach: | They propose a method for real-time, continuous backchannel prediction using a fine-tuned Voice Activity Projection model. |
| Outcome: | The proposed method outperforms baseline methods in timing and type prediction tasks in real-world environments. |
Helping the Weak Makes You Strong: Simple Multi-Task Learning Improves Non-Autoregressive Translators (2022.emnlp-main)
Copied to clipboard
| Challenge: | Non-autoregressive (NAR) neural machine translation models require a conditional independence assumption on target sequences, resulting in less informative learning signals. |
| Approach: | They propose a model-agnostic multi-task learning framework to provide more informative learning signals for NAR models under conventional MLE training. |
| Outcome: | The proposed framework improves accuracy of multiple NAR baselines without additional decoding overhead. |
Counterfactual Debiasing for Fact Verification (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for debiasing factchecking models learn such biases instead of understanding the semantic relationship between the claim and evidence. |
| Approach: | They propose a counterfactual framework CLEVER which is augmentation-free and mitigates biases on the inference stage. |
| Outcome: | The proposed method is augmentation-free and mitigates biases on the inference stage. |
Towards Transparent and Explainable Attention Models (2020.acl-main)
Copied to clipboard
Akash Kumar Mohankumar, Preksha Nema, Sharan Narasimhan, Mitesh M. Khapra, Balaji Vasan Srinivasan, Balaraman Ravindran
| Challenge: | Recent studies on interpretability of attention distributions have led to notions of faithful and plausible explanations for a model’s predictions. |
| Approach: | They propose to modify LSTM cells to ensure that the hidden representations learned at different time steps are diverse. |
| Outcome: | The proposed model can provide a faithful explanation if a higher attention weight implies a greater impact on the model’s prediction. |
Hierarchical CVAE for Fine-Grained Hate Speech Classification (D18-1)
Copied to clipboard
| Challenge: | Existing work on automated hate speech detection focuses on binary classification or on differentiating among a small set of categories. |
| Approach: | They propose a method to discriminate among 40 hate groups of 13 different hate group categories. |
| Outcome: | The proposed method outperforms discriminative models on a fine-grained hate speech classification task. |
UniEvent: Unified Generative Model with Multi-Dimensional Prefix for Zero-Shot Event-Relational Reasoning (2023.acl-long)
Copied to clipboard
| Challenge: | Reasoning about events and their relations is an indispensable ability to fulfill various event-centric or common-sense reasoning tasks. |
| Approach: | They propose a multi-task learning framework that organizes event relational reasoning tasks into a coordinate system with multiple axes, representing inter-event relations and reasoning formulations. |
| Outcome: | The proposed framework achieves state-of-the-art or competitive performance on zero-shot and supervised reasoning tasks. |
Dynamic Transformers Provide a False Sense of Efficiency (2023.acl-long)
Copied to clipboard
| Challenge: | Pre-trained language models typically lead to high computational cost during inference. |
| Approach: | They propose a slowdown attack framework that can reduce inference efficiency by 80% by leveraging existing adversarial attacks targeting model accuracy. |
| Outcome: | The proposed framework can reduce the efficiency of multi-exit models by 80% on average, validating its effectiveness and generalization ability. |
Self-Adjust Softmax (2025.emnlp-main)
Copied to clipboard
Chuanyang Zheng, Yihang Gao, Guoxuan Chen, Han Shi, Jing Xiong, Xiaozhe Ren, Chao Huang, Zhenguo Li, Yu Li
| Challenge: | Usually, tokens with larger attention scores are important for the final prediction. |
| Approach: | They propose to modify softmax(z) to z softmax and its normalized variant to improve the Transformer attention mechanism by making minor adjustments to the softmax function. |
| Outcome: | The proposed model provides enhanced gradient properties compared to the vanilla softmax function. |
Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control (D19-1)
Copied to clipboard
| Challenge: | Selective rationalization is a common mechanism to ensure that predictive models reveal how they use any available features. |
| Approach: | They propose a co-operative method which uses introspection to explicitly predict and incorporate the outcome into the selection process. |
| Outcome: | The proposed model maintains high predictive accuracy and leads to comprehensive rationales. |
Generate-and-Retrieve: Use Your Predictions to Improve Retrieval for Semantic Parsing (2022.coling-1)
Copied to clipboard
Yury Zemlyanskiy, Michiel de Jong, Joshua Ainslie, Panupong Pasupat, Peter Shaw, Linlu Qiu, Sumit Sanghai, Fei Sha
| Challenge: | Existing retrieval techniques for semantic parsing use similarity of query and exemplar inputs . Existing work suggests that appending training samples to training samples improves performance . |
| Approach: | They propose a retrieval procedure that retrieves exemplars for which outputs are similar . existing retrieval techniques are based on similarity of query and exemplar inputs . |
| Outcome: | Existing retrieval techniques rely on similarity of query and exemplar inputs . they retrieve exemplars with similar outputs and generate a final prediction . |
Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification (D19-1)
Copied to clipboard
| Challenge: | Existing models for multi-label classification ignore complexity and dependencies among labels . Experimental results show that our method can obtain more accurate multi-lab classification results. |
| Approach: | They propose a meta-learning method to capture complex label dependencies . they use a Meta-learner to jointly learn the training policies and prediction policies for different labels. |
| Outcome: | The proposed method can capture complex label dependencies on fine-grained entity typing and text classification tasks. |
Validity Assessment of Legal Will Statements as Natural Language Inference (2022.findings-emnlp)
Copied to clipboard
| Challenge: | This study introduces a dataset that focuses on the validity of statements in legal wills. |
| Approach: | They propose a dataset that focuses on the validity of statements in legal wills. |
| Outcome: | The proposed model achieves 80% macro F1 and accuracy, but group accuracy is in mid 80s at best, suggesting that the models’ understanding of the task remains superficial. |
Prediction and Calibration: Complex Reasoning over Knowledge Graph with Bi-directional Directed Acyclic Graph Neural Network (2023.findings-acl)
Copied to clipboard
| Challenge: | Knowledge graphs (KGs) organize world knowledge as interlinked triples which describe entities and their relationships. |
| Approach: | They propose a bi-directional Directed Acyclic Graph neural network that splits the reasoning process into prediction and calibration. |
| Outcome: | The proposed model outperforms previous QE models on FB15k, FB16k-237, and NELL995 on prediction and calibration. |
Modeling Historical Relevant and Local Frequency Context for Representation-Based Temporal Knowledge Graph Forecasting (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing representation-based approaches neglect candidate-specific temporal context, resulting in serious information loss or homogeneous prediction. |
| Approach: | They propose a temporal representation learning model that incorporates temporal contexts of candidates and models temporal contextual information from historiCal Relevant context and locAl Frequency contexT. |
| Outcome: | The proposed model can leverage temporal contextual information to achieve differential predictions on six benchmark datasets. |
Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals (2024.acl-long)
Copied to clipboard
| Challenge: | Existing interpretability research focused on analyzing a single mechanism . et al., 2023) focused on finding how models copy or recall factual knowledge . |
| Approach: | They propose a competition of mechanisms that focuses on the interplay of multiple mechanisms instead of individual mechanisms . they uncover how and where the competition of mechanism happens within LLMs using logit inspection and attention modification methods. |
| Outcome: | The proposed model is based on two interpretability methods, logit inspection and attention modification. |
Speed Reading: Learning to Read ForBackward via Shuttle (D18-1)
Copied to clipboard
| Challenge: | LSTM-Shuttle uses human speed reading techniques to perform natural language processing tasks. |
| Approach: | They propose a model which uses human speed reading techniques to perform natural language processing tasks for accurate and efficient comprehension. |
| Outcome: | The proposed model predicts on IMDB, Rotten Tomatoes, AG, and Children’s Book Test datasets and goes backwards. |
You Shall Know a User by the Company It Keeps: Dynamic Representations for Social Media Users in NLP (D19-1)
Copied to clipboard
| Challenge: | Current approaches to social media modelling ignore the fact that an individual may be part of several communities which are not equally relevant in all communicative situations. |
| Approach: | They propose a model that captures the sociological phenomenon of homophily and combines it with linguistic information to make a prediction. |
| Outcome: | The proposed model significantly outperforms existing models on three different tasks and is compared with other models. |
Token-Aware Editing of Internal Activations for Large Language Model Alignment (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to optimize the behavior of large language models neglect misalignment discrepancies among tokens, resulting in deviant alignment direction and inflexible editing strength. |
| Approach: | They propose a token-aware editing approach to exploit the misalignment discrepancy among tokens to enhance activation probing and facilitate intervention. |
| Outcome: | Extensive experiments on three alignment capabilities demonstrate the efficacy of the proposed approach surpassing baseline by 25.8% on the primary metric of truthfulness with minimal cost. |
Incorporating LIWC in Neural Networks to Improve Human Trait and Behavior Analysis in Low Resource Scenarios (2022.lrec-1)
Copied to clipboard
| Challenge: | Psycholinguistic knowledge resources have been widely used in constructing features for text-based human trait and behavior analysis. |
| Approach: | They propose to incorporate a widely-used psycholinguistic lexicon into NN models to improve human trait and behavior analysis in low resource scenarios. |
| Outcome: | The proposed methods perform significantly better than baselines that use only LIWC or NN-based feature learning methods. |
Multi-Layer Pseudo-Siamese Biaffine Model for Dependency Parsing (2022.coling-1)
Copied to clipboard
| Challenge: | Existing work only uses biaffine method at the end of the dependency parser as a scorer, and its application in multi-layer form is ignored. |
| Approach: | They propose a multi-layer pseudo-Siamese biaffine model for neural dependency parsing that uses biaffin method as a scorer and a biaffin module to construct arc weight matrix. |
| Outcome: | The proposed model achieves state-of-the-art on PTB, CTB, and UD datasets with low efficiency loss. |
MetaTKG: Learning Evolutionary Meta-Knowledge for Temporal Knowledge Graph Reasoning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing models rely on historical information to learn embeddings for entities, but ignore the evolution of facts. |
| Approach: | They propose a Temporal Meta-learning framework to learn evolutionary meta-knowledge from TKGs. |
| Outcome: | The proposed method improves on four widely-used datasets and three backbones on a wide range of scenarios on tKGs. |
A Neural Citation Count Prediction Model based on Peer Review Text (D19-1)
Copied to clipboard
| Challenge: | Recent studies have focused on extracting or mining useful features from the paper itself or the associated authors. |
| Approach: | They propose to utilize peer review data for the CCP task with a neural prediction model to learn a comprehensive semantic representation for peer review text. |
| Outcome: | The proposed model improves on the peer review data and hand-crafted features. |
Similarizing the Influence of Words with Contrastive Learning to Defend Word-level Adversarial Text Attack (2023.findings-acl)
Copied to clipboard
| Challenge: | Neural language models are vulnerable to word-level adversarial text attacks . previous word-based search methods assume important words influence prediction . |
| Approach: | They propose a method for similarizing the influence of words with contrast learning that encourages model to learn sentence representations in which words of varying importance have a more uniform influence on prediction. |
| Outcome: | The proposed method is compatible with various training methods and improves model robustness against various adversarial attacks. |
Coherent Entity Disambiguation via Modeling Topic and Categorical Dependency (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing entity disambiguation methods struggle to capture explicit discourse-level dependencies, resulting in incoherent predictions at the abstract level. |
| Approach: | They propose an unsupervised variational autoencoder to extract latent topic vectors of context sentences to enhance coherence of entity predictions. |
| Outcome: | The proposed system achieves state-of-the-art on popular ED benchmarks with an average improvement of 1.3 F1 points. |
CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing fine-tuning paradigms focus on aligning LLMs with task-specific objectives. |
| Approach: | They propose a pipeline that leverages human priors to automatically generate token-level causal signals and introduce the Re-Attention mechanism to guide training. |
| Outcome: | The proposed pipeline achieves an average improvement of 5.76% on the STG dataset and 1.56% on downstream tasks. |
Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps (2025.emnlp-main)
Copied to clipboard
| Challenge: | Language models (LMs) produce a chain of thought (CoT) when prompted to think step-by-step, but it is unclear whether the reasoning encoded in the CoT is faithful to the models’ parametric beliefs. |
| Approach: | They propose a framework for measuring parametric faithfulness of generated reasoning by unlearning reasoning steps (FUR) they propose to erase information contained in reasoning steps from model parameters and measure faithfulness as the resulting effect on the model’s prediction. |
| Outcome: | The proposed framework erases information contained in reasoning steps from model parameters and measures faithfulness as the resulting effect on the model’s prediction. |
Efficient Integration of External Knowledge to LLM-based World Models via Retrieval-Augmented Generation and Reinforcement Learning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing attempts to enhance LLM-based world models through prompting or fine-tuning approaches are either requiring human knowledge or computationally extensive. |
| Approach: | They propose a framework that leverages retrieval-augmented generation to integrate external knowledge to LLM-based world models. |
| Outcome: | The proposed framework outperforms baseline models and exhibits strong generalizability. |
APEACH: Attacking Pejorative Expressions with Analysis on Crowd-Generated Hate Speech Evaluation Datasets (2022.findings-emnlp)
Copied to clipboard
| Challenge: | flaming or trolling in online communities is considered hostile behavior . a dataset of hate speech examples can be useful for detecting toxic or pejorative expressions . annotating on existing web text has several limitations that deter the dataset's reliability . |
| Approach: | They propose a dataset that asks users to generate hate speech examples followed by minimal post-labeling. |
| Outcome: | a new approach can collect useful datasets that are less sensitive to overlaps, the authors say . annotating on web text has several limitations that deter the dataset's reliability . |
Ideology Prediction from Scarce and Biased Supervision: Learn to Disregard the “What” and Focus on the “How”! (2023.acl-long)
Copied to clipboard
| Challenge: | a novel supervised learning approach for political ideology prediction is needed for many applications. |
| Approach: | They propose a supervised learning approach for political ideology prediction that decomposes document embeddings into a linear superposition of two vectors. |
| Outcome: | The proposed model outperforms state-of-the-art models on two benchmark datasets with biased data with 5% accuracy. |
Label-Agnostic Sequence Labeling by Copying Nearest Neighbors (P19-1)
Copied to clipboard
| Challenge: | Retrieve-and-edit based structured prediction models condition on retrieved neighbors to generate new structures, but many models do not explicitly capture the discrete operations that allow for the neighbors to be edited into the target structure. |
| Approach: | They propose to explicitly condition on retrieved neighbors to create new structures . they propose to use a dynamic programming approach to sequence labeling . |
| Outcome: | The proposed model can perform accurate sequence labeling by explicitly copying labels from retrieved neighbors. |
Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis (2022.findings-emnlp)
Copied to clipboard
Yuxin Xiao, Paul Pu Liang, Umang Bhatt, Willie Neiswanger, Ruslan Salakhutdinov, Louis-Philippe Morency
| Challenge: | Pre-trained language models (PLMs) have gained increasing popularity due to compelling prediction performance in diverse natural language processing tasks. |
| Approach: | They compare three popular options for encoding and Temp Scaling for PLMs . they recommend using Temp Loss as uncertainty quantifier and Focal Loss for fine-tuning . |
| Outcome: | Using pre-trained language models, we compare three options on NLP classification tasks and domain shift. |
Visual News: Benchmark and Challenges in News Image Captioning (2021.emnlp-main)
Copied to clipboard
| Challenge: | Visual News Captioner is an entity-aware model for news image captioning . Unlike standard image captions, news images depict situations where people, locations, and events are of paramount importance. |
| Approach: | They propose a visual news captioner model that integrates visual and textual features to generate captions with richer information such as events and entities. |
| Outcome: | The proposed model can generate captions with richer information such as events and entities. |
Natural Evolution-based Dual-Level Aggregation for Temporal Knowledge Graph Reasoning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models ignore asynchronous characteristics of event evolution, resulting in suboptimal performance. |
| Approach: | They propose a Natural Evolution-based Dual-level Aggregation framework for TKG reasoning that incorporates asynchronous characteristics of event evolution into the model. |
| Outcome: | The proposed model incorporates the asynchronous characteristics of event evolution for representation computation, thus improving prediction performance. |
Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Increasing the ability of large language models to perform latent multihop reasoning is crucial for reducing the cost and deployment challenges. |
| Approach: | They propose an interpretability method that traces how logits propagate across layers and positions toward the final prediction. |
| Outcome: | The proposed method improves accuracy on five reasoning datasets. |
Model-tuning Via Prompts Makes NLP Models Adversarially Robust (2023.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained models are typically adapted to downstream tasks by appending a randomly initialized multilayer perceptron to their topmost representation layer and fine-tuning the entire model on a downstream task. |
| Approach: | They propose to append a multilayer perceptron to a CLS token and fine-tune the entire model on a downstream task. |
| Outcome: | The proposed model-tuning via prompts outperforms adversarial training-based state-of-art defenses by 3.5% and improves against adversarials by 8% over standard methods. |
Domain Classification-based Source-specific Term Penalization for Domain Adaptation in Hate-speech Detection (2022.coling-1)
Copied to clipboard
| Challenge: | Existing approaches for hate-speech detection exhibit poor performance in out-of-domain settings due to overemphasizing source-specific information that negatively impacts its domain invariance. |
| Approach: | They propose a domain adaptation approach that automatically extracts and penalizes source-specific terms using a classifier. |
| Outcome: | The proposed approach improves cross-domain evaluation on indomain held-out instances while preserving high performance on out-of-domain settings. |
Pyramid-BERT: Reducing Complexity via Successive Core-set based Token Selection (2022.acl-long)
Copied to clipboard
| Challenge: | Existing models that use heuristics to shorten sequence lengths are computationally prohibitive. |
| Approach: | They propose a new method to shorten sequence lengths by transforming tokens through encoders and a core-set based token selection method that avoids expensive pre-training and fine tuning. |
| Outcome: | The proposed model outperforms existing models on GLUE benchmarks and Long Range Arena datasets and demonstrates that it is cost-effective and space-efficient. |
Exploring and Mitigating Shortcut Learning for Generative Large Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent large language models (LLMs) have incredible instruction-following capabilities while maintaining strong task completion ability. |
| Approach: | They propose a framework to encourage LLMs to Forget Spurious correlations and Learn from In-context information. |
| Outcome: | The proposed framework can mitigate shortcut learning by forging spurious correlations and learning from in-context information. |
Attention Word Embedding (2020.coling-main)
Copied to clipboard
| Challenge: | Word embedding models learn semantically rich vector representations of words . popular word embedders include word2vec, GloVe, and fastText . |
| Approach: | They propose an AWE-S model which integrates the attention mechanism into the CBOW model and incorporates subword information. |
| Outcome: | The proposed model outperforms the state-of-the-art model on word similarity datasets and when used for initialization of NLP models. |
Batch-ICL: Effective, Efficient, and Order-Agnostic In-Context Learning (2024.findings-acl)
Copied to clipboard
| Challenge: | In-context learning (ICL) is a meta-optimization process that affects performance . we develop a batch-based inference algorithm that is order-agnostic to ICL examples . |
| Approach: | They develop an order-agnostic inference algorithm that aggregates ICL examples in batches . they find it outperforms most permutations of ICL, and it even exceeds the best order . |
| Outcome: | The proposed method outperforms standard ICL examples while reducing computational resources. |
Mental Disorder Classification via Temporal Representation of Text (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Current methods for mental disorder prediction split data into chunks and use limited context length . mental health professionals lack the skills to diagnose and treat mental disorders . |
| Approach: | They propose a framework which compresses chronologically ordered social media posts into a series of numbers and uses this time variant representation for mental disorder classification. |
| Outcome: | The proposed framework outperforms existing models in depression, self-harm and anorexia . it also shows that the proposed framework can be used across domains . |
Bayesian Topic Regression for Causal Inference (2021.emnlp-main)
Copied to clipboard
| Challenge: | a Bayesian topic regression model uses text and numerical information to model outcome variables. |
| Approach: | They propose a Bayesian Topic Regression model that uses both text and numerical information to model an outcome variable. |
| Outcome: | The proposed model recovers ground truth with lower bias than any benchmark model when text and numerical features are correlated. |
What’s in Your Head? Emergent Behaviour in Multi-Task Transformer Models (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing paradigms for multi-task training involve a shared pre-trained language model and a small, thin network (head) given an input, a target head is the head that is selected for outputting the final prediction. |
| Approach: | They examine the behaviour of non-target heads when given input that belongs to a different task than the one they were trained for. |
| Outcome: | The non-target heads exhibit emergent behaviour, which may explain the target task, or generalize beyond their original task. |
Are All Spurious Features in Natural Language Alike? An Analysis through a Causal Lens (2022.emnlp-main)
Copied to clipboard
| Challenge: | 'spurious correlations' have been used in NLP to informally denote any undesirable feature-label correlations. |
| Approach: | They formalize this distinction using a causal model and probabilities of necessity and sufficiency, which delineates causal relations between a feature and a label. |
| Outcome: | The proposed model is invariant to the feature, but not sufficient for prediction. |
Generalizing Backpropagation for Gradient-Based Interpretability (2023.acl-long)
Copied to clipboard
| Challenge: | Several feature-attribution methods for interpreting deep neural networks rely on computing the gradients of a model’s output with respect to its inputs, but they reveal little about the inner workings of the model itself. |
| Approach: | They propose a generalized backpropagation algorithm that generalizes the gradient computation of a model to efficiently compute other interpretable statistics about the gradient graph of neural networks. |
| Outcome: | The proposed generalized algorithm can be used to compute other interpretable statistics about the gradient graph of a neural network, such as the highest-weighted path and entropy. |
ForestCast: Open-Ended Event Forecasting with Semantic News Forest (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches and datasets overlook the complex relationships among events . current research lacks comprehensive evaluation methods to evaluate OEEF . |
| Approach: | They propose a prediction pipeline that extracts forecast-relevant events from news data . forestcast organizes news events into a story tree and predicts subsequent events along each path . |
| Outcome: | The proposed pipeline extracts forecast-relevant events from news data and predicts subsequent events along each path. |
Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown remarkable capabilities in various tasks, but may rely on dataset biases as shortcuts for prediction. |
| Approach: | They propose to use a test suite to evaluate the impact of shortcuts on LLMs' performance. |
| Outcome: | The proposed test suite incorporates six shortcut types, five evaluation metrics, and four prompting strategies. |
MalruleLib: Large-Scale Executable Misconception Reasoning with Step Traces for Modeling Student Thinking in Mathematics (2026.acl-long)
Copied to clipboard
| Challenge: | MalruleLib is a learning-science-grounded framework that translates documented misconceptions into executable procedures and generates step-by-step traces of malrule-consistent student reasoning. |
| Approach: | They propose a learning-science-grounded framework that translates documented misconceptions into executable procedures and generates step-by-step traces of malrule-consistent student reasoning. |
| Outcome: | The framework translates misconceptions into executable procedures and generates step-by-step traces of malrule-consistent student reasoning. |
Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing text-to-SQL models do not generalize when faced with domain knowledge that does not frequently appear in training data. |
| Approach: | They propose a human-curated dataset based on the Spider benchmark for text-to-SQL translation. |
| Outcome: | The proposed model performs better on unseen domains than existing models on public benchmarks. |
Unsupervised Selective Rationalization with Noise Injection (2023.acl-long)
Copied to clipboard
| Challenge: | Unsupervised selective rationalization produces rationales alongside predictions, but does not ensure that the rationale contains a plausible explanation for the prediction. |
| Approach: | They propose a technique that injects noise between a rationale generator and a predictor to limit generation of implausible rationales. |
| Outcome: | The proposed method achieves significant improvements in plausibility and task accuracy over the state-of-the-art models while maintaining or improving model faithfulness. |
Unsupervised Question Decomposition for Question Answering (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing QA systems struggle to answer complex questions because information is scattered in different places. |
| Approach: | They propose an unsupervised algorithm that decomposes hard questions into simpler sub-questions . they propose an algorithm that can be used to generate a final answer from millions of questions . |
| Outcome: | The proposed algorithm decomposes hard questions into simpler sub-questions that existing QA systems can answer. |
VECHR: A Dataset for Explainable and Robust Classification of Vulnerability Type in the European Court of Human Rights (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on the concept of vulnerability at the European Court of Human Rights (ECtHR) has focused on classification and analysis of textual data. |
| Approach: | They propose to use an expert-annotated multi-label dataset to assess vulnerability in court cases. |
| Outcome: | The proposed model performs poorly on out-of-domain data and shows that it is robust. |
Rationalizing Medical Relation Prediction from Corpus-level Statistics (2020.acl-main)
Copied to clipboard
| Challenge: | Existing work on predicting relations based on text corpus has focused on analyzing raw texts mentioning two entities. |
| Approach: | They propose a framework that can be used to rationalize medical relation prediction . they recall contexts associated with the target entities and recognize relational interactions between them . |
| Outcome: | The proposed framework can achieve competitive predictive performance against a comprehensive list of neural baseline models, and present rationales to justify its prediction. |
Precedent-Enhanced Legal Judgment Prediction with LLM and Domain-Model Collaboration (2023.emnlp-main)
Copied to clipboard
Yiquan Wu, Siying Zhou, Yifei Liu, Weiming Lu, Xiaozhong Liu, Yating Zhang, Changlong Sun, Fei Wu, Kun Kuang
| Challenge: | Recent advances in deep learning have enabled a variety of techniques to be used to solve the LJP task. |
| Approach: | They propose a framework that leverages the strength of both LLMs and domain-specific models in the context of precedents. |
| Outcome: | The proposed framework leverages the strength of both LLM and domain models in the context of precedents. |
KOLD: Korean Offensive Language Dataset (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent directions for offensive language detection focus on English and do not transfer well to other languages because of cultural and linguistic differences. |
| Approach: | They present a Korean offensive language dataset annotated with offensive language comments . they use the comments as training data for Korean BERT and RoBERTa models . |
| Outcome: | The proposed model improves offensiveness detection, target classification, and span detection while having room for improvement for target group classification and span prediction. |
Deep Equilibrium Non-Autoregressive Sequence Learning (2023.findings-acl)
Copied to clipboard
| Challenge: | et al., 2017) is the most prevailing neural architecture for sequence-to-sequence learning. |
| Approach: | They propose to solve for the equilibrium state of NAR models with black-box root-finding solvers and back-propagate through the equilibrium point via implicit differentiation with constant memory. |
| Outcome: | The proposed framework can converge to a more accurate prediction on four WMT benchmarks. |
Hierarchical Entity Typing via Multi-level Learning to Rank (2020.acl-main)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is a canonical information extraction task that assigns spans to one of a handful of types. |
| Approach: | They propose a hierarchical entity classification method that embraces ontological structure at training and during prediction. |
| Outcome: | The proposed method outperforms previous work on strict accuracy and significantly outperformed previous work. |
Text-Attributed Knowledge Graph Enrichment with Large Language Models for Medical Concept Representation (2026.acl-long)
Copied to clipboard
| Challenge: | eHRs encode a patient's medical history as a high-dimensional and sparse sequence of diagnosis, medication, and procedure concepts . robust concept representation learning is hindered by key challenges, authors say . clinically important cross-type dependencies are often missing or incomplete in existing ontology resources . |
| Approach: | They propose a graph learning framework that integrates semantics with medical concepts to improve prediction performance. |
| Outcome: | The proposed framework improves prediction performance and integrates semantics with graph structure. |
Selective “Selective Prediction”: Reducing Unnecessary Abstention in Vision-Language Reasoning (2024.findings-acl)
Copied to clipboard
Tejas Srinivasan, Jack Hessel, Tanmay Gupta, Bill Yuchen Lin, Yejin Choi, Jesse Thomason, Khyathi Chandu
| Challenge: | ReCoVERR reduces the over-abstention of a vision-language system with low tolerance for inaccurate predictions without increasing the error rate of the system’s predictions. |
| Approach: | They propose an inference-time algorithm to reduce the over-abstention of a selective vision-language system without increasing the error rate of the system’s predictions. |
| Outcome: | ReCoVERR reduces the over-abstention of a vision-language system without increasing the error rate of the system’s predictions. |
HuaSLIM: Human Attention Motivated Shortcut Learning Identification and Mitigation for Large Language models (2023.findings-acl)
Copied to clipboard
| Challenge: | Large language models tend to rely on shortcut features that spuriously correlate with labels for prediction, which weakens their generalization on out-of-distribution samples. |
| Approach: | They propose a human attention guided approach to identifying shortcut learning that encourages the LLM-based target model to learn relevant features by exploring both human and neural attention. |
| Outcome: | The proposed approach improves the robustness of large language models on out-of-distribution (OOD) samples while not affecting the performance on IID data. |
TEPrompt: Task Enlightenment Prompt Learning for Implicit Discourse Relation Recognition (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing prompt learning models for IDRR use multiple-prompt decisions from three different yet much similar connective prediction templates. |
| Approach: | They propose to fuse three related tasks to fuse the learned features of auxiliary tasks to create a prompt learning model that can be used to boost the main task. |
| Outcome: | The proposed model outperforms the ConnPrompt in the training phase and in the testing phase. |
Joint Geometrical and Statistical Domain Adaptation for Cross-domain Code Vulnerability Detection (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to detect code vulnerability are limited by labeled training data on target domains. |
| Approach: | They propose a cross-domain code vulnerability detection framework called MNCRI . they propose mutual nearest neighbor contrastive learning to align the source and target domains . |
| Outcome: | The proposed framework outperforms state-of-the-art methods in cross-domain code vulnerability detection tasks. |
A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies show that fine-tuned textual transformer models are vulnerable to adversarial text perturbations. |
| Approach: | They extract 13 different features representing a wide range of input fine-tuning corpora properties and use them to predict adversarial robustness of the fine- tuned models. |
| Outcome: | The proposed framework can be used as an additional tool for robustness evaluation since it saves 30x-193x runtime compared to the traditional technique and can be easily used under adversarial training. |
GNN-SL: Sequence Labeling Based on Nearest Examples via GNN (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing sequence labeling algorithms can be decomposed into two parts . |
| Approach: | They propose a graph neural networks sequence labeling (GNN-SL) that augments the vanilla SL model output with similar tagging examples retrieved from the whole training set. |
| Outcome: | The proposed model performs well on three sequence labeling tasks. |
IT2ACL Learning Easy-to-Hard Instructions via 2-Phase Automated Curriculum Learning for Large Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies have focused on the pre-training phase of large language models, but this study focuses on the learning phase of pre-trained LLMs. |
| Approach: | They propose a 2-phase automated curriculum learning guided instruction tuning framework that learns easy-to-hard instructions in a self-adjusting dynamic manner. |
| Outcome: | The proposed framework unlocks latent ability in pre-trained large language models and achieving superior performance across diverse tasks. |
Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers (2024.findings-emnlp)
Copied to clipboard
Yuxia Wang, Revanth Gangi Reddy, Zain Mujahid, Arnav Arora, Aleksandr Rubashevskii, Jiahui Geng, Osama Mohammed Afzal, Liangming Pan, Nadav Borenstein, Aditya Pillai, Isabelle Augenstein, Iryna Gurevych, Preslav Nakov
| Challenge: | Large language models generate naturally sounding answers over a broad range of human inquiries, but they often generate answers that contradict real-world facts. |
| Approach: | They propose a framework for annotating and evaluating the factuality of large language models . they propose 'factcheck-bench' which provides a multi-stage annotation scheme . |
| Outcome: | The proposed framework outperforms several popular LLM fact-checkers in claim, sentence, and document levels. |
Softmax Tree: An Accurate, Fast Classifier When the Number of Classes Is Large (2021.emnlp-main)
Copied to clipboard
| Challenge: | Classification problems with thousands or more classes occur in NLP, for example language models or document classification. |
| Approach: | a new algorithm uses a binary tree with sparse hyperplanes and small softmax classifiers at the leaves to predict the top class. |
| Outcome: | The proposed model is faster at inference because the input follows a single path to a leaf and the softmax classifier operates on a small subset of the classes. |
Jump to Conclusions: Short-Cutting Transformers with Linear Transformations (2024.lrec-main)
Copied to clipboard
| Challenge: | Transformer-based language models create hidden representations of inputs at every layer, but only use final-layer representations for prediction. |
| Approach: | They propose a method for casting hidden representations as final representations, bypassing transformer computation in-between. |
| Outcome: | The proposed method produces more accurate predictions from hidden layers across various model scales, architectures, and data distributions. |
Joint Pre-Encoding Representation and Structure Embedding for Efficient and Low-Resource Knowledge Graph Completion (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge graph completion models require longer training and inference times as well as increased memory usage. |
| Approach: | They propose to encode textual descriptions into semantic representations before training and integrate structural embedding with pre-encoded semantic description to improve model's prediction performance on 1-N relations. |
| Outcome: | The proposed model increases inference speed by 30x and reduces training memory by approximately 60% on the WN18RR and UMLS datasets. |
Residualized Similarity for Faithfully Explainable Authorship Verification (2025.findings-emnlp)
Copied to clipboard
Peter Zeng, Pegah Alipoormolabashi, Jihu Mun, Gourab Dey, Nikita Soni, Niranjan Balasubramanian, Owen Rambow, H. Schwartz
| Challenge: | Neural methods achieve high accuracy, but their representations lack direct interpretability. |
| Approach: | They propose a method that supplements systems using interpretable features with a neural network to improve their performance while maintaining interpretability. |
| Outcome: | The proposed method improves the performance of state-of-the-art models while maintaining interpretability. |
Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing research suggests that contextual representations of large language models exhibit subpar performance in downstream tasks, struggling to fully capture the semantic nuances of words. |
| Approach: | They investigate the bottom-up evolution of lexical semantics for a popular LLM . they probing its hidden states at the end of each layer using a contextualized word identification task . |
| Outcome: | The proposed model is able to encode lexical semantics in lower layers while achieving weaker induction in higher layers. |
LLMs for Generating and Evaluating Counterfactuals: A Comprehensive Study (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown remarkable performance in NLP tasks, but their efficacy in generating high-quality CFs remains uncertain. |
| Approach: | They compare LLMs' ability to generate CFs that flip the original label and human CF's. |
| Outcome: | The proposed models generate fluent CFs, but struggle to keep the induced changes minimal. |
Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Downstream scaling laws aim to predict task performance at larger scales from the model’s performance at smaller scales. |
| Approach: | They conduct a meta-analysis of existing data on downstream scaling laws and find that predictable scaling only occurs in a minority of cases: 39% of the time. |
| Outcome: | The proposed scaling laws only occur in a minority of cases, and seemingly benign changes to the experimental setting can completely change the scaling behavior. |
To Revise or Not to Revise: Learning to Detect Improvable Claims for Argumentative Writing Support (2023.acl-long)
Copied to clipboard
| Challenge: | assessing whether and how different claims in a text need to be revised is a hard task, especially for novice writers. |
| Approach: | They propose a sampling strategy based on revision distance to capture differences between versions of the same text. |
| Outcome: | The proposed sampling strategy can be done without additional annotations and judgments. |
Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization (2026.findings-acl)
Copied to clipboard
Yuxiang Ji, Yong Wang, Ziyu Ma, Yiming Hu, Hailang Huang, Xuecai Hu, Guanhua Chen, Liaoni Wu, Xiangxiang Chu
| Challenge: | Existing large vision-language model (LVLM) approaches overlook a common strategy used by humans — using maps. |
| Approach: | They propose a method to equip a vision-language model with the ability to think with maps and optimize it using agentic reinforcement learning and parallel test-time scaling. |
| Outcome: | The proposed method outperforms open- and closed-source models on most metrics. |
SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing black-box instruction backdoors can detect poisoned inputs, but fail to recover correct outputs once the backdoor is activated. |
| Approach: | They propose a soft label mechanism and key-extraction-guided CoT-based defense against instruction backdoors in APIs (SLIP) they propose KCOT-based model to extract task-relevant keywords and phrases rather than only considering the single trigger or overall text semantics. |
| Outcome: | The proposed model reduces the average attack success rate to 25.13% and improves clean accuracy to 87.15% and outperforms state-of-the-art black-box defenses. |
Combining Constrained and Unconstrained Decoding via Boosting: BoostCD and Its Application to Information Extraction (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent approaches to structured NLP tasks use autoregressive models trained on pairs of unstructured input text and structured output targets. |
| Approach: | They propose a model that combines constrained and unconstrained decoding in two phases to achieve two weak predictions. |
| Outcome: | The proposed model outperforms previous approaches both in and out of distribution, addressing several common errors identified in those approaches. |
VISIT: Visualizing and Interpreting the Semantic Information Flow of Transformers (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent work in interpretability suggests we can project weights and hidden states of transformer-based language models (LMs) to their vocabulary space, a transformation that makes them more human interpretable. |
| Approach: | They propose a tool to visualize a forward pass of Generative Pre-trained Transformers as an interactive flow graph with nodes representing neurons or hidden states and edges representing interactions between them. |
| Outcome: | The proposed visualization simplifies huge amounts of data into easy-to-read graphs that can reflect the models’ internal processing, uncovering the contribution of each component to the models' final prediction. |
DocSplit: Simple Contrastive Pretraining for Large Document Embeddings (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing model pretraining methods only consider local information, resulting in low-quality embeddings for large documents. |
| Approach: | They propose a new method which forces models to consider the entire global context of a large document. |
| Outcome: | The proposed method outperforms existing models on document classification, few shot learning, and retrieval tasks. |
Chain-of-History Reasoning for Temporal Knowledge Graph Forecasting (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing graph-based models excel at capturing structural information within TKGs but lack semantic comprehension abilities. |
| Approach: | They propose a plug-and-play module to enhance the performance of graph-based TKG models by exploring high-order histories step-by-step. |
| Outcome: | Experiments on three datasets and backbones show that CoH is effective in capturing high-order historical information for LLMs. |
Tracing Mathematical Proficiency Through Problem-Solving Processes (2026.findings-acl)
Copied to clipboard
| Challenge: | Knowledge Tracing (KT) models a learner's evolving knowledge state over time, but lacks the rich information embedded in students' problem-solving processes. |
| Approach: | They propose a framework that uses a teacher-student-teacher pipeline to extract students’ Mathematical Proficiency (MP) as intermediate representation. |
| Outcome: | The proposed framework improves the prediction performance of existing KT methods and provides interpretable explanations by explicitly modeling students’ mathematical proficiency. |
A Training-Free Debiasing Framework with Counterfactual Reasoning for Conversational Emotion Detection (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies in Emotion Recognition in Conversations (ERC) focus on capturing context-sensitive and speaker-sensitive dependencies, ignoring the unintended dataset biases of data. |
| Approach: | They propose a training-free debiasing framework that extracts biases from the model by generating counterfactual utterances and contexts and mitigates them using simple yet empirically robust element-wise subtraction operations. |
| Outcome: | Experiments on three public datasets show that the proposed framework improves generalization ability and fairness across different ERC models. |
TacoPrompt: A Collaborative Multi-Task Prompt Learning Method for Self-Supervised Taxonomy Completion (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for automating taxonomy completion use subtasks to learn subtask results, ignoring the effects of subtask on the final prediction. |
| Approach: | They propose a multi-task automatic taxonomy completion method that attaches emerging concepts to an appropriate pair of hypernym and hyponym in existing taxonomies. |
| Outcome: | The proposed method improves on three datasets and improves inference efficiency. |
Can Large Language Models Enhance Predictions of Disease Progression? Investigating Through Disease Network Link Prediction (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have made significant strides in various tasks, yet their effectiveness in predicting disease progression remains relatively unexplored. |
| Approach: | They propose a large language model with graph prompting and Retrieval-augmented generation to enhance the prediction performance of disease comorbidity within disease networks. |
| Outcome: | The proposed model outperforms Graph Neural Networks and Graph Prompts and Retrieval-Augmented Generation models in disease progression prediction tasks. |
Towards Informative Few-Shot Prompt with Maximum Information Gain for In-Context Learning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language models (LLMs) have the capability to engage In-context Learning (ICL) however, this particular learning paradigm suffers from high instability stemming from factors such as input distribution, order and prompt formats. |
| Approach: | They propose to quantify the information gain obtained in prediction after observing a given example candidate and to sample those with maximum IG. |
| Outcome: | The proposed method can yield an average relative improvement of 14.3% across six classification tasks using three LLMs. |
Detecting Online Community Practices with Large Language Models: A Case Study of Pro-Ukrainian Publics on Twitter (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for identifying practices within social media are not yet available. |
| Approach: | They propose a methodological workflow for computational identification of such practices within social media texts by using open-source models and OpenAI’s large language models. |
| Outcome: | The proposed method improves accuracy and supports context-sensitive moderation and advancing the understanding of online community dynamics. |
Large Language Models with Temporal Reasoning for Longitudinal Clinical Summarization and Prediction (2025.findings-emnlp)
Copied to clipboard
Maya Kruse, Shiyue Hu, Nicholas Derby, Yifu Wu, Samantha Stonbraker, Bingsheng Yao, Dakuo Wang, Elizabeth M. Goldberg, Yanjun Gao
| Challenge: | Recent advances in large language models have shown potential in clinical text summarization, but their ability to handle long patient trajectories with multi-modal data spread across time remains underexplored. |
| Approach: | They evaluate open-source large language models, their Retrieval Augmented Generation variants and chain-of-thought prompting on long-context clinical summarization and prediction. |
| Outcome: | The proposed models can synthesize structured and unstructured EHR data while reasoning over temporal coherence. |
Adapters Mixup: Mixing Parameter-Efficient Adapters to Enhance the Adversarial Robustness of Fine-tuned Pre-trained Text Classifiers (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies show that augmenting the training data of pre-trained language models with parametric fine-tuning methods can enhance their robustness under adversarial attacks. |
| Approach: | They propose an approach that fine-tunes PLMs with adapters and adversarial augmentation via mixup to leverage existing knowledge from a set of pre-known attacks. |
| Outcome: | The proposed approach achieves best trade-off between training efficiency and robustness under adversarial attacks compared to baselines on five downstream tasks across six varied black-box attacks and 2 PLMs. |
Discourse-Driven Code-Switching: Analyzing the Role of Content and Communicative Function in Spanish-English Bilingual Speech (2025.emnlp-main)
Copied to clipboard
| Challenge: | Prior work has shown that a range of speaker and listener attributes affect or correlate with the prevalence of code-switching during conversation. |
| Approach: | They analyze the names of entities and dialogue acts present in a Spanish-English spontaneous speech corpus and build a predictive model of CSW. |
| Outcome: | The proposed model is the first to take a discourse-sensitive approach to understanding pragmatic and referential cues of bilingual speech. |
MedCPI: A Construct–Personalize–Integrate Framework for KG-enhanced Clinical Prediction (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing KG-enhanced approaches to clinical prediction are limited . existing approaches to personalize and integrate knowledge are weakly controlled . |
| Approach: | They propose a framework to integrate medical knowledge graphs into EHRs to support KG-enhanced clinical prediction. |
| Outcome: | The proposed framework improves on MIMIC-III and MIMIC IV tasks. |
Sequence-to-Sequence Language Models for Character and Emotion Detection in Dream Narratives (2024.lrec-main)
Copied to clipboard
| Challenge: | Sigmund Freud's interpretation of dreams has been central to understanding human consciousness for centuries. |
| Approach: | They propose to automate the annotation process by using a natural language framework . they evaluate the impact of model size, prediction order of characters, and consideration of proper names and character traits . |
| Outcome: | The proposed model performs better with a large language model while having 28 times fewer parameters. |
The Sonar Moment: An Audio Geo-Localization Benchmark for Audio-Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | AGL1K is the first audio geo-localization benchmark for audio language models (ALMs) it is based on a crowd-sourced platform and is available in 72 countries and territories. |
| Approach: | They propose a benchmark for audio geo-localization that quantifies the informativeness of each recording and a metric that quantizes the information of each audio clip. |
| Outcome: | The proposed benchmarks cover 72 countries and territories and can be used to improve audio geo-localization. |
Predicting Through Generation: Why Generation Is Better for Prediction (2025.acl-long)
Copied to clipboard
Md Kowsher, Nusrat Jahan Prottasha, Prakash Bhat, Chun-Nam Yu, Mojtaba Soltanalian, Ivan Garibay, Ozlem Garibay, Chen Chen, Niloofar Yousefi
| Challenge: | Large Language Models (LLMs) are increasingly used for predictive tasks such as classification and regression. |
| Approach: | They propose a framework that generates output tokens from mas-sive text corpora and a task adapter to ensure consistency between token generation and final prediction. |
| Outcome: | The proposed framework outperforms baseline models on classification and regression benchmarks and the proposed framework consistently outperformed standard baseline models. |
LLM-based Rumor Detection via Influence Guided Sample Selection and Game-based Perspective Analysis (2025.acl-long)
Copied to clipboard
Zhiliang Tian, Jingyuan Huang, Zejiang He, Zhen Huang, Menglong Lu, Linbo Qiao, Songzhu Mei, Yijie Wang, Dongsheng Li
| Challenge: | Existing methods for rumor detection on social media are limited by limited modeling capacity and insufficient training corpora. |
| Approach: | They propose an SFT-based rumor detection model with Influence guided Sample selection and Game-based multi-perspective analysis to address these issues. |
| Outcome: | The proposed model outperforms existing SOTA on three datasets. |
Aspect-Oriented Summarization for Psychiatric Short-Term Readmission Prediction (2025.emnlp-main)
Copied to clipboard
WonJin Yoon, Boyu Ren, Spencer Thomas, Chanhwi Kim, Guergana K Savova, Mei-Hua Hall, Timothy A. Miller
| Challenge: | Recent advances in large language models have enabled the automated processing of lengthy documents even without supervised training on a task-specific dataset. |
| Approach: | They propose a method for processing the summaries of long documents using different aspect-oriented prompts and integrate the information signals from these different prompts for supervised training of transformer models. |
| Outcome: | The proposed method improves on a high-impact task predicting readmissions from a psychiatric discharge using real-world data from four hospitals. |
Towards Explainability and Fairness in Swiss Judgement Prediction: Benchmarking on a Multilingual Dataset (2024.lrec-main)
Copied to clipboard
| Challenge: | Using Swiss Judgement Prediction, we evaluate the explainability of state-of-the-art monolingual and multilingual LJP models. |
| Approach: | They propose an occlusion-based approach to evaluate the explainability performance of legal judgement prediction models using Swiss Judgement Prediction, the only available multilingual LJP dataset. |
| Outcome: | The proposed framework allows us to quantify the influence of lower court information on model predictions, exposing current models’ biases. |
SciImpact: A Multi-Dimensional, Multi-Field Benchmark for Scientific Impact Prediction (2026.findings-acl)
Copied to clipboard
| Challenge: | Prior work on scientific impact prediction has focused on citation counts and its variants, leaving limited evaluation of models’ capability to reason about other dimensions. |
| Approach: | They propose a large-scale, multi-dimensional benchmark for scientific impact prediction spanning 19 fields. |
| Outcome: | The proposed model outperforms larger models and close-source models in a wide range of fields and measures of scientific impact across 19 fields. |
Less is More: Knowledge-Aware Compression for Long Legal Judgment Prediction (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent advances leverage large language models (LLMs) for legal reasoning, but they face high computational costs and information degradation when handling long cases. |
| Approach: | They propose a framework that selectively retains legally relevant information while reducing redundant or less informative content, enabling efficient and accurate long-context reasoning. |
| Outcome: | The proposed framework outperforms existing methods on four real-world datasets spanning multiple jurisdictions and languages. |
Tree-of-Evidence: Efficient "System 2" Search for Faithful Multimodal Grounding (2026.findings-acl)
Copied to clipboard
| Challenge: | Attention-based methods fail to faithfully represent the model’s decision process when integrating heterogeneous modalities. |
| Approach: | They propose an inference-time search algorithm that frames interpretability as a discrete optimization problem. |
| Outcome: | The proposed algorithm retains over 98% of full-model AUROC with as few as five evidence units and achieves higher decision agreement and lower error than LIME, SHAP, saliency, and concept-bottleneck baselines under sparse budgets. |
Unveiling Project-Specific Bias in Neural Code Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) based neural code models struggle to generalize effectively to real-world inter-project out-of-distribution data. |
| Approach: | They propose a Cond-Idf measurement to measure the relatedness of a token with a label and its project-specificness. |
| Outcome: | The proposed framework improves both inter-project OOD generalization and adversarial robustness while not sacrificing accuracy on intra-project IID data. |
WkNER: Enhancing Named Entity Recognition with Word Segmentation Constraints and kNN Retrieval (2024.lrec-main)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) tasks require detecting the span and category of the entity from the text block. |
| Approach: | They propose a kNN retrieval enhancement algorithm that incorporates word segmentation information to enhance the model’s generalization ability and alleviate the problem of missing entity tokens in prediction. |
| Outcome: | The proposed method improves the performance of baseline models and achieves better or compared recognition accuracy than previous state-of-the-art models in multiple public Chinese and English datasets. |
MultiDx: A Multi-Source Knowledge Integration Framework towards Diagnostic Reasoning (2026.findings-acl)
Copied to clipboard
Yimin Deng, Zhenxi Lin, Yejing Wang, Guoshuai Zhao, Pengyue Jia, Zichuan Fu, Derong Xu, Yefeng Zheng, Xiangyu Zhao, Li Zhu, Xian Wu, Xueming Qian
| Challenge: | Existing approaches focus on diagnostic reasoning based on internal model knowledge or static knowledge bases. |
| Approach: | They propose a two-stage diagnostic reasoning framework that integrates multi-perspective evidence to generate a diagnostic prediction. |
| Outcome: | The proposed method generates suspected diagnoses and reasoning traces from web search, SOAP-formatted case, and clinical case database. |
Characterizing the Robustness of Black-Box LLM Planners Under Perturbed Observations with Adaptive Stress Testing (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models have been used in reasoning-heavy planning tasks but their tendency to hallucinate unsafe outputs poses risks. |
| Approach: | They propose a method for searching the space of prompt perturbations using adaptive stress testing with Monte-Carlo tree search. |
| Outcome: | The proposed method can detect scenarios, sensor configurations, and prompt phrasing that cause models to act with high uncertainty or crash. |
Advancing Reasoning in Diffusion Language Models with Denoising Process Rewards (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for improving reasoning in diffusion language models rely on outcome-based rewards that provide no direct supervision over the denoising process. |
| Approach: | They propose a method that provides a process-level reinforcement signal over denoising trajectory of diffusion language models. |
| Outcome: | Experiments on challenging reasoning benchmarks show that the proposed model improves reasoning stability, interpretability and overall performance. |
Policy-Guided Stepwise Action Planning for Controllable LLM Reasoning (2026.findings-acl)
Copied to clipboard
| 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. |
R3-SQL: Ranking Reward and Resampling for Text-to-SQL (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing rankers assign inconsistent scores to functionally equivalent SQL queries . ranking cannot recover when the correct SQL is absent from the pool. |
| Approach: | They propose a Text-to-SQL framework that rewards ranking and resampling . it first groups candidates by execution result and ranks groups for consistency . |
| Outcome: | The proposed framework achieves 75.03 execution accuracy on BIRD-dev, a new state of the art among methods using models with disclosed sizes. |