Papers with Ablation studies
Relevance, Diversity, and Exclusivity: Designing Keyword-augmentation Strategy for Zero-shot Classifiers (2024.starsem-1)
Copied to clipboard
| Challenge: | Existing methods incorporate semantically similar keywords related to class names, but the properties of effective keywords remain unclear. |
| Approach: | They propose a method for acquiring keywords that satisfy these properties without additional knowledge bases or data. |
| Outcome: | The proposed method outperforms existing methods in fully zero-shot and generalized zero- shot settings. |
ConQuer: A Framework for Concept-Based Quiz Generation (2025.naacl-srw)
Copied to clipboard
| Challenge: | Existing concepts-based quiz generation frameworks that leverage external knowledge sources are challenging and labor intensive. |
| Approach: | They propose a concept-based quiz generation framework that leverages external knowledge sources to assess the quality of the generated quizzes, using LLMs as judges. |
| Outcome: | The proposed framework shows a 4.8% improvement in evaluation scores and a 77.52% win rate in pairwise comparisons against baseline quiz sets. |
Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm (2022.acl-long)
Copied to clipboard
Shaoyi Huang, Dongkuan Xu, Ian Yen, Yijue Wang, Sung-En Chang, Bingbing Li, Shiyang Chen, Mimi Xie, Sanguthevar Rajasekaran, Hang Liu, Caiwen Ding
| Challenge: | Conventional wisdom in pruning Transformer-based language models is that it reduces model expressiveness, but new research shows pruning increases risk of overfitting when performed at the fine-tuning phase. |
| Approach: | They propose to reduce pruning risk under pretrain-and-finetune paradigm . they propose to use knowledge distillation to improve pruning performance . |
| Outcome: | The proposed method outperforms the leading competitors on the GLUE benchmark. |
Proximity-Based Multi-Turn Optimization: Practical Credit Assignment for LLM Agent Training (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing group-based policy optimization methods rely on statistical deviation within discrete batches, misallocating credit when task difficulty fluctuates. |
| Approach: | They propose a framework for multi-turn LLM agents that integrates global context . they propose GRPO, which integrates success-rate-aware modulation and proximity-based soft aggregation . |
| Outcome: | The proposed framework yields performance gains over existing baselines with negligible computational cost. |
SMARTAVE: Structured Multimodal Transformer for Product Attribute Value Extraction (2022.findings-emnlp)
Copied to clipboard
Qifan Wang, Li Yang, Jingang Wang, Jitin Krishnan, Bo Dai, Sinong Wang, Zenglin Xu, Madian Khabsa, Hao Ma
| Challenge: | Existing methods for product attribute value extraction are noisy and incomplete with missing values for most retailers. |
| Approach: | They propose a Structure Mltimodal trAnsformeR for producT Attribute Value Extraction which jointly encodes the structured product information from multiple modalities. |
| Outcome: | The proposed method outperforms state-of-the-art methods on two multimodal product datasets. |
Analogical Structure, Minimal Contextual Cues and Contrastive Distractors: Input Design for Sample-Efficient Linguistic Rule Induction (2026.eacl-long)
Copied to clipboard
| Challenge: | Recent systems that use analogical reasoning require extensive knowledge engineering and even transformer-based models show inconsistent results across complexity levels. |
| Approach: | They propose to implement analogical structure, contrastive learning, and minimal contextual cue principles into large language models that train on English verb alternations. |
| Outcome: | The proposed models learn the alternation rules with high F1 on English verb alternations. |
MPRF: Interpretable Stance Detection through Multi-Path Reasoning Framework (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing stance detection methods treat the task as a classification problem, where models output a stance label without providing interpretable reasoning paths. |
| Approach: | They propose a framework that generates, evaluates, and integrates multiple reasoning paths to improve accuracy, robustness, and transparency in stance detection. |
| Outcome: | The proposed framework outperforms existing models on the SEM16, VAST, and PStance datasets and is highly interpretable and reliable. |
PCEE-BERT: Accelerating BERT Inference via Patient and Confident Early Exiting (2022.findings-naacl)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) are the state-of-the-art (SOTA) models for natural language processing (NLP). |
| Approach: | They propose a patient and confident early exiting BERT (PCEE-BERT) that can work with different PLMs and popular model compression methods. |
| Outcome: | The proposed method outperforms existing models on the GLUE benchmarks and achieves different speed-up ratios. |
Bidirectional Masked Self-attention and N-gram Span Attention for Constituency Parsing (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing attention mechanisms for constituency parsing lack directional information needed to form sentence spans. |
| Approach: | They propose a bidirectional masked and N-gram span Attention model which captures the explicit dependencies between each word and enhances the representation of the output span vectors. |
| Outcome: | The proposed model achieves state-of-the-art performance on the Penn Treebank and Chinese Penn TreeBank datasets with F1 scores of 96.47 and 94.15 respectively. |
TTM-RE: Memory-Augmented Document-Level Relation Extraction (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for document-level relation extraction are ineffective in exploiting the full potential of large amounts of training data with varied noise levels. |
| Approach: | They propose a novel approach that integrates a trainable memory module with a noisy-robust loss function that accounts for the positive-unlabeled setting to unlock the full potential of large-scale noisy training data. |
| Outcome: | The proposed model outperforms existing methods on a ReDocRED benchmark dataset with an absolute F1 score improvement of over 3%. |
ReflectiveRAG: Rethinking Adaptivity in Retrieval-Augmented Generation (2026.eacl-industry)
Copied to clipboard
| Challenge: | Existing methods for retrieval-augmented generation (RAG) fail to assess evidence sufficiency, detect subtle mismatches or reduce redundancy. |
| Approach: | They propose a lightweight yet reasoning-driven architecture that enhances factual grounding . ReflectiveRAG employs self-reflective retrieval and Contrastive noise removal . |
| Outcome: | a new architecture improves factual grounding by using self-reflective retrieval and Contrastive noise removal. |
You Only Need Attention to Traverse Trees (P19-1)
Copied to clipboard
| Challenge: | Recent research has focused on sentence representations. |
| Approach: | They propose a tree-based model that captures phrase-level syntax and word-level dependencies by doing recursive traversal with attention. |
| Outcome: | a new model captures phrase-level syntax and word-level dependencies with attention. |
T-MAD: Target-driven Multimodal Alignment for Stance Detection (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for Multimodal Stance Detection struggle with generalizing to unseen targets and handling modality inconsistencies. |
| Approach: | They propose a multimodal stability detection model which captures target-specific relationships and balances modality contributions by iterative reasoning. |
| Outcome: | Experiments on the MMSD and MultiClimate datasets show that the proposed model outperforms state-of-the-art models with optimal results achieved using RoBERTa, ViT, and an iterative depth of 5. |
PAXQA: Generating Cross-lingual Question Answering Examples at Training Scale (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing question answering systems rely on large, high-quality training data. |
| Approach: | They propose a synthetic data generation method which decomposes cross-lingual QA into two stages . they apply a question generation model to the English side and annotation projection to translate both questions and answers. |
| Outcome: | The proposed method outperforms existing methods on cross-lingual QA datasets. |
BigTokDetect: A Clinically-Informed Vision–Language Modeling Framework for Detecting Pro-Bigorexia Videos on TikTok (2026.eacl-long)
Copied to clipboard
Minh Duc Chu, Kshitij Pawar, Zihao He, Roxanna Sharifi, Ross M. Sonnenblick, Magdalayna Curry, Laura DAdamo, Lindsay Young, Stuart Murray, Kristina Lerman
| Challenge: | Social media platforms face escalating challenges in detecting harmful content that promotes muscle dysmorphic behaviors and cognitions (bigorexia). |
| Approach: | They propose a framework for detecting pro-bigorexia content on TikTok using an expert-annotated multimodal benchmark dataset of over 2,200 Tiktok videos labeled by clinical psychiatrists. |
| Outcome: | The proposed framework improves on fine-grained subcategories while commercial models achieve the highest accuracy on primary categories. |
NEST: Nested Evidence Survival for Retrieval (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing approaches to retrieval-augmented generation (RAG) rely on rigid heuristics or computational overhead. |
| Approach: | They propose a lightweight, training-free RAG framework that separates recall amplification from precision selection. |
| Outcome: | Evaluated on WebQuestions, HotpotQA and internalQA benchmarks, NEST outperforms strong adaptive RAG baselines. |
A Dual-Phase Self-Evolution Framework for Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing strategies to optimize LLMs through pretraining fail to enhance domain cognition. |
| Approach: | They propose a dual-phase self-evolution framework that integrates user preference adaptation and domain-specific competence to optimize LLMs. |
| Outcome: | The proposed framework outperforms Supervised Fine-Tuning, Preference Optimization, and Memory-Augmented baselines on general NLP benchmarks and long-term dialogue tasks. |
PAFT: Prompt-Agnostic Fine-Tuning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Prompt-agnostic fine-tuning (PAFT) improves performance by reducing overfitting to specific prompts. |
| Approach: | They propose a method that enhances robustness through dynamic prompt variation during training. |
| Outcome: | The proposed method achieves higher generalization accuracy on unseen prompts than standard methods with similar training efficiency. |
Fast or Slow? Integrating Fast Intuition and Deliberate Thinking for Enhancing Visual Question Answering (2025.acl-short)
Copied to clipboard
| Challenge: | Current approaches generate visual markers for all questions, generating excessive visual markers. |
| Approach: | They propose a plug-and-play approach that adapts to the complexity of questions . they propose combining fast intuitive judgments with deliberate analytical reasoning . |
| Outcome: | The proposed approach improves performance on four benchmarks on ScienceQA, TextQA, VizWiz, and MME. |
AutoBool: Reinforcement-Learned LLM for Effective Automatic Systematic Reviews Boolean Query Generation (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing approaches to generate Boolean queries for systematic reviews are limited by the lack of ground-truth best Boolesan queries. |
| Approach: | They propose a reinforcement learning framework that trains large language models to generate effective Boolean queries for medical systematic reviews. |
| Outcome: | The proposed framework outperforms zero-shot/few-shot prompting on 65 588 topics . it also matches or exceeds the effectiveness of larger GPT-based models using smaller backbones . |
DATScore: Evaluating Translation with Data Augmented Translations (2023.findings-eacl)
Copied to clipboard
| Challenge: | Experimental results show that DATScore correlates better with human meta-evaluations than the other recent state-of-the-art metrics. |
| Approach: | They propose to use data augmented translations to improve the evaluation of machine translations by using two new scoring strategies. |
| Outcome: | The proposed metric improves on 3 NLG tasks other than translation. |
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training (2021.findings-acl)
Copied to clipboard
| Challenge: | Symbolic music understanding is useful for many music applications, but lack of training data hinders representation learning. |
| Approach: | They propose a pre-trained model for music understanding that uses symbolic music data to train music representations. |
| Outcome: | The proposed model improves on four music understanding tasks. |
Optimal Transport Posterior Alignment for Cross-lingual Semantic Parsing (2023.tacl-1)
Copied to clipboard
| Challenge: | Existing work on cross-lingual semantic parsing has focused on English . a few-shot approach to parse from natural languages is comparatively unexplored . |
| Approach: | They propose a method that minimizes cross-lingual divergence between probabilistic latent variables by Optimal Transport. |
| Outcome: | The proposed method improves performance even without parallel input translations on two datasets. |
VividMed: Vision Language Model with Versatile Visual Grounding for Medicine (2025.naacl-long)
Copied to clipboard
| Challenge: | Vision Language Models (VLMs) have demonstrated promise in generating visually grounded responses, but their application in the medical domain is hindered by unique challenges. |
| Approach: | They propose a vision language model with versatile visual grounding for medicine that generates semantic segmentation masks and instance-level bounding boxes. |
| Outcome: | The proposed model can generate semantic segmentation masks and instance-level bounding boxes, and accommodates various imaging modalities, including both 2D and 3D data. |
Morphology-Aware Multi-Granularity Representation Learning for Agglutinative Languages (2026.acl-srw)
Copied to clipboard
| Challenge: | Existing methods for learning low-resource agglutinative languages are limited to word and phrase levels. |
| Approach: | They propose a morphology-aware gated multi-granularity pre-training framework for agglutinative languages . framework leverages morphological knowledge and integrates a word-level encoder to capture contextual semantics . |
| Outcome: | The proposed framework improves on Mongolian and Turkish agglutinative languages . it leverages morphological knowledge and integrates tagging and segmentation to build fine-grained representations . |
A Multistage Extraction Pipeline for Long Scanned Financial Documents: An Empirical Study in Industrial KYC Workflows (2026.acl-industry)
Copied to clipboard
| Challenge: | Structured information extraction from long, multilingual scanned financial documents is a core requirement in industrial KYC and compliance workflows. |
| Approach: | They propose a framework for structured information extraction from long, multilingual scanned financial documents . they combine image preprocessing, multilinguistic OCR, hybrid page-level retrieval and VLMs . |
| Outcome: | The proposed pipeline outperforms direct PDF-to-VLM baselines on 120 production KYC documents. |
Revealing the Truth with ConLLM for Detecting Multi-Modal Deepfakes (2026.findings-eacl)
Copied to clipboard
Gautam Siddharth Kashyap, Harsh Joshi, Niharika Jain, Ebad Shabbir, Jiechao Gao, Nipun Joshi, Usman Naseem
| Challenge: | Existing methods for deepfake detection suffer from two limitations: modality fragmentation and shallow inter-modal reasoning. |
| Approach: | They propose a framework for multimodal deepfake detection that uses contrastive learning and large language models to mitigate modality fragmentation and refine embeddings to address shallow inter-modal reasoning. |
| Outcome: | ConLLM reduces audio deepfake EER by 50%, improves video accuracy by 8%, and achieves approximately 9% accuracy gains in audio-visual tasks. |
ChatR1: Reinforcement Learning for Conversational Reasoning and Retrieval Augmented Question Answering (2026.acl-long)
Copied to clipboard
| Challenge: | Unlike static ‘rewrite, retrieve, and generate’ pipelines, ChatR1 interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through RL. |
| Approach: | They propose a reasoning framework based on reinforcement learning (RL) for conversational question answering that interleaves search and reasoning across turns and provides turn-level feedback. |
| Outcome: | The proposed framework outperforms competing models on five CQA datasets, measured by different metrics (F1, BERTScore, and LLM-as-judge). |
An Effective Deployment of Diffusion LM for Data Augmentation in Low-Resource Sentiment Classification (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for textual data augmentation (DA) are highly data-hungry and struggle to perform satisfactorily under noisy conditions. |
| Approach: | They propose to leverage a diffusion language model to capture in-domain knowledge and generate pseudo samples by reconstructing strong label-related tokens. |
| Outcome: | The proposed method captures in-domain knowledge and generates pseudo samples by reconstructing strong label-related tokens. |
Biomedical Event Extraction with Hierarchical Knowledge Graphs (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Biomedical event extraction is critical in understanding biomolecular interactions described in scientific corpus. |
| Approach: | They propose to integrate domain knowledge from Unified Medical Language System (UMLS) to a pre-trained language model using Graph Edge-conditioned Attention Networks and hierarchical graph representation. |
| Outcome: | The proposed approach achieves 1.41% F1 and 3.19% F1 improvements on the BioNLP 2011 GENIA Event Extraction task. |
Cascaded Mutual Modulation for Visual Reasoning (D18-1)
Copied to clipboard
| Challenge: | Visual reasoning is a multi-step and compositional problem that requires intensive text-vision interactions. |
| Approach: | They propose a visual reasoning model that uses a feature-wise linear modulation technique to enable textual/visual pipelines to mutually control each other. |
| Outcome: | The proposed model outperforms existing models on visual reasoning benchmarks CLEVR and NLVR . it can generate a textual answer to a visual question answering problem with images . |
Learning from Diverse Reasoning Paths with Routing and Collaboration (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies suggest that the reasoning abilities of large language models (LLMs) grows with model size and pre-training data. |
| Approach: | They propose to combine quality filtering, conditional routing, and cooperative peer teaching to transfer knowledge from powerful teacher models to compact and transparent students. |
| Outcome: | Experiments show that QR-Distill is superior to traditional methods. |
Generalized Embedding Models for Industry 4.0 Applications (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Using Large Language Models (LLMs) to automate tasks has emerged as the next frontier of innovation. |
| Approach: | They propose a model that generalizes to queries involving similar assets and retrieves relevant items from natural language tasks. |
| Outcome: | The proposed model can be used to generalize to queries involving similar assets, such as identifying sensors relevant to an asset’s failure mode. |
InfiniSST: Simultaneous Translation of Unbounded Speech with Large Language Model (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing models for simultaneous speech translation assume pre-segmented speech, limiting their real-world applicability. |
| Approach: | They propose a multi-turn dialogue task that can translate unbounded streaming speech . they construct translation trajectories and robust segments from MuST-C with multi-latency augmentation during training and develop a cache management strategy to facilitate efficient inference. |
| Outcome: | The proposed approach reduces computation-aware latency by 0.5 to 1 second while maintaining the same translation quality compared to baselines. |
MotivGraph-SoIQ: Integrating Motivational Knowledge Graphs and Socratic Dialogue for Enhanced LLM Ideation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have limitations in grounding ideas and mitigating confirmation bias during refinement. |
| Approach: | They propose a framework that integrates a Motivational Knowledge Graph with a Q-Driven Socratic Ideator to enhance LLM ideation. |
| Outcome: | The proposed framework enhances LLM ideation by integrating a Motivational Knowledge Graph with a Q-Driven Socratic Ideator. |
<SYNTACT>: Structuring Your Natural Language SOPs into Tailored Ambiguity-Resolved Code Templates (2025.emnlp-industry)
Copied to clipboard
Sachin Kumar Giroh, Pushpendu Ghosh, Aryan Jain, Harshal Giridhari Paunikar, Aditi Rastogi, Promod Yenigalla, Anish Nediyanchath
| Challenge: | Unstructured and ambiguous Standard Operating Procedures suffer from ambiguity, missing information, and inconsistency, all of which hinder automation. |
| Approach: | They propose a three-stage LLM framework that transforms unstructured SOPs into a structured plan and an executable code template. |
| Outcome: | The proposed framework shows an 88.4% accuracy and significant reduction in inconsistency on real-world SOPs and synthetic variants. |
SPaCe: Unlocking Sample-Efficient Large Language Models Training With Self-Pace Curriculum Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing training pipelines sample training examples uniformly across steps or epochs, ignoring differences in difficulty, redundancy, and learning value, which slows learning and wastes computation. |
| Approach: | They propose a self-paced learning framework that enables efficient learning based on the capability of the model being trained through optimizing which data to use and when. |
| Outcome: | The proposed framework achieves comparable or better accuracy than state-of-the-art baselines while using up to (100 times) fewer samples. |
Which One? Leveraging Context Between Objects and Multiple Views for Language Grounding (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for identifying object referents of language expressions consider target and distractor objects independently and pool multiple views before grounding. |
| Approach: | They propose a model that selects an object referent based on language that distinguishes between two similar objects and a multi-view approach to grounding in context model which reduces the relative error by 12.9% . |
| Outcome: | The proposed model improves on the SNARE object reference task with a relative error reduction of 12.9% and an absolute improvement of 2.7%. |
DeCEMBERT: Learning from Noisy Instructional Videos via Dense Captions and Entropy Minimization (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods to train models on unlabeled web videos are noisy and temporally misaligned . authors propose a method that adds captions and constrained attention loss to improve performance . |
| Approach: | They propose a method that adds captions from video frames as auxiliary text input to provide visual cues for learning better video and language associations. |
| Outcome: | The proposed method outperforms state-of-the-art methods on video-and-language tasks . it adds captions and constrained attention loss to improve model performance . |
EventWeave: A Dynamic Framework for Capturing Core and Supporting Events in Dialogue Systems (2026.acl-long)
Copied to clipboard
Zhengyi Zhao, Shubo Zhang, Yiming Du, Bin Liang, Baojun Wang, Zhongyang Li, Binyang Li, Kam-Fai Wong
| Challenge: | Existing dialogue systems process conversational turns in isolation, overlooking event structures that guide natural interactions. |
| Approach: | They propose a framework that explicitly models relationships between conversational events to generate more contextually appropriate dialogue responses. |
| Outcome: | Experiments on three dialogue datasets show that the proposed approach produces more natural responses while requiring less computational overhead. |
LNMap: Departures from Isomorphic Assumption in Bilingual Lexicon Induction Through Non-Linear Mapping in Latent Space (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for bilingual lexicon induction are mapping-based, but they do not hold for closely related languages. |
| Approach: | They propose a semi-supervised method to learn cross-lingual word embeddings for BLI using a linear mapping function and a latent space of two independently trained autoencoders. |
| Outcome: | The proposed method outperforms existing models on 15 different language pairs on both directions. |
Answer-state Recurrent Relational Network (AsRRN) for Constructed Response Assessment and Feedback Grouping (2023.findings-emnlp)
Copied to clipboard
| Challenge: | STEM educators must trade off the ease of assessing selected response (SR) questions with constructed response (CR) questions, where students articulate their own reasoning. |
| Approach: | They propose to use multiple choice questions to construct response questions . they use a relational neural network to relate context, questions, reference responses, and students’ answers to a new dataset of 6,532 student responses to three, two-part CR questions. |
| Outcome: | The proposed network outperforms classifiers based on LLMs and few-shot learning with GPT-3.5 on a new dataset of 6,532 student responses to three, two-part CR questions. |
From Numbers to Narratives: Efficient Language Model-Based Detection for Safety-Critical Minority Classes (2026.findings-eacl)
Copied to clipboard
| Challenge: | Tabular datasets with high overall accuracy and poor performance on minority classes are often misaligned . a numbers to narratives framework improves overall accuracy by up to 22.43% in five of six datasets while maintaining computational feasibility. |
| Approach: | They propose a number-to-narrative framework that transforms tabular data into contextually rich descriptions. |
| Outcome: | The proposed framework achieves superior minority class F1-scores in five of six datasets. |
Retrieval-augmented Image Captioning (2023.eacl-main)
Copied to clipboard
| Challenge: | Experimental results show that image captioning can be effectively formulated from this new perspective. |
| Approach: | They propose a pretrained visual and language decoders for image captioning that generate sentences from the input image and a set of captions retrieved from a datastore. |
| Outcome: | The proposed model generates sentences given the input image and retrieved captions, while the decoder attends to the multimodal encoder representations. |
ReGraphRAG: Reorganizing Fragmented Knowledge Graphs for Multi-Perspective Retrieval-Augmented Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Graph-based RAG systems have been promising for enabling multi-hop reasoning . but when knowledge graphs are constructed from unstructured documents, they suffer from fragmentation . |
| Approach: | They propose a framework to reconstruct and enrich fragmented knowledge graphs . they propose three core components: Graph Reorganization, Perspective Expansion, and Query-aware Reranking. |
| Outcome: | The proposed framework outperforms state-of-the-art benchmarks on four benchmarks . it achieves over 80% diversity win rate and enables multi-hop reasoning . |
TinyThinker: Distilling Reasoning through Coarse-to-Fine Knowledge Internalization with Self-Reflection (2025.naacl-long)
Copied to clipboard
| Challenge: | Large Language Models exhibit impressive reasoning capabilities across diverse tasks . direct training on synthesized reasoning data may lead to superficial imitation of reasoning process, authors argue . |
| Approach: | They propose a framework that introduces a three-stage process that incrementally guides the student model through the reasoning process, progressively refining knowledge from coarse to fine granularity. |
| Outcome: | The proposed framework achieves superior performance on commonsense reasoning benchmarks and can be extended to other knowledge-intensive reasoning tasks. |
MedCOD: Enhancing English-to-Spanish Medical Translation of Large Language Models Using Enriched Chain-of-Dictionary Framework (2025.findings-emnlp)
Copied to clipboard
| Challenge: | MedCOD integrates domain-specific structured knowledge into large language models . evaluators evaluated four open-source LLMs with structured prompts . |
| Approach: | They propose a framework that integrates domain-specific structured knowledge into large language models . they constructed a parallel corpus of 2,999 English-Spanish MedlinePlus articles . |
| Outcome: | The proposed framework improves translation quality across four open-source LLMs. |
Code-Switching Curriculum Learning for Multilingual Transfer in LLMs (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) exhibit near human-level performance in various tasks, but performance drops after a handful of high-resource languages due to the imbalance in pre-training data. |
| Approach: | They propose a code-switching curriculum learning model to enhance cross-lingual transfer for LLMs by progressively training models with a curriculum consisting of token-level code-changing, sentence-level codeswitching, and monolingual corpora. |
| Outcome: | The proposed model improves language transfer to Korean, with significant gains in Japanese and Indonesian . the proposed model mitigates spurious correlations between language resources and safety alignment . |
Cognitive Visual-Language Mapper: Advancing Multimodal Comprehension with Enhanced Visual Knowledge Alignment (2024.acl-long)
Copied to clipboard
| Challenge: | Recent Large Multimodal Models (LMMs) focus on visual knowledge-dimension alignment, but ignore visual knowledge. |
| Approach: | They propose a cognitive visual-language mapper that integrates visual-linguistic knowledge alignment with a fine-grained knowledge Adapter. |
| Outcome: | The proposed model significantly improves LMMs on knowledge-based visual question answering (VQA) it also improves the performance of other models, including GPT-4V and Gemini-Pro. |
MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes (2022.acl-long)
Copied to clipboard
| Challenge: | MemSum is a reinforcement-learning-based extractive summarizer that considers the text content of the sentence, the global context of the rest of the document, and the extraction history of the sentences that have already been extracted. |
| Approach: | They propose a reinforcement-learning-based extractive summarizer that iteratively selects sentences from a broad set of information that would intuitively be used by humans. |
| Outcome: | The proposed extractive summarizer is enriched with information on the extraction history and local, global, and historical information. |
Text Counterfactuals via Latent Optimization and Shapley-Guided Search (2021.emnlp-main)
Copied to clipboard
| Challenge: | Using latent optimization and Shapley values, we generate a set of minimal modifications to the text to change the classifier's prediction. |
| Approach: | They propose to generate a counterfactual by making minimal modifications to the text to change the model's prediction. |
| Outcome: | The proposed approach achieves favorable performance compared to white-box and black-box baselines using human and automatic evaluations. |
FineLAP: Taming Heterogeneous Supervision for Fine-grained Language-Audio Pretraining (2026.acl-long)
Copied to clipboard
| Challenge: | Existing audio-language models excel at clip-level understanding but struggle with frame-level tasks. |
| Approach: | They propose a novel training paradigm that advances both clip- and frame-level alignment in CLAP with heterogeneous data. |
| Outcome: | The proposed training paradigm improves both clip- and frame-level alignment in CLAP with heterogeneous data. |
Exploring and Evaluating Attributes, Values, and Structures for Entity Alignment (2020.emnlp-main)
Copied to clipboard
| Challenge: | Entity alignment (EA) aims at building a Knowledge Graph (KG) of rich content by linking the equivalent entities from various KGs. |
| Approach: | They propose to use an attributed value encoder to partition a Knowledge Graph into subgraphs to model the various types of attribute triples efficiently. |
| Outcome: | The proposed method achieves significant improvements over 12 baselines in cross-lingual and monolingual datasets. |
CLAPSpeech: Learning Prosody from Text Context with Contrastive Language-Audio Pre-Training (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for expressive text-to-speech only implicitly learn prosody with masked token reconstruction tasks. |
| Approach: | They propose a cross-modal contrastive pre-training framework that learns from prosody variance of the same text token under different contexts. |
| Outcome: | The proposed framework can learn from prosody variance of a text token under different contexts. |
LaMP-Cap: Personalized Figure Caption Generation With Multimodal Figure Profiles (2025.findings-emnlp)
Copied to clipboard
Ho Yin Sam Ng, Edward Hsu, Aashish Anantha Ramakrishnan, Branislav Kveton, Nedim Lipka, Franck Dernoncourt, Dongwon Lee, Tong Yu, Sungchul Kim, Ryan A. Rossi, Ting-Hao Kenneth Huang
| Challenge: | Figure captions are crucial for helping readers understand and remember a figure’s key message. |
| Approach: | They propose a dataset for personalized figure caption generation with multimodal figure profiles that provide inputs and profiles for each figure . |
| Outcome: | The proposed dataset provides inputs and profiles for personalized figure caption generation with multimodal figure profiles. |
Learning Latent Trees with Stochastic Perturbations and Differentiable Dynamic Programming (P19-1)
Copied to clipboard
| Challenge: | Discrete structures are ubiquitous in the study of natural languages, for example in morphology, syntax and discourse analysis. |
| Approach: | They treat projective dependency trees as latent variables in their probabilistic model and induce them in such a way as to be beneficial for a downstream task. |
| Outcome: | The proposed model is effective on sentiment analysis and natural language inference tasks and is fully differentiable. |
LATTE: Learning to Think with Vision Specialists (2025.emnlp-main)
Copied to clipboard
Zixian Ma, Jianguo Zhang, Zhiwei Liu, Jieyu Zhang, Juntao Tan, Manli Shu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Caiming Xiong, Ranjay Krishna, Silvio Savarese
| Challenge: | Open-source vision-language models excel on simple question-answering tasks, but struggle with complex questions that require both perception and reasoning. |
| Approach: | They propose a family of vision-language models that have LeArned to Think wiTh vision spEcialists by offloading perception to state-of-the-art vision models. |
| Outcome: | The proposed model achieves 4-5% gains over baselines across 6 benchmarks covering both perception and reasoning abilities. |
Peering Behind the Shield: Guardrail Identification in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Identifying guardrails in conversational AI agents is critical for identifying malicious content . identifying guardrail components in black-box AI agents poses security challenges . |
| Approach: | They propose a method that leverages guard-specific adversarial prompts to detect guardrails in black-box AI agents. |
| Outcome: | The proposed method achieves perfect classification accuracy in multiple scenarios. |
P-QuASAR: A Unified Probabilistic Framework for Holistic Patent Quality Assessment and Refinement (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for assessing patent quality rely on modular pipelines or generic detectors, resulting in fragmented decisions and limited integration across quality dimensions. |
| Approach: | They propose a probabilistic framework that represents patent specifications as Quality Graphs. |
| Outcome: | The proposed framework outperforms existing methods on 500 patents against seven baselines. |
MARE: Multi-Aspect Rationale Extractor on Unsupervised Rationale Extraction (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to extract text snippets from input text to support model predictions without explicit rationale annotation have limited their ability to capture meaningful internal correlations between aspects. |
| Approach: | They propose a multi-aspect rationale extractor that extracts text snippets to support model predictions without explicit rationale annotation. |
| Outcome: | The proposed method achieves state-of-the-art on two unsupervised rationale extraction benchmarks. |
Summarize-Exemplify-Reflect: Data-driven Insight Distillation Empowers LLMs for Few-shot Tabular Classification (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies show the promise of large language models for few-shot tabular classification but highlight challenges due to the variability in structured data. |
| Approach: | They propose a framework that distills data into actionable insights to enable robust and effective classification by large language models. |
| Outcome: | The proposed framework integrates rule summarization, strategic exemplification, and insight reflection through deep collaboration between LLMs and data modeling techniques. |
Exploiting Twitter as Source of Large Corpora of Weakly Similar Pairs for Semantic Sentence Embeddings (2021.emnlp-main)
Copied to clipboard
| Challenge: | Semantic sentence embeddings are usually supervisedly built minimizing distances between pairs of embeddable sentences labelled as semantically similar by annotators. |
| Approach: | They propose a language-independent approach to build large datasets of pairs of informal texts weakly similar, without manual human effort, exploiting Twitter’s powerful signals of relatedness: replies and quotes of tweets. |
| Outcome: | The proposed model learns classical Semantic Textual Similarity, and excels on tasks where pairs of sentences are not exact paraphrases. |
Automated Knowledge Graph Construction using Large Language Models and Sentence Complexity Modelling (2025.emnlp-main)
Copied to clipboard
Sydney Anuyah, Mehedi Mahmud Kaushik, Sri Rama Krishna Reddy Dwarampudi, Rakesh Shiradkar, Arjan Durresi, Sunandan Chakraborty
| Challenge: | integrating coreference and decomposition increases recall on rare relations by over 20%. |
| Approach: | They propose an open-source pipeline for extracting sentence-level knowledge graphs by combining robust coreference resolution with syntactic sentence decomposition. |
| Outcome: | The proposed pipeline achieves a 99.8% exact-match accuracy on sentence simplification. |
CritiQ: Mining Data Quality Criteria from Human Preferences (2025.acl-long)
Copied to clipboard
Honglin Guo, Kai Lv, Qipeng Guo, Tianyi Liang, Zhiheng Xi, Demin Song, Qiuyinzhe Zhang, Yu Sun, Kai Chen, Xipeng Qiu, Tao Gui
| Challenge: | Existing methods to train language models rely on manual design, perplexity, or careful prompt engineering. |
| Approach: | They propose a method that automatically mines criteria from human preferences for data quality with only 30 human-annotated pairs and performs efficient data selection. |
| Outcome: | The proposed method improves on human-annotated test sets and shows high accuracy on code, math, and logic domains. |
LLM-empowered Dynamic Prompt Routing for Vision-Language Models Tuning under Long-Tailed Distributions (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained vision-language models (VLMs) often suffer from bias in class-imbalanced scenes. |
| Approach: | They propose a multi-dimensional dynamic prompt routing framework that integrates a knowledge base for classes spanning multiple visual-semantic dimensions. |
| Outcome: | The proposed framework achieves comparable results with current SOTA methods on long-tailed benchmarks, including CIFAR-LT, ImageNet-LT and Places-LT. |
Exploiting Contrastive Learning and Numerical Evidence for Confusing Legal Judgment Prediction (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies fail to distinguish different classification errors with a standard cross-entropy classification loss and ignore the numbers in the fact description for predicting the term of penalty. |
| Approach: | They propose to extract crime amounts from fact description and use them to learn distinguishable representations to exploit the numbers in the fact description for predicting the term of penalty. |
| Outcome: | The proposed method achieves state-of-the-art results on real-world datasets and ablation studies demonstrate the effectiveness of each component. |
Context Minimization for Resource-Constrained Text Classification: Optimizing Performance-Efficiency Trade-offs through Linguistic Features (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Pretrained language models have transformed text classification, but their computational demands often render them impractical for resource-constrained settings. |
| Approach: | They propose a linguistically-grounded framework for context minimization that leverages theme-rheme structure to preserve critical classification signals while reducing input complexity. |
| Outcome: | The proposed framework preserves critical classification signals while reducing input complexity. |
Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization (2025.findings-acl)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) are known to hallucinate, which limits their practical applications. |
| Approach: | They propose a method that uses three types of preference pairs to target hallucinations from their diverse forms and causes. |
| Outcome: | The proposed method surpasses most state-of-the-art methods and shows potential for further improvements. |
Stratagem: Learning Transferable Reasoning via Trajectory-Modulated Game Self-Play (2026.acl-long)
Copied to clipboard
Xiachong Feng, Deyi Yin, Xiaocheng Feng, Yi Jiang, Libo Qin, Yangfan Ye, Lei Huang, Weitao Ma, Qiming Li, Yuxuan Gu, Bing Qin, Lingpeng Kong
| Challenge: | Existing self-play approaches to developing general reasoning in language models rely on terminal game outcomes. |
| Approach: | They propose a game-based reasoning transfer model that addresses two barriers to reasoning transfer. |
| Outcome: | The proposed model improves mathematical reasoning, general reasoning, and code generation benchmarks. |
RAMP: Risk-Aware Multi-Turn Planning for Jailbreak Red-Teaming (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for evaluating the safety of large language models rely on heuristic strategies or trained attack agents. |
| Approach: | They propose a method for multi-turn jailbreaking that iteratively plans and executes each turn via a Judge, a Transitioner, and a Planner. |
| Outcome: | The proposed framework achieves strong attack performance across open-source and closed-source target models while remaining effective under stricter turn budgets. |
Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism (2026.acl-long)
Copied to clipboard
Yuhua Jiang, Shuang Cheng, Yihao Liu, Ermo Hua, Che Jiang, Weigao Sun, Yu Cheng, Feifei Gao, Biqing Qi, Bowen Zhou
| Challenge: | Existing models lack task-guided specialized memory mechanisms . specialized generalist models excel at general language tasks but struggle in specialized domains. |
| Approach: | They propose a specialized generalist model with specialized memory and updater that can optimize for specialized domains. |
| Outcome: | The proposed model matches or surpasses baselines on general benchmarks and achieves lowest perplexity across specialized domains. |
Veri-R1: Toward Precise and Faithful Claim Verification via Online Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to online claim verification rely on prompt engineering or pre-designed reasoning workflows. |
| Approach: | They propose an online reinforcement learning framework that enables an LLM to interact with a search engine and receive reward signals that explicitly shape its planning, retrieval, and reasoning behaviors. |
| Outcome: | Empirical results show that Veri-R1 improves joint accuracy by 30% and doubles evidence score, often surpassing larger-scale model counterparts. |
Make LLMs See Like Investigators, Not Just Think More: The Role of Structured Analysis in Investigative Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Criminal investigators and intelligence analysts have developed structured analytic techniques to evaluate competing hypotheses under incomplete information. |
| Approach: | They focus on the task of analyzing evidence from complex narratives and identifying the perpetrator among suspects using the MuSR murder mystery benchmark. |
| Outcome: | The PRISM framework outperforms general-purpose strategies across all models, with its effectiveness manifesting regardless of model scale. |
Decoding Knowledge Attribution in Mixture-of-Experts: A Framework of Basic-Refinement Collaboration and Efficiency Analysis (2025.acl-long)
Copied to clipboard
| Challenge: | Existing attribution methods for dense models fail to capture dynamic routing-expert interactions in sparse MoE architectures. |
| Approach: | They propose to analyze sparse MoE architectures against dense models to capture dynamic routing-expert interactions. |
| Outcome: | The proposed algorithm shows that sparse models achieve higher efficiency per layer . it also shows that deep Qwen-MoE mitigates expert failures while minimizing complexity . |
Prompting Explicit and Implicit Knowledge for Multi-hop Question Answering Based on Human Reading Process (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies have not explored the link between PLMs’ pre-training-based knowledge and input passages. |
| Approach: | They propose a framework that uses prompts to connect explicit and implicit knowledge to elicit type-specific reasoning via prompts, a form of implicit knowledge. |
| Outcome: | The proposed model performs comparable to the state-of-the-art on HotpotQA. |
EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention (2026.acl-long)
Copied to clipboard
Yifan Zhang, Chen Huang, Yueke Zhang, Jiahao Zhang, Toby Jia-Jun Li, Collin McMillan, Kevin Leach, Yu Huang
| Challenge: | Code Language Models learn attention based on statistical input-output token correlations. |
| Approach: | They propose a model-agnostic technique to align CodeLLM attention with human visual attention without architectural changes. |
| Outcome: | The proposed model outperforms baselines in three languages, with gains of over 30 CodeBLEU points in translation and up to 22 BERTScore points in summarization. |
PVTNL: Prompting Vision Transformers with Natural Language for Generalizable Person Re-identification (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Domain generalization person re-identification (DG-ReID) aims to train models on source domains and generalize to unseen target domains. |
| Approach: | They propose a framework to generalize person re-identification using a vision-language model . body-part cues are used to segment images into semantically coherent regions . |
| Outcome: | The proposed framework can generalize to unseen domains and generalize semantics to people . it leverages the pre-trained vision-language model BLIP to extract aligned visual and textual embeddings. |
VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval (2026.acl-long)
Copied to clipboard
| Challenge: | Text-to-image retrieval is challenging because of cross-modal embeddings are bags of concepts, underrepresenting structured visual relationships. |
| Approach: | They propose a retrieval paradigm that embeds textual queries into the image modality via T2I generation and performs retrieval within the image mode to bypass weaknesses of cross-modal retrievers in recognizing subtle visual-spatial features. |
| Outcome: | The proposed retrieval paradigm outperforms previous approaches in visual-spatial retrieval benchmarks. |
When Seeing Is not Enough: Revealing the Limits of Active Reasoning in MLLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Existing evaluations of multimodal large language models focus on passive inference, where seeing is not enough. |
| Approach: | They propose a benchmark to evaluate active reasoning in multimodal large language models . they propose to acquire missing evidence and iteratively refine decisions under incomplete information . |
| Outcome: | The proposed model performs better on active reasoning than on passive inference settings. |
FairGen: Controlling Sensitive Attributes for Fair Generations in Diffusion Models via Adaptive Latent Guidance (2025.emnlp-main)
Copied to clipboard
Mintong Kang, Vinayshekhar Bannihatti Kumar, Shamik Roy, Abhishek Kumar, Sopan Khosla, Balakrishnan Murali Narayanaswamy, Rashmi Gangadharaiah
| Challenge: | Text-to-image diffusion models often exhibit generation biases toward specific demographic groups, raising ethical concerns and limiting their adoption. |
| Approach: | They propose an adaptive latent guidance mechanism which controls the generation distribution during inference by dynamically adjusting the diffusion process to enforce specific attributes. |
| Outcome: | The proposed model outperforms existing models on HBE and Stable Bias datasets and achieves substantial bias reduction. |
RoCoFT: Efficient Finetuning of Large Language Models with Row-Column Updates (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning large language models use full finetunation, but this is impractical as language models continue to scale up. |
| Approach: | They propose a parameter-efficient fine-tuning method for large language models based on updating only a few rows and columns of the weight matrices in transformers. |
| Outcome: | The proposed method gives comparable or better accuracies than state-of-the-art methods while being more memory and computation-efficient. |
Inceptive Transformers: Enhancing Contextual Representations through Multi-Scale Feature Learning Across Domains and Languages (2025.emnlp-main)
Copied to clipboard
| Challenge: | Encoder transformer models compress information from all tokens into a single [CLS] token to represent global context. |
| Approach: | They propose a 1-D convolution module that augments token representations with multi-scale local features to improve performance. |
| Outcome: | Experiments on five diverse tasks show that the proposed framework outperforms baseline models by 1% to 14% while maintaining efficiency. |
Too Helpful, Too Harmless, Too Honest or Just Right? (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods optimize for individual alignment dimensions in isolation, leading to trade-offs and inconsistent behavior. |
| Approach: | They propose a modular alignment framework that integrates a Mixture of Calibrated Experts (MoCaE) within the Transformer architecture. |
| Outcome: | The proposed framework outperforms baselines on three alignment benchmarks, achieving 32.5% win rate, 33.9% safety score, and 28.4% truthfulness. |
Neuron-Aware Active Few-Shot Learning for LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods rely on output-level signals for sample identification, such as predictive entropy or semantic similarities with test-time data, which overlook models’ internal dynamics which could pinpoint specific knowledge gaps. |
| Approach: | They propose a Neuron-Aware Active Few-Shot Learning framework that shifts the selection paradigm from output-level proxies to models’ internal dynamics. |
| Outcome: | Experiments on three datasets show that NeuFS outperforms existing AFSL baselines. |
Glance-or-Gaze: Incentivizing LMMs to Adaptively Focus Search via Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing search-augmented approaches rely on indiscriminate whole-image retrieval and lack deep iterative reflection, limiting their effectiveness on complex visual queries. |
| Approach: | They propose a fully autonomous framework that shifts from passive perception to active visual planning and introduces a Selective Gaze mechanism that dynamically chooses whether to glance at global context or gaze into high-value regions. |
| Outcome: | Experiments across six benchmarks demonstrate state-of-the-art performance. |
NaviMaster: Learning a Unified Policy for GUI and Embodied Navigation Tasks (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in Graphical User Interface (GUI) and embodied navigation have driven progress, yet these domains have largely evolved in isolation, with disparate datasets and training paradigms. |
| Approach: | They propose a visual-target trajectory collection pipeline that generates trajectories for GUI and embodied tasks using a single formulation. |
| Outcome: | The proposed agent outperforms state-of-the-art agents in GUI navigation, spatial affordance prediction, and embodied navigation. |
Prompt Optimization for Relation Extraction using Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing prompt-based methods rely heavily on large-scale annotated datasets limiting their applicability in domain-specific and low-resource scenarios. |
| Approach: | They propose a reinforcement learning-based automated prompt optimization framework for domain relation extraction that optimizes prompt quality through interaction with a black-box LLM. |
| Outcome: | The proposed framework outperforms existing prompt-based methods and supervised baselines on multiple extraction datasets across medical, financial, legal, and news domains. |
REVEALER: Reinforcement-Guided Visual Reasoning for Element-Level Text-Image Alignment Evaluation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for text-to-image alignment evaluation rely on coarse-grained metrics or static Question Answering pipelines that lack fine-grounded interpretability and struggle to reflect human preferences. |
| Approach: | They propose a reinforcement-guided visual reasoning framework for element-level text-to-image alignment evaluation. |
| Outcome: | The proposed framework achieves state-of-the-art results on four benchmarks and surpasses the strong proprietary Gemini 3 Pro and Training-based baselines. |