NATURAL LANGUAGE TASKS

Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts (2025.findings-acl)

Challenge:	Existing tools for learning the embeddings of words and entities from Wikipedia are not yet available.
Approach:	They propose a Python-based tool for learning Wikipedia embeddings from Wikipedia . they use a Wikipedia dump file as an argument to issue a single command .
Outcome:	The proposed tool achieves state-of-the-art results on the KORE entity relatedness dataset and competitive results on benchmark datasets.

Copied to clipboard

Zeliang Zhang, Xiaodong Liu, Hao Cheng, Chenliang Xu, Jianfeng Gao

Challenge:	Large Language Models (LLMs) have outstanding performance by learning a large number of model parameters on large amounts of data.
Approach:	They propose a method of grouping and pruning similar experts to improve the model’s parameter efficiency by a range of natural language tasks.
Outcome:	The proposed method outperforms other model pruning methods on a range of natural language tasks.

LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models (2024.eacl-long)

Copied to clipboard

Adian Liusie, Potsawee Manakul, Mark Gales

Unsupervised Question Answering for Fact-Checking (D19-66)

Challenge:	Recent advances in large language models have enabled impressive zero-shot capabilities across various natural language tasks.
Approach:	They propose two ways to exploit the emergent abilities of large language models for NLG assessment.
Outcome:	The proposed methods improve performance and positional biases in comparisons between candidates.

Copied to clipboard

Mayank Jobanputra

Analyzing Biases to Spurious Correlations in Text Classification Tasks (2022.aacl-short)

Challenge:	Recent Deep Learning (DL) models have achieved human-level accuracy on natural language tasks such as question-answering, natural language inference, and textual entailment.
Approach:	They propose an unsupervised question-answering based approach for a similar task, fact-checking.
Outcome:	The proposed approach achieves label accuracy of 80.2% on the development set and 80.25% on the test set.

Copied to clipboard

Adian Liusie, Vatsal Raina, Vyas Raina, Mark Gales

Information Retrieval

Challenge:	Often these systems exceed human performance, but there is a caveat: standard benchmarks often assume that training and evaluation data are drawn independently and identically from the same underlying distribution.
Approach:	They propose to exploit spurious correlations in training data to exploit these correlations . they show that even when only ‘stop’ words are available, it is possible to predict the class significantly better than random.
Outcome:	The proposed model can predict class significantly better when only ‘stop’ words are available at the input stage, but can degrade the ability of the system to generalize well to out-of-domain data.

LETI: Learning to Generate from Textual Interactions (2024.findings-naacl)

Copied to clipboard

Xingyao Wang, Hao Peng, Reyhaneh Jabbarvand, Heng Ji

Model-agnostic Methods for Text Classification with Inherent Noise (2020.coling-industry)

Challenge:	Existing techniques fine-tune on input-output pairs or with numerical rewards that gauge the output quality are not effective.
Approach:	They propose to fine-tune pre-trained language models with binary labels and a Python interpreter to get textual feedback from the inputs.
Outcome:	The proposed model outperforms the base model on unseen problems and achieves comparable or better performance on humanEval.

Copied to clipboard

Kshitij Tayal, Rahul Ghosh, Vipin Kumar

Information Extraction & Text Mining

Challenge:	Text classification is a fundamental problem in natural language processing, but its performance relies on high-quality annotations.
Approach:	They propose to use model-agnostic methods to handle inherent noise in large scale text classification that can be easily incorporated into existing machine learning workflows with minimal interruption.
Outcome:	The proposed method outperforms baselines by up to 10% in classification accuracy while requiring no network modifications.

Neural Token Representations and Negation and Speculation Scope Detection in Biomedical and General Domain Text (D19-62)

Copied to clipboard

Elena Sergeeva, Henghui Zhu, Amir Tahmasebi, Peter Szolovits

Representation Learning

Challenge:	Existing evidence for improved performance on natural language tasks is unclear to what degree the learned token representations capture and encode highlevel morphological/syntactic knowledge about the usage of a given token in a sentence.
Approach:	They propose to use context-aware token representations to capture morphological/syntactic knowledge about the usage of a given word/token in a sentence.
Outcome:	The proposed representations capture and encode high-level morphological/syntactic knowledge about the usage of a given token in a sentence.

A Robust Semantics-based Watermark for Large Language Model against Paraphrasing (2024.findings-naacl)

Copied to clipboard

Jie Ren, Han Xu, Yiding Liu, Yingqian Cui, Shuaiqiang Wang, Dawei Yin, Jiliang Tang

Can a Large Language Model Keep My Secrets? A Study on LLM-Controlled Agents (2025.acl-srw)

Challenge:	Existing methods to detect LLM-generated content use simple hashes of precedent tokens to partition vocabulary.
Approach:	They propose a semantics-based watermark framework to enhance the robustness against paraphrase.
Outcome:	The proposed framework is robust under different paraphrases and the semantic meaning of the sentences will be likely preserved under paraphrase.

Copied to clipboard

Niklas Hemken, Sai Koneru, Florian Jacob, Hannes Hartenstein, Jan Niehues

RadLing: Towards Efficient Radiology Report Understanding (2023.acl-industry)

Challenge:	Using large language models, agents can assist with natural language tasks when given access to confidential data.
Approach:	They created a synthetic dataset consisting of confidentiality-aware planning and deduction tasks in organizational access control.
Outcome:	The proposed model can perform tasks similar to humans when given access to confidential data.

Copied to clipboard

Rikhiya Ghosh, Oladimeji Farri, Sanjeev Kumar Karn, Manuela Danu, Ramya Vunikili, Larisa Micu

Measuring Social Biases in Masked Language Models by Proxy of Prediction Quality (2025.acl-long)

Challenge:	a few pre-trained language models have produced comparable results in fine-tuning tasks in radiology domain.
Approach:	They propose a continuously pretrained language model with ELECTRA-small architecture that can compete with state-of-the-art results in radiology domain.
Outcome:	The proposed model can compete with state-of-the-art models for fine tuning tasks in radiology domain.

Copied to clipboard

Rahul Zalkikar, Kanchan Chandra

Unified Multimodal Interleaved Document Representation for Retrieval (2026.findings-eacl)

Challenge:	Innovative transformer-based language models produce contextually-aware token embeddings, but have been shown to encode unwanted biases for downstream applications.
Approach:	They extend previous work by evaluating social biases introduced after retraining an MLM under the masked language modeling objective and propose proxy functions within an iterative masking experiment to measure the quality of transformer models’ predictions.
Outcome:	The proposed proxy functions within an iterative masking experiment show that all transformer models encode concerning social biases.

Copied to clipboard

Jaewoo Lee, Joonho Ko, Jinheon Baek, Soyeong Jeong, Sung Ju Hwang

CoSe-Co: Text Conditioned Generative CommonSense Contextualizer (2022.naacl-main)

Challenge:	Existing methods focus on textual content, ignoring the fact that documents can contain multiple modalities.
Approach:	They propose a method that holistically embeds documents interleaved with multiple modalities . they use vision-language models that combine text, images, and tables into a unified format .
Outcome:	The proposed method outperforms baselines on textual and multimodal queries.

Copied to clipboard

Rachit Bansal, Milan Aggarwal, Sumit Bhatia, Jivat Kaur, Balaji Krishnamurthy

Robust Multilingual Part-of-Speech Tagging via Adversarial Training (N18-1)

Challenge:	Pre-trained language models (PTLMs) have been shown to perform well on natural language tasks.
Approach:	They propose a commonsense contextualizer conditioned on sentences as input to make it generically usable in tasks involving natural language text.
Outcome:	The proposed model improves on existing methods on CSQA, ARC, QASC and OBQA datasets.

Copied to clipboard

Michihiro Yasunaga, Jungo Kasai, Dragomir Radev

Syntactic Text Processing

Challenge:	Adversarial training (AT) is a powerful regularization method for neural networks, aiming to achieve robustness to input perturbations.
Approach:	They propose and analyze a neural POS tagging model that exploits adversarial training by training on unmodified and adversarials.
Outcome:	The proposed model improves overall tagging accuracy and prevents over-fitting in low resource languages and boosts tabbing accuracy for rare / unseen words.

Confidence-Driven Multi-Scale Model Selection for Cost-Efficient Inference (2026.findings-eacl)

Copied to clipboard

Bo-Wei Chen, Chung-Chi Chen, An-Zi Yen

Green & Sustainable NLP

Challenge:	Large Language Models (LLMs) have revolutionized inference across diverse natural language tasks, with larger models performing better but at higher computational costs.
Approach:	They propose a confidence-driven strategy that dynamically selects the most suitable model based on confidence estimates.
Outcome:	The proposed approach reduces token usage by approximately 60% and improves cost efficiency on the Massive Multitask Language Understanding (MMLU) benchmark.

Language Models of Code are Few-Shot Commonsense Learners (2022.emnlp-main)

Copied to clipboard

Aman Madaan, Shuyan Zhou, Uri Alon, Yiming Yang, Graham Neubig

CoMM: Collaborative Multi-Agent, Multi-Reasoning-Path Prompting for Complex Problem Solving (2024.findings-naacl)

Challenge:	Existing approaches to generate graphs using pre-trained language models hinder their ability to generate them correctly.
Approach:	They propose to frame structured commonsense reasoning tasks as code generation tasks instead of serializing the output graph as a flat list of nodes and edges.
Outcome:	The proposed approach outperforms natural-language LMs in three natural language tasks even when the downstream task does not involve source code at all.

Copied to clipboard

Pei Chen, Shuai Zhang, Boran Han

Low-Resource NLP

Challenge:	Large Language Models (LLMs) have shown great ability in solving traditional natural language tasks and elementary reasoning tasks with appropriate prompting techniques.
Approach:	They propose a collaborative multi-agent, multi-reasoning-path prompting framework that prompts LLMs to play different roles in a problem-solving team and encourages different role-play agents to collaboratively solve the target task.
Outcome:	The proposed framework is applied to two college-level science problems over competitive baselines.

Cross-lingual Visual Pre-training for Multimodal Machine Translation (2021.eacl-main)

Copied to clipboard

Ozan Caglayan, Menekse Kuyu, Mustafa Sercan Amac, Pranava Madhyastha, Erkut Erdem, Aykut Erdem, Lucia Specia

Multilinguality

Challenge:	Pre-trained language models have been shown to improve performance in many natural language tasks.
Approach:	They propose to combine cross-lingual and visual pre-training to learn visually-grounded cross-linguistic representations using masked region classification and three-way parallel vision & language corpora.
Outcome:	The proposed models obtain state-of-the-art performance when fine-tuned for multimodal machine translation.

SKILL: Structured Knowledge Infusion for Large Language Models (2022.naacl-main)

Copied to clipboard

Fedor Moiseev, Zhe Dong, Enrique Alfonseca, Martin Jaggi

Cooperative Learning of Disjoint Syntax and Semantics (N19-1)

Challenge:	Large language models (LLMs) have demonstrated human-level performance on a vast spectrum of natural language tasks.
Approach:	They propose a method to infuse structured knowledge into large language models by directly training T5 models on factual triples of knowledge graphs (KGs).
Outcome:	The proposed method outperforms baseline models on FreebaseQA and WikiHop, as well as the Wikidata-answerable subset of TriviaQA and NaturalQuestions.

Copied to clipboard

Serhii Havrylov, Germán Kruszewski, Armand Joulin

Syntactic Text Processing

Challenge:	Existing models that learn to jointly infer an expression’s syntactic structure and its semantics fail to learn the correct parsing strategy on mathematical expressions generated from a simple context-free grammar.
Approach:	They propose a recursive model that learns to jointly infer an expression’s syntactic structure and its semantics without requiring a formal supervision.
Outcome:	The proposed model performs competitively on several natural language tasks, such as Natural Language Inference and Sentiment Analysis.

Toward Inclusive Language Models: Sparsity-Driven Calibration for Systematic and Interpretable Mitigation of Social Biases in LLMs (2025.findings-emnlp)

Copied to clipboard

Prommy Sultana Hossain, Chahat Raj, Ziwei Zhu, Jessica Lin, Emanuela Marasco

StyleDGPT: Stylized Response Generation with Pre-trained Language Models (2020.findings-emnlp)

Challenge:	a new method to mitigate stereotypical bias in large language models is needed . inherent biases from training on vast Internet datasets can amplify harmful stereotypes .
Approach:	They propose a method to identify stereotypical bias in decoder-only transformer models . they apply a localization mechanism that correlates internal activations with a new Context Influence score .
Outcome:	The proposed method reduces stereotypical biases on BBQ, StereoSet, and CrowS-Pairs while improving reasoning performance on MMLU by 10%.

Copied to clipboard

Ze Yang, Wei Wu, Can Xu, Xinnian Liang, Jiaqi Bai, Liran Wang, Wei Wang, Zhoujun Li

Text Generation

Challenge:	Existing methods for generating responses following a desired style are lacking of parallel data for training.
Approach:	They propose a KL loss and a style classifier to fine-tune response generation . they show that their model can significantly outperform state-of-the-art methods .
Outcome:	The proposed model outperforms state-of-the-art models in style consistency and contextual coherence with two public datasets.

Generalized Embedding Models for Industry 4.0 Applications (2025.emnlp-industry)

Copied to clipboard

Christodoulos Constantinides, Shuxin Lin, Dhaval C Patel

Scaling Sentence Embeddings with Large Language Models (2024.findings-emnlp)

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.

Copied to clipboard

Ting Jiang, Shaohan Huang, Zhongzhi Luan, Deqing Wang, Fuzhen Zhuang

Understanding HTML with Large Language Models (2023.findings-emnlp)

Challenge:	Current methods based on contrastive learning have generated high-quality sentence embeddings.
Approach:	They propose a method to enhance LLM performance on sentence embeddings with a one-word limitation.
Outcome:	The proposed method outperforms contrastive learning methods on sentence embeddings without fine-tuning and with fine-untun.

Copied to clipboard

Izzeddin Gur, Ofir Nachum, Yingjie Miao, Mustafa Safdari, Austin Huang, Aakanksha Chowdhery, Sharan Narang, Noah Fiedel, Aleksandra Faust

Filling the Image Information Gap for VQA: Prompting Large Language Models to Proactively Ask Questions (2023.findings-emnlp)

Challenge:	Large language models have shown exceptional performance on a variety of natural language tasks, but their capabilities for HTML understanding have not been fully explored.
Approach:	They propose to use HTML understanding models to parse HTML and perform HTML navigation tasks with a large-scale HTML dataset.
Outcome:	The proposed models perform 50% more tasks with 192x less data than the previous best supervised model.

Copied to clipboard

Ziyue Wang, Chi Chen, Peng Li, Yang Liu

An End-to-End Submodular Framework for Data-Efficient In-Context Learning (2024.findings-naacl)

Challenge:	Large Language Models (LLMs) demonstrate impressive reasoning ability and the maintenance of world knowledge in natural language tasks.
Approach:	They propose a framework that enables LLMs to ask relevant questions to uncover more details in the image, along with filters for refining the generated information.
Outcome:	The proposed framework boosts the performance of baseline methods by 2.15% on OK-VQA and achieves consistent improvements across different LLMs.

Copied to clipboard

Lilly Kumari, Shengjie Wang, Arnav Das, Tianyi Zhou, Jeff Bilmes

GEM: A General Evaluation Benchmark for Multimodal Tasks (2021.findings-acl)

Challenge:	Recent advances in natural language tasks leverage the emergent In-Context Learning ability of pretrained Large Language Models (LLMs).
Approach:	They propose a framework for exemplar selection for in-context learning that uses a pool-based active learning approach to select Diverse and informative exemplars from the target tasks’ unlabeled pool.
Outcome:	The proposed framework outperforms existing methods for data annotation and similarity-based methods for test query-specific exemplar retrieval on 7 different NLP datasets and 5 LLMs of varying complexities.

Copied to clipboard

Lin Su, Nan Duan, Edward Cui, Lei Ji, Chenfei Wu, Huaishao Luo, Yongfei Liu, Ming Zhong, Taroon Bharti, Arun Sacheti

LeeBERT: Learned Early Exit for BERT with cross-level optimization (2021.acl-long)

Challenge:	Existing datasets that focus on natural language tasks are not considered as a general evaluation benchmark for multimodal tasks.
Approach:	They present a general evaluation benchmark for multimodal tasks, GEM 1 . they compare it with existing multimodal vision-language datasets .
Outcome:	The proposed model is compared with existing vision-language datasets focusing on natural language tasks . it is the largest vision-linguistic dataset covering image-language tasks and video-language task at the same time .

Copied to clipboard

Wei Zhu

Investigating Efficiently Extending Transformers for Long Input Summarization (2023.emnlp-main)

Challenge:	Pre-trained language models are resource exhaustive and computationally expensive for industrial scenarios.
Approach:	They propose a learning scheme to learn from each other to speed up inference . they ask each exit to learn the weights of different loss terms, instead of learning only from the last layer .
Outcome:	The proposed scheme improves state-of-the-art (SOTA) early exit methods for pre-trained models on the GLUE benchmark.

Copied to clipboard

Jason Phang, Yao Zhao, Peter Liu

Summarization

Challenge:	Large pretrained Transformer models have proven capable at tackling natural language tasks, but handling long sequence inputs still poses a significant challenge.
Approach:	They propose an extension of the PEGASUS model with additional long input pretraining to handle inputs of up to 16K tokens.
Outcome:	The proposed model achieves strong performance on long input summarization tasks comparable with much larger models.

Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling (2025.findings-emnlp)

Copied to clipboard

Yue Zhao, Xiaoyu Wang, Dan Wang, Zhonglin Jiang, Qingqing Gu, Teng Chen, Ningyuan Xi, Jinxian Qu, Yong Chen, Luo Ji

Dialogue Systems & Conversational Agents

Challenge:	a framework for constructing dialogue world models for natural language tasks is currently lacking.
Approach:	They propose a framework that can be used to train a dialogue world model.
Outcome:	The proposed framework can predict future utterances and user beliefs . it can achieve state-of-the-art performance on emotion classification and sentiment identification .

GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization (2022.emnlp-main)

Copied to clipboard

Zhiyuan Zhang, Ruixuan Luo, Qi Su, Xu Sun

Definitions Matter: Guiding GPT for Multi-label Classification (2023.findings-emnlp)

Challenge:	Recent studies show flat minima tend to imply better generalization abilities . however, it has some difficulty implying SAM to some natural language tasks .
Approach:	They propose a flatness-aware minimization algorithm that can be applied to natural language tasks . they propose to use parameter corruptions to explain why flat minima generalize better .
Outcome:	The proposed algorithm can generalize better for flat minima that are robust against corruptions or perturbations.

Copied to clipboard

Youri Peskine, Damir Korenčić, Ivan Grubisic, Paolo Papotti, Raphael Troncy, Paolo Rosso

SuLoRA: Subspace Low-Rank Adaptation for Parameter-Efficient Fine-Tuning (2025.findings-acl)

Challenge:	Recent success of Large Language Models (LLMs) is due to their superior performance on various tasks such as text generation, summarization, question answering, and inductive reasoning.
Approach:	They propose to generate definitions from examples and use them for zero-shot classification and to investigate how an LLM makes use of the definitions.
Outcome:	The proposed method improves the definitions of class labels and improves their understanding of the definition.

Copied to clipboard

Chenhao Ding, Jiangyang Li, SongLin Dong, Xinyuan Gao, Yuhang He, Yihong Gong

Aggregation Artifacts in Subjective Tasks Collapse Large Language Models’ Posteriors (2025.naacl-long)

Challenge:	Existing methods for fine-tuning large language models (LLMs) introduce parameter interference, leading to a gap in generalization performance for specific tasks compared to full fine-uning.
Approach:	They propose a parameter-separated low-rank adapter to account for task differences by decomposing LoRA’s parameter matrix into multiple independent subspaces and assigning them differentially to distinct tasks.
Outcome:	The proposed method outperforms LoRA in trainable parameter efficiency and overall model performance on various NLP tasks.

Copied to clipboard

Georgios Chochlakis, Alexandros Potamianos, Kristina Lerman, Shrikanth Narayanan

Towards Zero-Shot Conditional Summarization with Adaptive Multi-Task Fine-Tuning (2020.findings-emnlp)

Challenge:	In-context Learning (ICL) is the primary method for performing natural language tasks with Large Language Models.
Approach:	They examine whether aggregation is a confounding factor in the modeling of subjective tasks . they find it is possible for minority annotators to better align with LLMs .
Outcome:	The proposed method is based on aggregation of annotations in a dataset with appropriate priors.

Copied to clipboard

Travis Goodwin, Max Savery, Dina Demner-Fushman

RobBERT: a Dutch RoBERTa-based Language Model (2020.findings-emnlp)

Challenge:	Existing methods for automatic summarization are limited to providing general-purpose summaries . ad-hoc nature of the task can cause arbitrary summarizing, causing a problem .
Approach:	They propose to use multi-task fine-tuning to enable conditional summarization on five tasks . they propose to combine two novel "online" or adaptive task-mixing strategies .
Outcome:	The proposed method improves zero-shot conditional summarization quality on five tasks.

Copied to clipboard

Pieter Delobelle, Thomas Winters, Bettina Berendt

Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents (2025.findings-emnlp)

Challenge:	Pre-trained language models have been dominating the field of natural language processing in recent years, and have led to significant performance gains for various complex natural language tasks.
Approach:	They used a robustly optimized BERT approach to train a Dutch language model called RobBERT.
Outcome:	The proposed model outperforms models trained on a single language on dozens of tasks and is available for further downstream NLP applications.

Copied to clipboard

Tianmi Ma, Jiawei Du, Wenxin Huang, Wenjie Wang, Liang Xie, Xian Zhong, Joey Tianyi Zhou

Transformer-based Causal Language Models Perform Clustering (2025.findings-naacl)

Challenge:	Existing approaches to large language models are limited to historical backtesting and static data.
Approach:	a new large-language model is developed to simulate real-time trading in a virtual stock market . the agent trading arena simulates real-world bid-ask interactions and provides real-life trading scenarios .
Outcome:	The Agent Trading Arena simulates real-world market conditions and directly impacts price dynamics.

Copied to clipboard

Xinbo Wu, Lav R. Varshney

Roles and Utilization of Attention Heads in Transformer-based Neural Language Models (2020.acl-main)

Challenge:	Recent studies have shown great improvements in instruction-following capability through additional training for instruction- following tasks.
Approach:	They propose to use a Transformer-based causal language model to study instruction-following capabilities.
Outcome:	The proposed model learns task-specific information by clustering data within its hidden space, with this clustering process evolving dynamically during learning.

Copied to clipboard

Jae-young Jo, Sung-Hyon Myaeng

Recursive Neural Networks with Bottlenecks Diagnose (Non-)Compositionality (2022.findings-emnlp)

Challenge:	Sentence encoders based on transformer architectures have shown promising results on various natural language understanding tasks.
Approach:	They propose a sentence representation method that takes advantage of most influential attention heads.
Outcome:	The proposed method improves performance on the downstream tasks.

Copied to clipboard

Verna Dankers, Ivan Titov

Challenge:	Compositional generalisation is often investigated with artificial languages or highly-structured natural language data.
Approach:	They propose to use recursive neural models with bottlenecks to generalise compositionally for artificial languages.
Outcome:	The proposed model can generalise compositionally for natural language tasks without limiting the transfer of information between nodes.

Embedding Imputation with Grounded Language Information (P19-1)

Copied to clipboard

Ziyi Yang, Chenguang Zhu, Vin Sachidananda, Eric Darve

Representation Learning

Challenge:	Existing approaches to embedding imputation use vector space properties or subword information to learn representations for rare or unseen words.
Approach:	They propose an online method to construct a knowledge graph from grounded information and an algorithm to map from the resulting graph to the space of the pre-trained embeddings.
Outcome:	The proposed method improves on a card-660 task by 11% and 17.8% respectively using GloVe embeddings.

Evaluating Generalization Capability of Language Models across Abductive, Deductive and Inductive Logical Reasoning (2025.coling-main)

Copied to clipboard

Yu Sheng, Wanting Wen, Linjing Li, Daniel Zeng

Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models (2021.acl-long)

Challenge:	Recent research in language models (LMs) have demonstrated remarkable performance on many natural language tasks, yet to what extent LMs possess the capability of generalizing to unseen logical rules remains unclear.
Approach:	They propose to use a dataset to assess the generalization capabilities of LMs on ADI reasoning to assess their generalization abilities.
Outcome:	The proposed dataset shows that LMs perform poorly on ADI reasoning tasks and lacks generalization capabilities.

Copied to clipboard

Tyler Chang, Yifan Xu, Weijian Xu, Zhuowen Tu

SURF: Semantic-level Unsupervised Reward Function for Machine Translation (2022.naacl-main)

Challenge:	Recent work has shown that convolutions have been successful in natural language learning.
Approach:	They propose a convolutional approach to construct relative position embeddings in self-attention layers and propose 'compact attention' they propose multiple ways to integrate convolutions into Transformer self- attention.
Outcome:	The proposed composite attention improves performance on multiple downstream tasks, replacing absolute position embeddings, and is more expressive than convolutions in NLP.

Copied to clipboard

Atijit Anuchitanukul, Julia Ive

Machine Translation

Challenge:	Reinforcement Learning (RL) is dependent on the reward formulation due to the intrinsic difficulty of the task in the high-dimensional discrete action space and the sparseness of the standard reward functions.
Approach:	They propose a maximally dense semantic-level unsupervised reward function which mimics human evaluation by considering both sentence fluency and semantic similarity.
Outcome:	The proposed reward outperforms the standard sparse reward by 2% on average for in- and out-of-domain settings.

Enhancing Byzantine-Resistant Aggregations with Client Embedding (2024.findings-emnlp)

Copied to clipboard

Zhiyuan Zhang, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

MPrompt: Exploring Multi-level Prompt Tuning for Machine Reading Comprehension (2023.findings-emnlp)

Challenge:	Existing Byzantine-resistant aggregations detect poisonous clients but cannot defend against backdoor injection by malicious attackers in natural language tasks.
Approach:	They propose to embed client parameters to enhance Byzantine-resistant aggregations.
Outcome:	The proposed client embeddings detect poisonous clients and discard them . the proposed algorithms can't defend against backdoor injection by malicious attackers in natural language tasks .

Copied to clipboard

Guoxin Chen, Yiming Qian, Bowen Wang, Liangzhi Li

Prompt Compression for Large Language Models: A Survey (2025.naacl-long)

Challenge:	Existing soft prompt methods focus on designing the input-independent prompts that steer the model to fit the domain of the new dataset.
Approach:	They propose a multi-level prompt tuning method that utilizes prompts at task-specific, domain-specific and context-specific levels to enhance the comprehension of input semantics.
Outcome:	The proposed method improves on 12 benchmarks on various QA formats and achieves an average improvement of 1.94% over the state-of-the-art methods.

Copied to clipboard

Zongqian Li, Yinhong Liu, Yixuan Su, Nigel Collier

Dual Activation-Weight Sparsity: A Training-Free Framework for Efficient Large Language Model Compression (2026.acl-long)

Challenge:	Current methods for improving LLM efficiency focus on optimizing the model itself, while prompt-centric methods focus on lowering the complexity of input.
Approach:	They propose to use prompt compression to optimize the compression encoder and combine hard and soft prompt methods to improve the efficiency of LLMs.
Outcome:	The proposed methods are categorized into hard prompt methods and soft prompt methods.

Copied to clipboard

Luoyang Sun, Guangyan Li, Cheng Deng, Haifeng Zhang, Jian Zhao, Yongqiang Tang, Wensheng Zhang, Jun Wang

HeSum: a Novel Dataset for Abstractive Text Summarization in Hebrew (2024.findings-acl)

Challenge:	Large language models (LLMs) excel at natural language tasks but face deployment bottlenecks due to computational demands.
Approach:	They propose a training-free framework that exploits activation and weight sparsity . they use a three-tier routing strategy that uses magnitude-based pruning .
Outcome:	Experiments on Llama and Mistral models show that DAWS outperforms activation-weight sparsity pruning methods.

Copied to clipboard

Tzuf Paz-Argaman, Itai Mondshine, Asaf Achi Mordechai, Reut Tsarfaty

Text Generation

Challenge:	Large language models excel in various natural language tasks in English, but their performance in low-resource languages like Hebrew remains unclear.
Approach:	They propose a benchmark dataset specifically designed for Hebrew abstractive text summarization that combines 10,000 article-summary pairs from Hebrew news websites.
Outcome:	The proposed dataset shows that it presents distinct difficulties even for state-of-the-art LLMs.

LaMP: When Large Language Models Meet Personalization (2024.acl-long)

Copied to clipboard

Alireza Salemi, Sheshera Mysore, Michael Bendersky, Hamed Zamani

Cross-Cultural Transfer Learning for Text Classification (D19-1)

Challenge:	Existing benchmarks for personalization in large language models are understudied .
Approach:	They propose a benchmark for training and evaluating language models for producing personalized outputs using a set of seven personalized tasks . they propose two retrieval augmentation approaches that retrieve personal items from each user profile for personalizing language model outputs.
Outcome:	The proposed approach is effective for a set of zero-shot and fine-tuned language models and highlights the impact of personalization in various natural language tasks.

Copied to clipboard

Dor Ringel, Gal Lavee, Ido Guy, Kira Radinsky

Text Classification

Challenge:	a large dataset is required to achieve competitive performance in most natural language tasks. large datasets are expensive, time consuming, and error-prone.
Approach:	They propose a transfer-learning framework that leverages bilingual corpora for natural language text classification using no task-specific data.
Outcome:	The proposed framework can achieve good performance on formality classification and sarcasm detection tasks without any task-specific labeled data.

PiVe: Prompting with Iterative Verification Improving Graph-based Generative Capability of LLMs (2024.findings-acl)

Copied to clipboard

Jiuzhou Han, Nigel Collier, Wray Buntine, Ehsan Shareghi

MAF: Multi-Aspect Feedback for Improving Reasoning in Large Language Models (2023.emnlp-main)

Challenge:	Existing large language models are pre-trained on unstructured data, which leads to poor performance when dealing with structured data.
Approach:	They propose a framework to train large language models to act as verifier modules and to apply iterative corrections offline.
Outcome:	The proposed framework improves graph-based generative capability of large language models by iterating corrective instructions on three graph-derived datasets.

Copied to clipboard

Deepak Nathani, David Wang, Liangming Pan, William Wang

XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs (2024.emnlp-main)

Challenge:	Existing approaches to enhance Language Models fail to address diverse error types . generic feedback is a bottleneck for addressing diverse errors in reasoning chains .
Approach:	They propose an iterative refinement framework that integrates multiple feedback modules . they propose to address errors in reasoning chains by integrating frozen LMs with external tools .
Outcome:	The proposed framework improves performance in Mathematical Reasoning and Logical Entailment by 20% and 18% respectively.

Copied to clipboard

Zichen Chen, Jianda Chen, Ambuj Singh, Misha Sra

Robust Backed-off Estimation of Out-of-Vocabulary Embeddings (2020.findings-emnlp)

Challenge:	Large Language Models (LLMs) have achieved remarkable success in natural language tasks, yet understanding their reasoning processes remains a significant challenge.
Approach:	They propose a dataset that includes 24204 instances where each instance interprets the LLM’s reasoning behavior using knowledge graphs and graph attention networks (GAT).
Outcome:	The proposed explanation framework reduces hallucinations and improves grounded explanation generation in large language models.

Copied to clipboard

Nobukazu Fukuda, Naoki Yoshinaga, Masaru Kitsuregawa

Leveraging Denoised Abstract Meaning Representation for Grammatical Error Correction (2023.findings-acl)

Challenge:	Existing approaches to solving out-of-vocabulary (OOV) words use subwords to represent oov words with a bag of subword.
Approach:	They propose a method to estimate oov word embeddings by referring to pre-trained word embeds for known words with similar surfaces to target ov words.
Outcome:	The proposed method improves word similarity tasks and biomedical tasks even with weak baselines.

Copied to clipboard

Hejing Cao, Dongyan Zhao

Branch-Solve-Merge Improves Large Language Model Evaluation and Generation (2024.naacl-long)

Challenge:	Popular GEC models use large-scale synthetic corpora or use a large number of human-designed rules.
Approach:	They propose a model that incorporates denoised AMR as additional knowledge to get AMRs more reliable.
Outcome:	The proposed model reduces training time by 32% while inference time is comparable.

Copied to clipboard

Swarnadeep Saha, Omer Levy, Asli Celikyilmaz, Mohit Bansal, Jason Weston, Xian Li

Gradient-based Adversarial Attacks against Text Transformers (2021.emnlp-main)

Challenge:	Large Language Models (LLMs) are often used for multi-faceted language generation and evaluation tasks that require complex user constraints or taking into account multiple aspects and criteria.
Approach:	They propose a Large Language Model program that consists of branch, solve, and merge modules that are parameterized with specific prompts to the base LLM.
Outcome:	The proposed program improves the evaluation correctness and consistency for each LLM by up to 26%, reducing length and pairwise position biases by up 50%, and allowing LLaMA-2-chat to match or outperform GPT-4 on most domains.

Copied to clipboard

Chuan Guo, Alexandre Sablayrolles, Hervé Jégou, Douwe Kiela

Structured Pruning of Large Language Models (2020.emnlp-main)

Challenge:	Existing methods for obtaining adversarial examples are difficult with text data.
Approach:	They propose a gradient-based adversarial attack against transformer models that searches for a distribution of adversarials parameterized by a continuous-valued matrix.
Outcome:	The proposed attack outperforms existing methods on a variety of natural language tasks with matching imperceptibility.

Copied to clipboard

Ziheng Wang, Jeremy Wohlwend, Tao Lei

A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations (2021.acl-long)

Challenge:	Recent advances in language modeling have led to remarkable improvements on a variety of tasks.
Approach:	They propose a generic, structured pruning approach by parameterizing each weight matrix and adaptively removing rank-1 components during training.
Outcome:	The proposed method outperforms unstructured pruning and block pruning on language modeling tasks while achieving speedups during training and inference.

Copied to clipboard

Pierre Colombo, Pablo Piantanida, Chloé Clavel

Representation Learning

Challenge:	Existing methods for learning disentangled representations of textual data are difficult to implement and suffer from the degeneracy of other losses in multi-class scenarios.
Approach:	They propose a variational upper bound to the mutual information between an attribute and the latent code of an encoder that controls the approximation error.
Outcome:	The proposed method is superior on fair classification and on textual style transfer tasks.

PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion (2024.findings-acl)

Copied to clipboard

Yiduo Guo, Zekai Zhang, Yaobo Liang, Dongyan Zhao, Nan Duan

Generating Data for Symbolic Language with Large Language Models (2023.emnlp-main)

Challenge:	Recent evaluations of Large Language Models (LLMs) focus on their zero-shot/few-shot capabilities for basic natural language tasks and their ability to translate instructions into tool APIs.
Approach:	They propose a PowerPoint Task Completion benchmark to assess LLMs’ ability to create and edit PPT files based on user instructions.
Outcome:	The proposed system outperforms open-source and closed LLMs with 75.1% accuracy in single-turn dialogue testing but only achieves 6% session accuracy.

Copied to clipboard

Jiacheng Ye, Chengzu Li, Lingpeng Kong, Tao Yu

LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention (2020.emnlp-main)

Challenge:	Large language models (LLMs) bring performance and complexity, but they incur a large computational cost in practice.
Approach:	They propose a task-based model which uses large language models to generate symbolic language data by an informative prompt and agreement-based verifier.
Outcome:	The proposed model can generate symbolic language data with a few human demonstrations and saves a considerable amount of inference effort.

Copied to clipboard

Ikuya Yamada, Akari Asai, Hiroyuki Shindo, Hideaki Takeda, Yuji Matsumoto

PORT: Preference Optimization on Reasoning Traces (2025.naacl-long)

Challenge:	Existing models for entity representations do not capture information in a knowledge base, and cannot represent entities that do not exist in the KB.
Approach:	They propose a pretrained contextualized representation of words and entities based on the bidirectional transformer.
Outcome:	The proposed model achieves impressive empirical performance on a wide range of entity-related tasks.

Copied to clipboard

Salem Lahlou, Abdalgader Abubaker, Hakim Hacid

Soft Contextual Data Augmentation for Neural Machine Translation (P19-1)

Challenge:	Preference optimization methods have been successfully applied to improve the alignment of large language models with human values.
Approach:	They propose to use preference optimization methods to generate rejected answers using weak LLM prompting and digit corruption to improve the mathematical reasoning abilities of language models.
Outcome:	The proposed method leads to increased accuracy on the GSM8K and AQuA-RAT benchmarks without annotations.

Copied to clipboard

Fei Gao, Jinhua Zhu, Lijun Wu, Yingce Xia, Tao Qin, Xueqi Cheng, Wengang Zhou, Tie-Yan Liu

Machine Translation

Challenge:	Existing methods for enhancing training data are limited in natural language tasks due to text characteristics.
Approach:	They propose a data augmentation method that softly augments a randomly chosen word in a sentence by its contextual mixture of multiple related words.
Outcome:	The proposed method outperforms baseline methods on small and large scale machine translation datasets.

Atomic Inference for NLI with Generated Facts as Atoms (2024.emnlp-main)

Copied to clipboard

Joe Stacey, Pasquale Minervini, Haim Dubossarsky, Oana-Maria Camburu, Marek Rei

Evaluating the Quality of a Corpus Annotation Scheme Using Pretrained Language Models (2024.lrec-main)

Challenge:	Existing models that can provide accurate explanations are not interpretable, i.e. they do not reflect the inner workings of the model.
Approach:	They propose to use LLM-generated facts as atoms to make interpretable models that can be used to make accurate predictions for each component part of an input.
Outcome:	The proposed method outperforms existing methods on natural language understanding tasks with a multi-stage fact generation process and a training regime that incorporates the facts.

Copied to clipboard

Furkan Akkurt, Onur Gungor, Büşra Marşan, Tunga Gungor, Balkiz Ozturk Basaran, Arzucan Özgür, Susan Uskudarli

Improving Instruct Models for Free: A Study on Partial Adaptation (2025.emnlp-main)

Challenge:	Pretrained language models and large language models are increasingly used to assist in a variety of natural language processing tasks.
Approach:	They propose to use pretrained language models and large language models to evaluate their quality in natural language processing.
Outcome:	The proposed annotation scheme (2.11) yields sentences with higher success rate than the previous one.

Copied to clipboard

Ozan Irsoy, Pengxiang Cheng, Jennifer L Chen, Daniel Preotiuc-Pietro, Shiyue Zhang, Duccio Pappadopulo

Low-Resource NLP

Challenge:	Instruct models are deemed superior and more usable but can be eroded by instruction tuning . a recent study shows that instruct models are better at following instructions than base models .
Approach:	They scale down the strength of instruction tuning to improve model performance . they show that reducing instruction tuning results in material improvement .
Outcome:	The proposed model improves on a few-shot in-context learning benchmark . but it loses some degree of its in-training ability .

Learning to Plan by Updating Natural Language (2024.findings-emnlp)

Copied to clipboard

Yiduo Guo, Yaobo Liang, Chenfei Wu, Wenshan Wu, Dongyan Zhao, Nan Duan

DS-MHP: Improving Chain-of-Thought through Dynamic Subgraph-Guided Multi-Hop Path (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) have shown remarkable performance in basic natural language tasks.
Approach:	They propose a method that iteratively updates the task plan with new steps and behavioral instructions to guide LLMs to generate the correct solutions step by step.
Outcome:	The proposed method improves performance on five reasoning type tasks and can be directly applied to other LLMs.

Copied to clipboard

Yongqiang Liu, Qiyao Peng, Binrong Liu, Hongtao Liu, XueWei Li, Wenjun Wang

ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness (2023.emnlp-main)

Challenge:	Existing knowledge graph methods lack adaptability in knowledge-intensive tasks with multiple entities and implicit multi-hop relations.
Approach:	They propose a zero-shot framework to enhance LLM reasoning in multi-entity relation tasks.
Outcome:	DS-MHP outperforms baselines and state-of-the-art methods on 12 datasets spanning commonsense, logical, symbolic, and arithmetic reasoning.

Copied to clipboard

Archiki Prasad, Swarnadeep Saha, Xiang Zhou, Mohit Bansal

Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs (2024.emnlp-main)

Challenge:	Existing methods focus on whether the reasoning chain leads to the correct conclusion, but this view may confound reasoning quality with other spurious shortcuts to predict the answer.
Approach:	They propose a framework that evaluates reasoning chains via two key properties: (1) correctness, i.e., each step makes a valid inference based on information contained within the step, preceding steps, and input context, and (2) informativeness, respectively.
Outcome:	The proposed framework evaluates reasoning chains via two key properties: (1) correctness, i.e., each step makes a valid inference based on information contained within the step, preceding steps, and input context, and (2) informativeness, which is helpful towards deriving the generated answer.

Copied to clipboard

Haritz Puerto, Martin Tutek, Somak Aditya, Xiaodan Zhu, Iryna Gurevych

PANDA: Preference Adaptation for Enhancing Domain-Specific Abilities of LLMs (2024.findings-acl)

Challenge:	Recent prompting techniques have improved LLMs’ performance on various reasoning tasks, but there is little understanding of what triggers reasoning abilities in LLM in the inference stage.
Approach:	They propose a method that transforms a natural language problem into code and directly prompts the LLM using the generated code without resorting to external code execution.
Outcome:	The proposed method boosts multiple LLMs by 22.52 percentage points on GPT 3.5, 7.75 on Mixtral, and 16.78 on Mistral.

Copied to clipboard

An Liu, Zonghan Yang, Zhenhe Zhang, Qingyuan Hu, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Yang Liu

Challenge:	Large language models have demonstrated considerable capabilities across various tasks . however, they often fall short of the performance achieved by domain-specific state-of-the-art models .
Approach:	They propose a tuning-free method to augment domain-specific abilities of Large language models . they leverage insights from the response preference of expert models to augment LLMs .
Outcome:	The proposed method outperforms the expert model on 4 ScienceWorld tasks.

How Ambiguous Are the Rationales for Natural Language Reasoning? A Simple Approach to Handling Rationale Uncertainty (2025.coling-main)

Copied to clipboard

Hazel H. Kim

Flexora: Flexible Low-Rank Adaptation for Large Language Models (2025.acl-long)

Challenge:	Language models have made significant progress on complex reasoning tasks, but it is impossible to obtain perfect rationales from models or even from humans.
Approach:	They propose a way to guide models to choose between two different reasoning paths depending on the ambiguity of rationales.
Outcome:	The proposed approach leads to robust performance in adversarial scenarios where rationale quality is inconsistent.

Copied to clipboard

Chenxing Wei, Yao Shu, Ying Tiffany He, Fei Yu

ILLUMINER: Instruction-tuned Large Language Models as Few-shot Intent Classifier and Slot Filler (2024.lrec-main)

Challenge:	Large language models (LLMs) have revolutionized artificial intelligence, but performance on specific tasks is limited by knowledge boundaries.
Approach:	They propose a method that automatically selects the most critical layers for fine-tuning to optimize performance across diverse downstream tasks.
Outcome:	The proposed method outperforms baseline models and natural language tasks.

Copied to clipboard

Paramita Mirza, Viju Sudhi, Soumya Ranjan Sahoo, Sinchana Ramakanth Bhat

IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theory (2025.acl-long)

Challenge:	State-of-the-art intent classification and slot filling methods rely on data-intensive deep learning models . large language models exhibit remarkable zero-shot performance across various natural language tasks.
Approach:	They propose an approach framing IC and SF as language generation tasks for instruction-LLMs with a more efficient SF-prompting method.
Outcome:	The proposed approach outperforms state-of-the-art IC+SF method and in-context learning methods with GPT3.5 (175B).

Copied to clipboard

Wei Song, Zhenya Huang, Cheng Cheng, Weibo Gao, Bihan Xu, GuanHao Zhao, Fei Wang, Runze Wu

Linguistic Theories

Challenge:	Large language models have demonstrated exceptional performance across a wide range of tasks . however, selecting the optimal LLM to respond to a user query often necessitates a delicate balance between performance and cost.
Approach:	They propose a multi-LLM routing framework that efficiently routes user queries to the most suitable LLM.
Outcome:	The proposed framework outperforms baseline methods in terms of effectiveness and interpretability.

AnchorCoT: Anchors Pave the Way for Multi-hop Reasoning (2025.findings-acl)

Copied to clipboard

Tianshi Ming, Xian Wu, Yingying Zhang, Zichuan Fu, Dawei Cheng

Natural Language Interfaces

Challenge:	Large language models (LLMs) have demonstrated potential reasoning capabilities through prompt design, such as the Chain of Thought (CoT).
Approach:	They propose a new reasoning approach that predicts key entities which work as important “anchors” and employs a ranking algorithm to ensure the logical sequence of the predicted answers.
Outcome:	The proposed approach outperforms existing methods in multi-hop question reasoning and provides more accurate reasoning results in multihop question answering tasks.

Finetuning Pretrained Transformers into RNNs (2021.emnlp-main)

Copied to clipboard

Jungo Kasai, Hao Peng, Yizhe Zhang, Dani Yogatama, Gabriel Ilharco, Nikolaos Pappas, Yi Mao, Weizhu Chen, Noah A. Smith

MeetingQA: Extractive Question-Answering on Meeting Transcripts (2023.acl-long)

Challenge:	Efficient transformers outperform recurrent neural networks in natural language generation, but this comes with significant computational cost and memory footprint during generation.
Approach:	They propose to convert a pretrained transformer into its efficient recurrent counterpart, improving efficiency while maintaining accuracy.
Outcome:	The proposed transformers outperform recurrent neural networks in natural language generation but come with significant computational and memory footprint during generation.

Copied to clipboard

Archiki Prasad, Trung Bui, Seunghyun Yoon, Hanieh Deilamsalehy, Franck Dernoncourt, Mohit Bansal

ACCEPT: Adaptive Codebook for Composite and Efficient Prompt Tuning (2024.findings-emnlp)

Challenge:	Meeting transcripts are a promising domain for natural language tasks . lack of annotated data impedes research on other important tasks in this domain .
Approach:	They propose an extractive QA dataset comprising questions asked by meeting participants and corresponding responses.
Outcome:	The proposed dataset extracts questions asked by meeting participants and corresponding responses from transcripts.

Copied to clipboard

Yu-Chen Lin, Wei-Hua Li, Jun-cheng Chen, Chu-Song Chen

Vulnerability of LLMs to Vertically Aligned Text Manipulations (2025.acl-long)

Challenge:	Prompt Tuning has been a popular fine-tuning method for large-scale pretrained language models.
Approach:	They propose a method that allows all soft prompts to share a set of learnable codebook vectors in each subspace, with each prompt differentiated by a number of adaptive weights.
Outcome:	The proposed method achieves superior performance on 17 diverse natural language tasks including natural language understanding (NLU) and question answering (QA) tasks by tuning only 0.3% of parameters of the PLMs.

Copied to clipboard

Zhecheng Li, Yiwei Wang, Bryan Hooi, Yujun Cai, Zhen Xiong, Nanyun Peng, Kai-Wei Chang

Text Classification

Challenge:	Recent research shows that vertical text input significantly degrades the accuracy of large language models (LLMs) in text classification tasks.
Approach:	They investigate the impact of vertical text input on the performance of LLMs . they find that chain of thought reasoning does not help LLM recognize vertical input .
Outcome:	The proposed model can significantly mislead models, posing a risk of bypassing detection in real-world scenarios involving harmful or sensitive information.

Getting The Most Out of Your Training Data: Exploring Unsupervised Tasks for Morphological Inflection (2024.emnlp-main)

Copied to clipboard

Abhishek Purushothama, Adam Wiemerslage, Katharina Wense

Whiteboard-of-Thought: Thinking Step-by-Step Across Modalities (2024.emnlp-main)

Challenge:	Pre-trained transformers have been shown to be effective in many natural language tasks, but are under-explored for character-level sequence to sequence tasks.
Approach:	They propose to use pre-trained transformers for character-level morphological inflection in several languages to train models for unsupervised tasks.
Outcome:	The proposed model outperforms the best two shared tasks on morphological inflection and graphemeto-phoneme conversion benchmarks.

Copied to clipboard

Sachit Menon, Richard Zemel, Carl Vondrick

LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models (2025.findings-acl)

Challenge:	Large language models have shown promising results in arithmetic and symbolic reasoning by expressing intermediate reasoning in text as a chain of thought, yet struggle to extend this capability to answer text queries that are easily solved by visual reasoning.
Approach:	They propose a method to unlock the visual reasoning capabilities of multimodal large language models by using a metaphorical ‘whiteboard’ to draw out reasoning steps as images and return these images back to the model for further processing.
Outcome:	The proposed method shows that it can be used on four difficult tasks that involve visual and spatial reasoning with no demonstrations or specialized modules.

Copied to clipboard

Marcus Tantakoun, Christian Muise, Xiaodan Zhu

Efficient Real-time Refinement of Language Model Text Generation (2025.emnlp-main)

Challenge:	Large Language Models excel in various natural language tasks but struggle with long-horizon planning problems requiring structured reasoning.
Approach:	They propose to integrate large language models into AP and NLP planning frameworks by reviewing current research and identifying critical challenges and future directions.
Outcome:	The proposed frameworks are used to support reliable off-the-shelf AP planners.

Copied to clipboard

Joonho Ko, Jinheon Baek, Sung Ju Hwang

Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Fine-tuning (2025.emnlp-main)

Challenge:	Large language models (LLMs) generate factually incorrect answers, a challenge that remains . Streaming-VR enables on-the-fly verification and correction of tokens as they are generated .
Approach:	They propose a method that enables on-the-fly verification and correction of LLM tokens as they are generated.
Outcome:	The proposed method improves factual accuracy and improves refinement efficiency compared to prior methods.

Copied to clipboard

Junjie Xing, Yeye He, Mengyu Zhou, Haoyu Dong, Shi Han, Dongmei Zhang, Surajit Chaudhuri