Papers by Yi Wang
L2Dir: Integrating L_2-Norm and Directional Alignment for Unsupervised Contrastive Representation Learning in Multimodal Retrieval (2026.acl-long)
Copied to clipboard
Tianyu Zong, Rui Dai, Hongzhu Yi, Yuanxiang Wang, Zhenghao Zhang, Zhenyu Guan, Yujia Yang, Bingkang Shi, Yueyang Ding, Xiangxiang Chu, Kaikui Liu, Jungang Xu
| Challenge: | Existing approaches to multimodal representation learning focus on directional alignment and embedding magnitudes (L2-norm) however, these methods often fail to account for the intrinsic role of L2-norm in the contrastive process. |
| Approach: | They propose a plug-and-play framework that optimizes L2-norm alignment and Directional consistency jointly. |
| Outcome: | The proposed framework achieves consistent and significant performance gains over established baselines across 95 tasks using UniIR and VLM2Vec-V2 frameworks. |
ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances have extended DPO to multimodal scenarios, achieving strong performance. |
| Approach: | They propose to use a sentence-level preference optimization technique to optimize individual sentences for more precise preference optimization without additional models or parameters. |
| Outcome: | Experiments show that Adaptive Sentence-level Preference Optimization significantly improves the alignment of multimodal models. |
CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds (2025.naacl-long)
Copied to clipboard
| Challenge: | Evaluating role-playing capabilities in large language models is challenging due to complex dynamics involved in role-playering. |
| Approach: | They propose a simulation sandbox that generates situational fine-grained character behavior trajectories to enhance LLM performance. |
| Outcome: | The proposed model generates situational fine-grained character behavior trajectories to enhance performance. |
FISTAPruner: Layer-wise Post-training Pruning for Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing pruning methods require inefficient retraining for billion-scale LLMs or rely on heuristicically designed metrics to determine pruning masks, leading to performance degradation. |
| Approach: | They propose a convex optimization model that induces sparsity in large language models by leveraging FISTA. |
| Outcome: | The proposed method can remove 50% of model parameters while retaining 98.6% and 95.6% of the zero-shot performance. |
Slot Attention with Value Normalization for Multi-Domain Dialogue State Tracking (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing dialogue state tracking approaches rely on ontology already defined, where all slots and their possible values are given. |
| Approach: | They propose a new architecture to exploit domain ontology by using Slot Attention and Value Normalization . they supplement the annotation of supporting span for MultiWOZ 2.1, which is the shortest span in utterances to support the labeled value. |
| Outcome: | The proposed architecture exploits ontology and can convert supporting spans to values. |
A Logical Pattern Memory Pre-trained Model for Entailment Tree Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing models overlook the importance of generating intermediate conclusions with logical consistency from the given facts, leading to inaccurate conclusions and undermining the overall credibility of entailment trees. |
| Approach: | They propose a model that utilizes logical entailment patterns to generate coherent explanations by leveraging logical patterns. |
| Outcome: | The proposed model produces more coherent and reasonable conclusions that closely align with the underlying premises. |
Updating Large Language Models’ Memories with Time Constraints (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) can modify their internal memory by incorporating the latest external knowledge, but in practical applications, outdated information may be inputted into LLMs. |
| Approach: | They propose a two-stage decoupling framework that separates the identification and computation of time constraints into a symbolic system and propose 'selective update' of internal memory based on time constraints. |
| Outcome: | The proposed framework improves ChatGPT performance by 60% and improves state-of-the-art LLM GPT-4. |
Disentangled Multi-span Evolutionary Network against Temporal Knowledge Graph Reasoning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for temporal knowledge Graphs neglect internal structural interactions between subgraphs and ignore potential smooth features that do not lead to semantic changes. |
| Approach: | They propose to use a disentangled multi-span evolutionary network to capture local neighbor features while perceiving historical neighbor semantic information. |
| Outcome: | Extensive experiments show that the proposed model outperforms the state-of-the-art in TKG reasoning by 22.7%. |
A Deep Learning-Based System for PharmaCoNER (D19-57)
Copied to clipboard
Ying Xiong, Yedan Shen, Yuanhang Huang, Shuai Chen, Buzhou Tang, Xiaolong Wang, Qingcai Chen, Jun Yan, Yi Zhou
| Challenge: | Efficient access to mentions of clinical entities is very important for using clinical text. |
| Approach: | They developed a pipeline system based on deep learning methods for this shared task . it achieves a micro-average F1-score of 0.9105 on track 1 and a mini-average LSTM score of 0.8391 on track 2 . |
| Outcome: | The proposed system achieves a micro-average F1-score of 0.9105 on track 1 and a mini-average score of 0.8391 on track 2. |
When Evolution Strategy Meets Language Models Tuning (2025.coling-main)
Copied to clipboard
| Challenge: | Autoregressive language models with pretraining often display limited capability in effectively following instructions. |
| Approach: | They propose an on-policy approach to optimize models by harnessing the principle of biological evolution, namely survival of the fittest. |
| Outcome: | The proposed method can achieve superior performance in various tasks and comparable performance in the human alignment task. |
HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference (2025.findings-acl)
Copied to clipboard
Ping Gong, Jiawei Yi, Shengnan Wang, Juncheng Zhang, Zewen Jin, Ouxiang Zhou, Ruibo Liu, Guanbin Xu, Youhui Bai, Bowen Ye, Kun Yuan, Tong Yang, Gong Zhang, Renhai Chen, Feng Wu, Cheng Li
| Challenge: | Existing top-k attention methods struggle to strike a balance between efficiency and accuracy. |
| Approach: | They propose a top-k attention approach that integrates low-overhead techniques into the Top-k Attention process to achieve 7.2 speedup compared to vanilla full attention. |
| Outcome: | The proposed approach achieves 7.2 speedup compared to current top-k attention methods while maintaining model accuracy. |
LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Existing vector steering methods adjust the magnitude of answer vectors, but this creates a fundamental trade-off—reducing jailbreak increases over-refusal. |
| Approach: | They propose a method which aligns va with vb through closed-form weight updates, making the model’s willingness to respond causally dependent on its safety assessment. |
| Outcome: | Experiments on 12 LLMs show that the proposed method achieves 11.45% higher F1 than the best baseline while preserving 95.92% utility. |
ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge (2025.emnlp-main)
Copied to clipboard
Chaoyue He, Xin Zhou, Yi Wu, Xinjia Yu, Yan Zhang, Lei Zhang, Di Wang, Shengfei Lyu, Hong Xu, Wang Xiaoqiao, Wei Liu, Chunyan Miao
| Challenge: | ESGenius is a comprehensive benchmark for evaluating Large Language Models on ESG and sustainability knowledge. |
| Approach: | They introduce ESGenius, a benchmark for evaluating and enhancing ESG proficiency . they use a rigorous two-stage evaluation protocol and a repository of foundational frameworks . |
| Outcome: | ESGenius is a benchmark for evaluating and enhancing the proficiency of Large Language Models (LLMs) in ESG and sustainability-focused question answering. |
LinguaLens: Towards Interpreting Linguistic Mechanisms of Large Language Models via Sparse Auto-Encoder (2025.emnlp-main)
Copied to clipboard
| Challenge: | Prior research on linguistic mechanisms of large language models is limited by coarse granularity, limited analysis scale, and narrow focus. |
| Approach: | They propose a framework for analyzing the linguistic mechanisms of large language models based on Sparse Auto-Encoders. |
| Outcome: | The proposed framework extracts Chinese and English linguistic features across four dimensions . it uncovers intrinsic representations of linguistic knowledge in LLMs and can control outputs . |
Detoxifying Large Language Models via the Diversity of Toxic Samples (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for analyzing and utilizing toxic samples are limited . current methods fail to fully harness their potential . |
| Approach: | They propose a diverse detoxification framework that leverages toxic samples' diversity . they propose MPSG strategy and SC-DPO approach to elicit personalized toxic responses . |
| Outcome: | The proposed framework could be used to optimize large language models for user safety . it incorporates two components: MPSG strategy and SC-DPO approach . |
ATLANTIS: Weak-to-Strong Learning via Importance Sampling (2025.acl-long)
Copied to clipboard
| Challenge: | ATLANTIS is a new technique to improve the performance of large language models. |
| Approach: | They propose a new technique to bridge the gap between the distribution of current datasets and the real-world data distribution by using importance sampling. |
| Outcome: | The proposed technique can bring consistent and significant improvements to models’ performance and can be flexibly transferred among models with different structures. |
WhitenedCSE: Whitening-based Contrastive Learning of Sentence Embeddings (2023.acl-long)
Copied to clipboard
| Challenge: | Extensive experiments on seven semantic textual similarity tasks show our method achieves consistent improvement over the contrastive learning baseline and sets new states of the art. |
| Approach: | They propose a whitening-based contrastive learning method for sentence embedding learning which combines contrastive and shuffled group whitening. |
| Outcome: | The proposed method achieves better alignment and uniformity on seven semantic textual similarity tasks. |
Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models (2026.acl-long)
Copied to clipboard
Yanbin Yin, Kun Zhou, Zhen Wang, Xiangdong Zhang, Yifei Shao, Shibo Hao, Yi Gu, Jieyuan Liu, Somanshu Singla, Tianyang Liu, Eric P. Xing, Zhengzhong Liu, Haojian Jin, Zhiting Hu
| Challenge: | closed-ended question-based benchmarks struggle with saturation as newer models emerge . crowd-sourced leaderboards rely on costly and slow human judges . |
| Approach: | They propose a framework that leverages collective intelligence from all large language models to evaluate each other. |
| Outcome: | a new framework enables a democratic, pairwise evaluation of all large language models . it achieves 97% correlation with human judgements, while significantly reducing the cost. |
PromptPrism: A Linguistically-Inspired Taxonomy for Prompts (2026.findings-eacl)
Copied to clipboard
| Challenge: | PromptPrism is a linguistically-inspired taxonomy that enables prompt analysis across three hierarchical levels. |
| Approach: | They propose a linguistically-inspired taxonomy that enables prompt analysis across three hierarchical levels: functional structure, semantic component, and syntactic pattern. |
| Outcome: | The proposed taxonomy bridges traditional language understanding with modern LLM research . it improves prompt quality and improves model performance across tasks . |
Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Text-to-Image Diffusion models generate high-quality images from textual descriptions, but they often produce images that do not fully align with the input prompts, resulting in semantic inconsistencies. |
| Approach: | They propose an automated repair approach to address catastrophic-neglect in T2I DMs. |
| Outcome: | The proposed model achieves 10.1%-16.3% higher Correct Rate in image generation compared to baselines. |
MS2SL: Multimodal Spoken Data-Driven Continuous Sign Language Production (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing solutions for sign language production are limited due to phonological differences and data scarcity. |
| Approach: | They propose a unified framework for continuous sign language production that generates sign predictions step by step from text or speech embeddings. |
| Outcome: | The proposed model achieves competitive performance on how2sign and PHOENIX14T datasets. |
Enhancing Extractive Question Answering in Multiparty Dialogues with Logical Inference Memory Network (2025.coling-main)
Copied to clipboard
| Challenge: | Existing models for multiparty dialogue question answering (QA) do not consider logical inference relations in multiparty dialogs, leading to suboptimal performance. |
| Approach: | They propose a memory network with logical inference for extractive QA in multiparty dialogues. |
| Outcome: | The proposed model achieves state-of-the-art on Molweni and FriendsQA benchmarks. |
Task-oriented Domain-specific Meta-Embedding for Text Classification (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods neglect domain-specific knowledge and use the same word embedding for each word in all domain-specified datasets. |
| Approach: | They propose a method to incorporate domain-specific and task-oriented information into meta-embeddings by combining pre-trained word embeddings. |
| Outcome: | The proposed method performs well on four text classification datasets and shows that it is compatible with existing methods. |
NEWTON: Are Large Language Models Capable of Physical Reasoning? (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models have been shown to encapsulate syntactic, semantic, word sense, and common-sense knowledge, but limited exploration of their physical reasoning abilities has been conducted. |
| Approach: | They propose a repository and benchmark to evaluate LLMs' physical reasoning skills . they use a pipeline to generate a variant of the benchmark customized to the objects and attributes relevant for their application. |
| Outcome: | The proposed benchmark examines the reasoning capabilities of language models across reasoning tasks. |
Beyond Code: Evaluate Thought Steps for Complex Code Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing efforts to generate code in C++ rely on relatively simple programming problems . large language models (LLMs) pre-trained on numerous code data have opened up new opportunities for code generation. |
| Approach: | They propose a task that evaluates the quality of thought steps and code implementation . they construct a dataset of complex programming problems in C++ . |
| Outcome: | The proposed task evaluates the quality of thought steps and code implementation in a C++ programming language. |
SafetyQuizzer: Timely and Dynamic Evaluation on the Safety of LLMs (2025.naacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have been used to evaluate the safety of their users . however, evaluation questions in current benchmarks are too straightforward and difficult to update with practical relevance due to their lack of correlation with real-world events. |
| Approach: | They propose a question-generation framework to evaluate the safety of LLMs in the Chinese context. |
| Outcome: | The proposed framework reduces decline rate while maintaining similar attack success rate. |
DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing safety mechanisms for Large Language Models (LLMs) are inadequate to protect against jailbreak attacks, resulting in performance degradation on general tasks. |
| Approach: | They propose a method that directly updates a minimal set of relevant parameters to neutralize harmful behaviors while preserving the model’s utility. |
| Outcome: | The proposed model outperforms baseline methods in mitigating jailbreak attacks while preserving the model’s utility. |
PLATO-Ad: A Unified Advertisement Text Generation Framework with Multi-Task Prompt Learning (2022.emnlp-industry)
Copied to clipboard
Zeyang Lei, Chao Zhang, Xinchao Xu, Wenquan Wu, Zheng-yu Niu, Hua Wu, Haifeng Wang, Yi Yang, Shuanglong Li
| Challenge: | Online advertisement text generation models have achieved remarkable success in generating high-quality text ads, but some challenges remain, such as low-resource scenarios and training efficiency for multiple ad tasks. |
| Approach: | They propose a unified text ad generation framework with multi-task prompt learning to tackle low-resource ade generation problem and a multi-step prompt learning mechanism to efficiently solve multiple aed generation tasks. |
| Outcome: | The proposed framework outperforms the state-of-the-art on offline and online metrics. |
Generalized Intent Discovery: Learning from Open World Dialogue System (2022.coling-1)
Copied to clipboard
| Challenge: | Existing intent classification models rely on a pre-defined intent set and supervised labels, which is limited in some practical scenarios. |
| Approach: | They propose to extend an IND intent classifier to an open-world intent set including IND and OOD intents. |
| Outcome: | The proposed task can classify IND and OOD intents while discovering new unlabeled OOD types incrementally. |
Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives (P19-1)
Copied to clipboard
Yi Tay, Shuohang Wang, Anh Tuan Luu, Jie Fu, Minh C. Phan, Xingdi Yuan, Jinfeng Rao, Siu Cheung Hui, Aston Zhang
| Challenge: | Using a pointer-generator framework for reading/sampling over large documents, we propose a framework for learning over long narratives where documents easily span over thousands of tokens. |
| Approach: | They propose a curriculum learning (CL) based pointer-generator framework for reading/sampling over large documents, enabling diverse training of the neural model based on the notion of alternating contextual difficulty. |
| Outcome: | The proposed framework improves on the NarrativeQA reading comprehension benchmark and reaches state-of-the-art performance. |
Reasoning with Language Model is Planning with World Model (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown remarkable reasoning capabilities, particularly with Chain-of-Thought-style prompts. |
| Approach: | They propose a framework that repurposes the LLM as both a world model and a reasoning agent and incorporates a principled planning algorithm (based on Monte Carlo Tree Search) |
| Outcome: | The proposed framework repurposes the LLM as both a world model and a reasoning agent and incorporates a principled planning algorithm (based on Monte Carlo Tree Search) it achieves optimum balance between exploration and exploitation, while achieving high-reward reasoning paths efficiently. |
DocMMIR: A Framework for Document Multi-modal Information Retrieval (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing multi-modal information retrieval models lack a comprehensive exploration of document-level retrieval . existing models suffer from the absence of cross-domain datasets at this granularity. |
| Approach: | They propose a multi-modal document retrieval framework to unify diverse document formats and domains with a comprehensive retrieval scenario. |
| Outcome: | The proposed framework improves document retrieval performance on a large multimodal dataset. |
Interpreting Twitter User Geolocation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for identifying user geolocation suffer from a lack of interpretability on the corresponding results. |
| Approach: | They adopt influence functions to interpret the behavior of GNN-based models by identifying the importance of training users when predicting locations. |
| Outcome: | The proposed method provides meaningful explanations on prediction results and also uncovers the so-called "black-box" GNN-based models by investigating the effect of individual nodes. |
Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy (2026.acl-long)
Copied to clipboard
| Challenge: | Existing RAG methods focus on external retrieval, while ignoring the rich content of the model. |
| Approach: | They propose a framework that enhances explicit synergy over parametric and retrieved knowledge by integrating external retrieval components into the input context of the LLMs. |
| Outcome: | The proposed framework enhances explicit synergy over parametric and retrieved knowledge. |
Confusionset-guided Pointer Networks for Chinese Spelling Check (P19-1)
Copied to clipboard
| Challenge: | Existing methods to detect and fix errors in Chinese are limited due to context. |
| Approach: | They propose a Confusionset-guided pointer network for Chinese Spell Check task . they propose to use off-the-shelf confusionset to guide character generation . |
| Outcome: | The proposed model outperforms all competitor models on three human-annotated datasets. |
Multi-Attribute Controlled Text Generation with Contrastive-Generator and External-Discriminator (2022.coling-1)
Copied to clipboard
| Challenge: | Existing studies on controlled text generation focus on single-attribute control, but in practical applications, they lack controllability. |
| Approach: | They propose a framework for multi-attribute controlled text generation that can effectively generate texts with more attributes. |
| Outcome: | The proposed framework achieves remarkable controllability while keeping the text fluent and diverse. |
Evaluating Fairness in Large Vision-Language Models Across Diverse Demographic Attributes and Prompts (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large vision-language models have demonstrated strong capabilities in open-world visual understanding, but it is not clear how they address demographic biases in real life. |
| Approach: | They propose a method to assess visual fairness in LVLMs by question-answering/classification tasks. |
| Outcome: | The proposed approach improves transparency and offers a scalable solution for fairness mitigation. |
Representation Potentials of Foundation Models for Multimodal Alignment: A Survey (2025.emnlp-main)
Copied to clipboard
| Challenge: | foundation models learn highly transferable representations through large-scale pretraining on diverse data. |
| Approach: | They examine the representation potentials of foundation models by examining their latent capacity to capture task-specific information within a single modality while providing a transferable basis for alignment and unification across modalities. |
| Outcome: | The foundation models exhibit remarkable similarities across architectures and modalities, the authors show . the models can capture task-specific information within a single modality while providing a transferable basis for alignment and unification across modality. |
Rethinking Multi-Modal Alignment in Multi-Choice VideoQA from Feature and Sample Perspectives (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to VideoQA focus on utilizing frame- or object-level visual representations, but they neglect visual-language interactions. |
| Approach: | They propose to break down video into trajectories and first leverage trajectory feature in VideoQA to enhance alignment between two modalities. |
| Outcome: | The proposed method outperforms all the state-of-the-art models on the NExT-QA benchmark. |
Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models (2025.acl-long)
Copied to clipboard
| Challenge: | Sticky tokens, when repeatedly inserted into sentences, pull sentence similarity toward a certain value, disrupting the normal distribution of embedding distances and degrading downstream performance. |
| Approach: | They propose a method to detect “sticky tokens” by sentence and token filtering and apply it to 40 checkpoints across 14 model families. |
| Outcome: | The proposed method detects 868 sticky tokens across 14 models and shows that their presence does not correlate with model size or vocabulary size. |
NewsClaims: A New Benchmark for Claim Detection from News with Attribute Knowledge (2022.emnlp-main)
Copied to clipboard
Revanth Gangi Reddy, Sai Chetan Chinthakindi, Zhenhailong Wang, Yi Fung, Kathryn Conger, Ahmed ELsayed, Martha Palmer, Preslav Nakov, Eduard Hovy, Kevin Small, Heng Ji
| Challenge: | Current claims detection methods focus on sentence analysis, ignoring other attributes . a key element of identifying misinformation is detecting the claims and the arguments that have been presented. |
| Approach: | They propose a benchmark for attribute-aware claim detection in the news domain . they extend the problem to include extraction of additional attributes related to each claim . |
| Outcome: | The proposed system performs well on the test, but human performance is still poor. |
Target-Sensitive Memory Networks for Aspect Sentiment Classification (P18-1)
Copied to clipboard
| Challenge: | Aspect sentiment classification (ASC) is a fundamental task in sentiment analysis. |
| Approach: | They propose to use memory networks to deal with ASC using aspect and sentence terms and use them to classify the sentiment polarity. |
| Outcome: | The proposed techniques can be implemented in a variety of contexts and their effectiveness is evaluated. |
PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing reward models evaluate empathy from a single perspective, overlooking bidirectional interaction nature of empathy. |
| Approach: | They propose a reward model that evaluates empathy from a single perspective . they propose PERM to integrate a bystander perspective to monitor overall interaction quality . |
| Outcome: | a new reward model outperforms state-of-the-art models on an emotional intelligence benchmark and an industrial daily conversation dataset. |
Understanding How Value Neurons Shape the Generation of Specified Values in LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Current approaches to interpret value representations are limited by superficial judgments over mechanistic analysis. |
| Approach: | They propose a mechanistic interpretability framework that uses the Schwartz Values Survey to interpret value . they use a dataset that operationalizes four dimensions of universal value through behavioral contexts . |
| Outcome: | The proposed method bridges psychological value frameworks with neuron analysis in large language models. |
When Efficiency Becomes a Vulnerability: Computational Cost Attacks on WebAgents (2026.acl-long)
Copied to clipboard
| Challenge: | Existing WebAgents suffer from computational cost attacks due to long reasoning processes and excessive computational cost. |
| Approach: | They propose a framework that generates adversarial prompts and a reinforcement learning-enhanced selector to identify the most effective perturbations. |
| Outcome: | The proposed framework exploits large language models to generate diverse adversarial prompts and a reinforcement learning–enhanced selector to identify the most effective perturbations. |
Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures (2026.acl-long)
Copied to clipboard
Yi Hu, Jiaqi Gu, Ruxin Wang, Zijun Yao, Hao Peng, Xiaobao Wu, Jianhui Chen, Muhan Zhang, Liangming Pan
| Challenge: | Recent research has shown that reinforcement learning can elicit intriguing emergent reasoning behaviors. |
| Approach: | They propose a comprehensive survey of the mechanistic understanding of large reasoning models . they organize findings into three core dimensions: 1) training dynamics, 2) reasoning mechanisms, and 3) unintended behaviors. |
| Outcome: | This paper synthesizes the mechanistic understanding of large reasoning models into three dimensions . authors outline a roadmap for future studies including improved interpretability and methodologies . |
PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts (2025.findings-acl)
Copied to clipboard
Ming Zhang, Yuhui Wang, Yujiong Shen, Tingyi Yang, Changhao Jiang, Yilong Wu, Shihan Dou, Qinhao Chen, Zhiheng Xi, Zhihao Zhang, Yi Dong, Zhen Wang, Zhihui Fei, Mingyang Wan, Tao Liang, Guojun Ma, Qi Zhang, Tao Gui, Xuanjing Huang
| Challenge: | Large Language Models (LLMs) have shown remarkable progress in dialogue and reasoning, but they struggle to solve strictly constrained dialogue tasks. |
| Approach: | They construct a dataset that contains 12,705 high-quality Chinese dialogue instructions from 440 flowcharts containing 5,055 process nodes. |
| Outcome: | The proposed model outperforms GPT-4o models on backward transitions and outperformed GPT-42 models on the same dataset. |
FastClass: A Time-Efficient Approach to Weakly-Supervised Text Classification (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent research shows keyword-driven methods can achieve state-of-the-art performance on various tasks. |
| Approach: | They propose an efficient weakly-supervised text classification approach using unlabeled data . they use dense text representation to retrieve class-relevant documents from unlabed corpus . |
| Outcome: | The proposed weakly-supervised classification method outperforms keyword-driven models on a wide range of classification tasks. |
RLKGF: Reinforcement Learning from Knowledge Graph Feedback Without Human Annotations (2025.findings-acl)
Copied to clipboard
| Challenge: | Lack of human preference labels remains a significant bottleneck when applying RLHF to a downstream domain. |
| Approach: | They propose a method that leverages human priors encoded in Knowledge Graphs (KGs) to derive RL rewards in the absence of manual annotations. |
| Outcome: | Experiments on three public and one private medical dialogue datasets show that the proposed method outperforms the competitive RLAIF in improving LLM diagnostic accuracy. |
HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks (2025.acl-long)
Copied to clipboard
Zhilin Wang, Jiaqi Zeng, Olivier Delalleau, Daniel Egert, Ellie Evans, Hoo-Chang Shin, Felipe Soares, Yi Dong, Oleksii Kuchaiev
| Challenge: | Inference-Time Scaling is critical to the success of recent models such as OpenAI o1 and DeepSeek R1 . however, many techniques require tasks to have answers that can be verified . |
| Approach: | They use data to train dedicated Feedback and Edit Models capable of inference-time scaling for open-ended tasks. |
| Outcome: | The proposed model can reach SoTA performance on Arena Hard at 92.7 as of 5 Mar 2025. |
DeepMaven: Deep Question Answering on Long-Distance Movie/TV Show Videos with Multimedia Knowledge Extraction and Synthesis (2023.eacl-main)
Copied to clipboard
| Challenge: | Long video content understanding poses a challenging set of research questions as it involves long-distance, cross-media reasoning and knowledge awareness. |
| Approach: | They propose a framework which extracts events, entities, and relations from the rich multimedia content in long videos to pre-construct movie knowledge graphs. |
| Outcome: | The proposed framework performs competitively for both the new DeepMovieQA and the pre-existing MovieQA dataset. |
CARE: Causality Reasoning for Empathetic Responses by Conditional Graph Generation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to empathetic response generation only consider causalities between the user’s emotion and the user's experiences and neglect interdependence among causalities and reason them independently. |
| Approach: | They propose to use a conditional variable Graph Auto-Encoder to reason all plausible causalities interdependently and simultaneously given the user’s emotion, dialogue history, and future dialogue content. |
| Outcome: | The proposed method achieves state-of-the-art in a real-world situation. |
Offline Reinforcement Learning for LLM Multi-step Reasoning (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly applied to complex tasks requiring multi-step reasoning. |
| Approach: | They propose an offline method for enhancing multi-step reasoning by optimizing the soft Bellman Equation by combining a policy model and a value function. |
| Outcome: | The proposed method surpasses existing methods on multi-step reasoning benchmarks and can be extended to multi-iteration frameworks when additional resources are available. |
R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling (2021.acl-long)
Copied to clipboard
| Challenge: | Existing models with stacked layers do not explicitly model hierarchical structure of language understanding. |
| Approach: | They propose a recursive Transformer model based on differentiable CKY style binary trees to emulate hierarchical composition process. |
| Outcome: | The proposed model can predict words given their left and right abstraction nodes. |
Reframe Your Life Story: Interactive Narrative Therapist and Innovative Moment Assessment with Large Language Models (2025.emnlp-main)
Copied to clipboard
Yi Feng, Jiaqi Wang, Wenxuan Zhang, Zhuang Chen, Shen Yutong, Xiyao Xiao, Minlie Huang, Liping Jing, Jian Yu
| Challenge: | Existing approaches to mental health support lack realism and capture therapeutic progression over time. |
| Approach: | They propose a framework that simulates expert narrative therapists by planning therapeutic stages, guiding reflection levels, and generating contextually appropriate responses through retrieval-augmentation. |
| Outcome: | The proposed framework outperforms standard methods in quality and depth on 260 simulated clients and 230 human participants. |
MIMIR: A Customizable Agent Tuning Platform for Enhanced Scientific Applications (2024.emnlp-demo)
Copied to clipboard
Xiangru Tang, Chunyuan Deng, Hanminwang Hanminwang, Haoran Wang, Yilun Zhao, Wenqi Shi, Yi Fung, Wangchunshu Zhou, Jiannan Cao, Heng Ji, Arman Cohan, Mark Gerstein
| Challenge: | Large language models (LLMs) have evolved into interactive agents capable of planning, tool use, and task execution across various tasks. |
| Approach: | They propose a platform that leverages large language models to generate agent-tuning data for fine-tuneing smaller, specialized models. |
| Outcome: | MIMIR enables large models to simulate various roles and create interaction data, which can then be used to fine-tune open-source models like LLaMA2. |
NovBench: Evaluating Large Language Models on Academic Paper Novelty Assessment (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for evaluating novelty have been proposed, but there is no systematic evaluation of their ability to generate novelty evaluations. |
| Approach: | They propose a benchmark to evaluate large language models’ ability to generate novelty evaluations in support of human peer review. |
| Outcome: | The proposed framework evaluates the quality of LLM-generated novelty evaluations under different prompting strategies. |
Delving Deep into Regularity: A Simple but Effective Method for Chinese Named Entity Recognition (2022.findings-naacl)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is a system for identifying text spans pertaining to specific entity types. |
| Approach: | They propose a method to investigate the regularity of Chinese NER's entity mentions by a regularity-aware module and a periodicity-gnostic module. |
| Outcome: | The proposed model significantly outperforms previous state-of-the-art methods on three benchmark datasets and a practical medical dataset. |
CQIL: Inference Latency Optimization with Concurrent Computation of Quasi-Independent Layers (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods to improve inference efficiency target to reduce per-layer latency, but ignore cumulative latency due to number of layers. |
| Approach: | They propose to identify quasi-independent layers that can be concurrently computed to significantly decrease inference latency. |
| Outcome: | Empirical results show that the proposed method reduces latency by 48.3% on LLaMA-33B while maintaining close level of performance. |
Towards Database-Free Text-to-SQL Evaluation: A Graph-Based Metric for Functional Correctness (2025.coling-main)
Copied to clipboard
Yi Zhan, Longjie Cui, Han Weng, Guifeng Wang, Yu Tian, Boyi Liu, Yingxiang Yang, Xiaoming Yin, Jiajun Xie, Yang Sun
| Challenge: | Existing metrics for evaluating functional correctness of SQL queries are prone to false positives due to inadequately prepared test databases. |
| Approach: | They propose a graph-based metric that uses a relational operator tree to extract rich semantic information from the logical execution plan of SQL queries and embed it into a diagram. |
| Outcome: | The proposed method eliminates the need for extensive test database preparation and performs graph matching on unseen SQL queries. |
RTADev: Intention Aligned Multi-Agent Framework for Software Development (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are efficient assistants to humans in software development tasks, but they can cause errors during the development process. |
| Approach: | They propose an intention aligned multi-agent framework that ensures that all agents work based on a consensus. |
| Outcome: | The proposed framework reduces errors and improves the quality of generated software code. |
Medical Dialogue Generation via Dual Flow Modeling (2023.findings-acl)
Copied to clipboard
| Challenge: | Medical dialogue systems (MDS) aim to provide patients with medical services, such as diagnosis and prescription. |
| Approach: | They propose a Dual Flow enhanced Medical (DFMed) dialogue generation framework that extracts the medical entities and doctor's dialogue acts used in the dialogue history and models their transitions with an entity-centric graph flow and a sequential act flow. |
| Outcome: | The proposed framework exceeds baselines in both automatic and manual evaluations on two datasets. |
Multimodal Sarcasm Target Identification in Tweets (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods to detect sarcasm target with text lacking context are not sufficient and complete. |
| Approach: | They propose a multi-modal sarcasm target identification task that performs both textual and visual detection. |
| Outcome: | The proposed model can perform textual target labeling and visual target detection. |
MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation (2026.acl-long)
Copied to clipboard
Weihua Zheng, Zhengyuan Liu, Tanmoy Chakraborty, Weiwen Xu, Xiaoxue Gao, Bryan Chen Zhengyu Tan, Bowei Zou, Chang Liu, Yujia Hu, Xing Xie, Xiaoyuan Yi, Jing Yao, Chaojun Wang, Long Li, Rui Liu, Huiyao Liu, Koji Inoue, Ryuichi Sumida, Tatsuya Kawahara, Fan Xu, Lingyu Ye, Wei Tian, Dongjun Kim, Jimin Jung, Jaehyung Seo, Nadya Yuki Wangsajaya, Pham Minh Duc, Ojasva Saxena, Palash Nandi, Xiyan Tao, Wiwik Karlina, Tuan Luong, Keertana Arun Vasan, Roy Ka-Wei Lee, Nancy F. Chen
| Challenge: | Existing models lack cultural alignment across modalities and languages . a new framework to assess cultural awareness across linguistics and languages is needed . |
| Approach: | They propose a framework that integrates tri-modally aligned cultural benchmarks and a five-dimensional evaluation protocol to assess cross-country awareness disparities. |
| Outcome: | The proposed framework assesses cultural awareness disparities across modalities and languages . it is the first dataset aligned at the input level across text, image, and speech . |
Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems (2021.naacl-demos)
Copied to clipboard
Anish Acharya, Suranjit Adhikari, Sanchit Agarwal, Vincent Auvray, Nehal Belgamwar, Arijit Biswas, Shubhra Chandra, Tagyoung Chung, Maryam Fazel-Zarandi, Raefer Gabriel, Shuyang Gao, Rahul Goel, Dilek Hakkani-Tur, Jan Jezabek, Abhay Jha, Jiun-Yu Kao, Prakash Krishnan, Peter Ku, Anuj Goyal, Chien-Wei Lin, Qing Liu, Arindam Mandal, Angeliki Metallinou, Vishal Naik, Yi Pan, Shachi Paul, Vittorio Perera, Abhishek Sethi, Minmin Shen, Nikko Strom, Eddie Wang
| Challenge: | Traditional goal-oriented dialogue systems require annotations which are hard to obtain for every new domain, limiting scalability. |
| Approach: | They propose a data-driven approach to building goal-oriented dialogue systems . they use a seed dialogue simulator to generate annotated conversations instead of collecting annotations . |
| Outcome: | The proposed system improves turn-level action signature prediction accuracy by 50% . the system is scalable, extensible and data efficient . |
VENUS: A VLLM-driven Video Content Discovery System for Real Application Scenarios (2025.emnlp-industry)
Copied to clipboard
Minyi Zhao, Yi Liu, Jianfeng Wen, Boshen Zhang, Hailang Chang, Zhiheng Ouyang, Jie Wang, Wensong He, Shuigeng Zhou
| Challenge: | Video Content Discovery (VCD) is to identify specific videos defined by a pre-specified text policy. |
| Approach: | They propose a Vision-Language Large Model-driven video content discovery system called VENUS to solve these problems. |
| Outcome: | The proposed system generates high-quality, VCD-specific data for model training and extends it to support it better. |
Accurate KV Cache Quantization with Outlier Tokens Tracing (2025.acl-long)
Copied to clipboard
Yi Su, Yuechi Zhou, Quantong Qiu, Juntao Li, Qingrong Xia, Ping Li, Xinyu Duan, Zhefeng Wang, Min Zhang
| Challenge: | Large Language Models (LLMs) require substantial computational resources during deployment. |
| Approach: | They propose a method to identify outlier tokens and exclude them from quantization . they find that the method can deliver a 6.4 times reduction in memory usage and a 2.5 times increase in throughput . |
| Outcome: | The proposed method delivers a 6.4 times reduction in memory usage and a 2.5 times increase in throughput under 2-bit quantization. |
Fine-grained Knowledge Enhancement for Retrieval-Augmented Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies rely on semantic similarity to retrieve knowledge but ignore fine-grained information within documents. |
| Approach: | They propose a fine-grained knowledge enhancement method to fill knowledge gaps with retrieved external information by a Chain-of-Thought prompting procedure and a decoding enhancement strategy to constrain the document-based decoding process. |
| Outcome: | The proposed method can be applied in a plug-and-play manner to enhance its performance with no additional modules or training process. |
Text Grafting: Near-Distribution Weak Supervision for Minority Classes in Text Classification (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent work generates pseudo labels by mining texts similar to the class names from the raw corpus, but there is a high risk that LLMs cannot generate in-distribution data, leading to ungeneralizable classifiers. |
| Approach: | They propose to use LLMs to generate pseudo labels by mining masked templates from corpus . they then use state-of-the-art LLM to synthesize near-distribution texts falling into minority classes . |
| Outcome: | The proposed framework improves on the previous methods for extremely weak-supervised text classification. |
DoTAT: A Domain-oriented Text Annotation Tool (2022.acl-demo)
Copied to clipboard
| Challenge: | DoTAT is a domain-oriented text annotation tool that can reduce the time for event annotation by 19.7% . the tool supports multi-person collaborative process with automatically merging and review . |
| Approach: | They propose a domain-oriented text annotation tool called DoTAT . it provides multi-person collaborative process with automatic merging and review . |
| Outcome: | The proposed tool can reduce the time for event annotation by 19.7% compared with existing tools. |
Is Reference Necessary in the Evaluation of NLG Systems? When and Where? (2024.naacl-long)
Copied to clipboard
| Challenge: | Despite recent advances in reference-free metrics, it has not been well understood when and where they can be used as an alternative to reference-based metrics. |
| Approach: | They propose to use reference-free metrics to evaluate NLG systems . they find they have a higher correlation with human judgment and greater sensitivity to deficiencies in language quality . |
| Outcome: | The proposed metrics exhibit higher correlation with human judgment and greater sensitivity to deficiencies in language quality. |
Mixture of Heterogeneous Grouped Experts for Language Modeling (2026.acl-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) based on Mixture-of-Experts (MoE) enforce uniform expert sizes, creating a rigidity that fails to align computational costs with varying token-level complexity. |
| Approach: | They propose a mixture of heterogeneous grouped experts (MoHGE) that allows for flexible, resource-aware expert combinations. |
| Outcome: | The proposed model matches the performance of existing Mixture-of-Experts architectures while maintaining balanced GPU utilization. |
Accelerating LLM Fine-Tuning via Embedding Knowledge Transfer (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on parameter-efficient fine-tuning (PEFT) have produced many state-of-the-art results by adapting LLMs to new tasks, but it requires substantial training data and time to enhance model performance. |
| Approach: | They propose a parameter-efficient fine-tuning framework which efficiently transfers knowledge from a small expert model to a target large model via embedding layers. |
| Outcome: | The proposed framework accelerates domain-specific fine-tuning, improves model performance and remains robust across diverse model families and PEFT methods. |
Counterfactual Debating with Preset Stances for Hallucination Elimination of LLMs (2025.coling-main)
Copied to clipboard
| Challenge: | Existing solutions to alleviate hallucination have considered utilizing LLMs’ inherent reasoning abilities to alleviating hallucinism, such as self-correction and diverse sampling methods. |
| Approach: | They propose a counterfactual multi-agent debate framework that predetermines LLMs' stances to override their inherent biases for answer inspection. |
| Outcome: | Extensive experiments on four datasets of three tasks demonstrate the superiority of the proposed framework over existing methods. |
IPR: Intelligent Prompt Routing with User-Controlled Quality-Cost Trade-offs (2025.emnlp-industry)
Copied to clipboard
Aosong Feng, Balasubramaniam Srinivasan, Yun Zhou, Zhichao Xu, Kang Zhou, Sheng Guan, Yueyan Chen, Xian Wu, Ninad Kulkarni, Yi Zhang, Zhengyuan Shen, Dmitriy Bespalov, Soumya Smruti Mishra, Yifei Teng, Darren Yow-Bang Wang, Haibo Ding, Lin Lee Cheong
| Challenge: | Existing systems require users to manually select models or employ rigid routing rules that fail to capture the continuous spectrum of query complexity. |
| Approach: | They propose a quality-constrained intelligent prompt routing framework that automatically selects optimal models based on predicted response quality and user-specified tolerance levels. |
| Outcome: | The proposed framework achieves 43.9% cost reduction while maintaining quality parity with strongest model in the Claude family and processes requests with sub-150ms latency. |
PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling (2022.coling-1)
Copied to clipboard
Guanting Dong, Daichi Guo, Liwen Wang, Xuefeng Li, Zechen Wang, Chen Zeng, Keqing He, Jinzheng Zhao, Hao Lei, Xinyue Cui, Yi Huang, Junlan Feng, Weiran Xu
| Challenge: | Existing slot filling models memorize inherent patterns of entities and contexts from training data. |
| Approach: | They propose a perturbed semantic structure awareness transferring method for slot filling models . they use two MLM-based training strategies to learn contextual semantic structure and word distribution . |
| Outcome: | The proposed method outperforms existing methods and gains strong generalization while preventing model from memorizing inherent patterns of entities and contexts. |
Agri-CM3: A Chinese Massive Multi-modal, Multi-level Benchmark for Agricultural Understanding and Reasoning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks lack comprehensive evaluations, particularly in multi-level reasoning, making it difficult to identify model limitations. |
| Approach: | They propose to use Agri-CM3 to assess multi-level reasoning in agricultural management by integrating multiple data modalities. |
| Outcome: | The Agri-CM3 benchmark includes 3,939 images and 15,901 multi-level multiple-choice questions with detailed explanations. |
Aerial Vision-and-Dialog Navigation (2023.findings-acl)
Copied to clipboard
| Challenge: | Aerial visionand-dialling navigation (AVDN) is a new approach to autonomous drones that can converse with humans and follow natural language commands to complete tasks. |
| Approach: | They propose to use Aerial Visionand-Dialog Navigation (AVDN) to navigate a drone via natural language conversation by collecting a dataset of over 3k recorded navigation trajectories with asynchronous human-human dialogs between commanders and followers. |
| Outcome: | The proposed system can converse with humans and follow natural language commands to fly to the expected destination. |
AutoPKG: An Automated Framework for Dynamic E-commerce Product-Attribute Knowledge Graph Construction (2026.findings-acl)
Copied to clipboard
Pollawat Hongwimol, Haoning Shang, Chutong Wang, Zhichao Wan, Yi Gao, Yuanming Li, Lin Gui, Wenhao Sun, Cheng Yu
| Challenge: | Product attribute extraction in e-commerce is bottlenecked by ontologies that are inconsistent, incomplete, and costly to maintain. |
| Approach: | They propose a multi-agent Large Language Model framework that constructs a Product-attribute Knowledge Graph from multimodal product content. |
| Outcome: | The proposed framework achieves 0.953 WKE for product types, 0.724 WKEs for attribute keys, and 0.531 edge-level accuracy for value assertions after canonicalization on a large real-world marketplace catalog dataset from Lazada (Alibaba). |
MTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language Sequences (2021.naacl-main)
Copied to clipboard
Jianing Yang, Yongxin Wang, Ruitao Yi, Yuying Zhu, Azaan Rehman, Amir Zadeh, Soujanya Poria, Louis-Philippe Morency
| Challenge: | a novel graph-based neural model for multimodal sequential data is proposed . fusion is the process of blending information from multiple modalities, usually preceded by alignment . |
| Approach: | They propose a graph-based neural model that converts unaligned data into a modal-temporal graph . they use a dynamic pruning and read-out technique to efficiently process the graph fusion operation . |
| Outcome: | The proposed model performs state-of-the-art on multimodal sentiment analysis and emotion recognition benchmarks while utilizing significantly fewer model parameters. |
MCPG: A Flexible Multi-Level Controllable Framework for Unsupervised Paraphrase Generation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on controllable unsupervised paraphrase generation are expensive and require supervised training on large parallel corpora. |
| Approach: | They propose a method for controllable unsupervised paraphrase generation that is flexible to adapt to specific domains without extra training. |
| Outcome: | The proposed method outperforms state-of-the-art unsupervised baselines by a margin. |
RESIN: A Dockerized Schema-Guided Cross-document Cross-lingual Cross-media Information Extraction and Event Tracking System (2021.naacl-demos)
Copied to clipboard
Haoyang Wen, Ying Lin, Tuan Lai, Xiaoman Pan, Sha Li, Xudong Lin, Ben Zhou, Manling Li, Haoyu Wang, Hongming Zhang, Xiaodong Yu, Alexander Dong, Zhenhailong Wang, Yi Fung, Piyush Mishra, Qing Lyu, Dídac Surís, Brian Chen, Susan Windisch Brown, Martha Palmer, Chris Callison-Burch, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Heng Ji
| Challenge: | We present a new information extraction system that can construct temporal event graphs from news documents. |
| Approach: | They propose a temporal event graph extraction system that can extract news documents . they extend the system from sentence-level event extraction to cross-document cross-media event extraction . |
| Outcome: | The proposed system can extract temporal event graphs from news documents in multiple languages and multiple data modalities. |
SocialEval: Evaluating Social Intelligence of Large Language Models (2025.acl-long)
Copied to clipboard
Jinfeng Zhou, Yuxuan Chen, Yihan Shi, Xuanming Zhang, Leqi Lei, Yi Feng, Zexuan Xiong, Miao Yan, Xunzhi Wang, Yaru Cao, Jianing Yin, Shuai Wang, Quanyu Dai, Zhenhua Dong, Hongning Wang, Minlie Huang
| Challenge: | Existing work on LLMs does not address their social intelligence (SI) and their discrepancy with humans. |
| Approach: | They propose a script-based bilingual SI benchmark that integrates outcome-oriented goal achievement evaluation and process-oriented interpersonal ability evaluation by manually crafting narrative scripts. |
| Outcome: | The proposed model is based on a script-based bilingual evaluation paradigm that integrates outcome- and process-oriented evaluation by manually crafting narrative scripts. |
PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)
Copied to clipboard
Yuzhen Shi, Huanghai Liu, Yiran HU, Song Gaojie, Xu Xinran, Yubo Ma, Tianyi Tang, Li Zhang, Qingjing Chen, Feng Di, Wenbo Lv, Weiheng Wu, Kexin Yang, Sen Yang, Wei Wang, Rongyao Shi, Qiu Yuanyang, Yuemeng Qi, Zhang Jingwen, Sui Xiaoyu, Yifan Chen, Zhang Yi, An Yang, Bowen Yu, Dayiheng Liu, Junyang Lin, Weixing Shen, Bing Zhao, Charles L. A. Clarke, HU Wei
| Challenge: | Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning. |
| Approach: | They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios. |
| Outcome: | The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics. |
An End-to-End Dialogue Summarization System for Sales Calls (2022.naacl-industry)
Copied to clipboard
| Challenge: | Summarizing sales calls is a routine task performed manually by salespeople. |
| Approach: | They propose a production system which combines generative models fine-tuned for customer-agent setting, with a human-in-the-loop user experience for an interactive summary curation process. |
| Outcome: | The proposed system can handle training data scarcity and privacy constraints in an industrial setting. |
RepEval: Effective Text Evaluation with LLM Representation (2024.emnlp-main)
Copied to clipboard
Shuqian Sheng, Yi Xu, Tianhang Zhang, Zanwei Shen, Luoyi Fu, Jiaxin Ding, Lei Zhou, Xiaoying Gan, Xinbing Wang, Chenghu Zhou
| Challenge: | Traditional metrics for automatic text evaluation are tailored to specific tasks, while LLM-based evaluation metrics are costly. |
| Approach: | They propose a metric that leverages projections of LLM representations for evaluation. |
| Outcome: | The proposed metric exhibits higher correlation with human judgments than previous methods on 14 datasets. |
Schema-Guided Culture-Aware Complex Event Simulation with Multi-Agent Role-Play (2024.emnlp-demo)
Copied to clipboard
Sha Li, Revanth Gangi Reddy, Khanh Nguyen, Qingyun Wang, Yi Fung, Chi Han, Jiawei Han, Kartik Natarajan, Clare Voss, Heng Ji
| Challenge: | Complex news events require swift responses from government and society, authors say . relying on historical events to project the future is insufficient, they say - a simulator for complex news events is needed . |
| Approach: | They propose a controllable complex news event simulator guided by event schema and user-provided assumptions . they incorporate a geo-diverse commonsense and cultural norm-aware knowledge enhancement component . |
| Outcome: | The proposed simulator achieves higher coherence and appropriateness than existing models. |
Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing jailbreak attacks primarily utilize scenario camouflage techniques, however their explicit mention of malicious intent will be easily recognized and defended by LLMs. |
| Approach: | They propose an indirect jailbreak attack approach, Puzzler, which can bypass LLM’s defensive strategies and obtain malicious response by implicitly providing LLMs with some clues about the original malicious query. |
| Outcome: | The proposed approach can bypass the LLM’s defensive strategies and obtain malicious response by implicitly providing LLMs with some clues about the original malicious query. |
Too Good to be Bad: On the Failure of LLMs to Role-Play Villains (2026.findings-acl)
Copied to clipboard
Zihao Yi, Qingxuan Jiang, Ruotian Ma, Xingyu Chen, Qu Yang, Mengru Wang, Fanghua Ye, Ying Shen, Zhaopeng Tu, Xiaolong Li, Liefeng Bo
| Challenge: | Large Language Models (LLMs) are increasingly tasked with creative generation, but their ability to portray non-prosocial, antagonistic personas remains largely unexamined. |
| Approach: | They propose a moral alignment benchmark to test the safety of large language models . they find that models struggle with traits directly antithetical to safety principles . |
| Outcome: | The proposed model fails to accurately portray morally ambiguous or villainous characters . the model fails most with traits directly antithetical to safety principles . |
Reinforcement Learning on Pre-Training Data (2026.acl-long)
Copied to clipboard
Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang
| Challenge: | Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings. |
| Approach: | They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data. |
| Outcome: | Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base. |
Can LLMs Hear the Dogwhistle? (2026.findings-acl)
Copied to clipboard
Yifan Liu, Yi Lin, Xinwei Guo, Ziwei Wang, Jiaxin Zhang, Guanhua Chen, Haiyan Wu, Xiangyu Zhao, Xin Yao, Xuetao Wei
| Challenge: | Existing safety benchmarks focus on explicitly harmful content, but ignore context-dependent expressions such as dogwhistles. |
| Approach: | They propose a benchmark for evaluating LLM safety under dogwhistle-driven prompts . their findings expose a blind spot in current safety evaluation practices . |
| Outcome: | The proposed benchmark compared safety performance with toxic terms using dogwhistle-driven prompts. |
The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG) (2024.findings-acl)
Copied to clipboard
Shenglai Zeng, Jiankun Zhang, Pengfei He, Yiding Liu, Yue Xing, Han Xu, Jie Ren, Yi Chang, Shuaiqiang Wang, Dawei Yin, Jiliang Tang
| Challenge: | Retrieval-augmented generation (RAG) is a powerful technique to facilitate language model generation with proprietary and private data, where data privacy is . a privacy issue that is currently under-explored, is posed by RAG. |
| Approach: | They propose to use retrieval-augmented generation (RAG) to facilitate language model generation with proprietary and private data where data privacy is a pivotal concern. |
| Outcome: | The proposed attack methods demonstrate that RAG can mitigate the old risks, i.e., leakage of the LLMs’ training data. |
Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing research on building ES conversation systems only considered single-turn interactions with users, which is over-simplified and has limited support for multi-turn systems. |
| Approach: | They propose a multi-turn ES conversation system that uses lookahead heuristics to estimate future user feedback after using particular strategies. |
| Outcome: | The proposed system significantly outperforms baselines in both dialogue generation and strategy planning. |
StructFlowBench: A Structured Flow Benchmark for Multi-turn Instruction Following (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation benchmarks focus on fine-grained constraint satisfaction and domain-specific capability assessment, yet overlook the crucial structural dependencies between dialogue turns that distinguish multi-turn from single-turn interactions. |
| Approach: | They propose a multi-turn instruction following benchmark with structural flow modeling that defines an innovative structural flow framework with six fundamental inter-turn relationships. |
| Outcome: | The proposed model is based on a framework with six fundamental inter-turn relationships and is able to analyze and generate specific dialogue flows tailored to specific scenarios. |
WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models (2026.acl-long)
Copied to clipboard
Rui Wang, Ce Zhang, Jun-Yu Ma, Jianshu Zhang, Hongru Wang, Yi Chen, Boyang Xue, Tianqing Fang, Zhisong Zhang, Hongming Zhang, Haitao Mi, Dong Yu, Kam-Fai Wong
| Challenge: | Existing agentic systems are retrieval-heavy but reasoning-light . current systems lack compositional reasoning, a key component of deep research . |
| Approach: | They propose a data synthesis pipeline WebAggregator to shift agentic paradigm . they use Proactive Explorer to collect interconnected knowledge and Compositional Logic Proposer to weave knowledge into complex questions . |
| Outcome: | The proposed pipeline surpasses GPT-4.1 and matches Claude-3.7-Sonnet on GAIA, WebWalkerQA, and XBench. |
Random Entity Quantization for Parameter-Efficient Compositional Knowledge Graph Representation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to learning on Knowledge Graphs (KGs) are not critical for learning on KGs. |
| Approach: | They propose an alternative approach to represent entities by composing entity-corresponding codewords matched from predefined small-scale codebooks. |
| Outcome: | The proposed approach achieves similar results to existing methods. |
Value Compass Benchmarks: A Comprehensive, Generative and Self-Evolving Platform for LLMs’ Value Evaluation (2025.acl-demo)
Copied to clipboard
Jing Yao, Xiaoyuan Yi, Shitong Duan, Jindong Wang, Yuzhuo Bai, Muhua Huang, Yang Ou, Scarlett Li, Peng Zhang, Tun Lu, Zhicheng Dou, Maosong Sun, James Evans, Xing Xie
| Challenge: | Current evaluation methods for large language models face two key challenges: 1. evaluation validity and 2. Result interpretation reduce the pluralistic and incommensurable values to one-dimensional scores. |
| Approach: | They propose a platform for comprehensive value diagnosis of large language models (LLMs) that provides a generative evaluation paradigm that automatically creates real-world test items co-evolving with ever-advancing LLMs. |
| Outcome: | The proposed platform provides a framework for comprehensive value diagnosis of large language models (LLMs) with fine-grained scores and case studies across 27 value dimensions for 33 leading LLMs, customized comparisons, and visualized analysis of LLM’s alignment with cultural values. |
Controllable LLM Reasoning via Sparse Autoencoder-Based Steering (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods struggle to control fine-grained reasoning strategies due to conceptual entanglement in LRMs’ hidden states. |
| Approach: | They propose to decompose strategy-entangled hidden states into a disentangled feature space by using Sparse Autoencoders to identify the few strategy-specific features from the vast pool of SAE features. |
| Outcome: | The proposed method outperforms existing methods by 15% in control effectiveness. |
Don’t Miss the Potential Customers! Retrieving Similar Ads to Improve User Targeting (2021.findings-emnlp)
Copied to clipboard
| Challenge: | a method for user targeting is developed to identify online users to whom an ad should be targeted. |
| Approach: | They propose a method for automatic augmentation of positive and negative clickthrough data for user targeting models. |
| Outcome: | The proposed method can increase positive and negative instances of positive training instances on two datasets. |
DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to augment self-training (ST) in attribute-controllable language generation are limited and limited. |
| Approach: | They propose a new ST framework that integrates self-generated pseudo text into attribute-controllable language generation. |
| Outcome: | The proposed framework can be applied to semi-supervised controllable language generation. |
GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to retrieve information from large language models (LLMs) but they fail to address the preference gap between retrievers and LLMs. |
| Approach: | They propose a retrieval module that dynamically injects retrieved information into the input context of large language models (LLMs) This approach aligns the retriever’s and LLM’s preferences by defining a new metric, “gain”, which measure how well an input passage contributes to correct outputs. |
| Outcome: | The proposed approach has shown significant success in various NLP tasks, but there is a preference gap between retrievers and LLMs. |
Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward (2026.findings-acl)
Copied to clipboard
Guanhua Huang, Tingqiang Xu, Mingze Wang, Qi Yi, Xue Gong, Siheng Li, Ruibin Xiong, Kejiao Li, Yuhao Jiang, Bo Zhou
| Challenge: | Recent studies show that RLVR training is slow and results plateau as policy entropy collapses . low-probability regularization (Lp-Reg) reduces the number of low-quality exploratory tokens induced by RL training . |
| Approach: | They propose a method to reduce RLVR over-penalization by eliminating low-probability exploratory tokens . they propose 'Low-provability Regularization' to reduce the gradual elimination of low-quality exploratory entropy tokens. |
| Outcome: | The proposed method eliminates low-probability exploratory tokens and prevents suppression of potentially valuable low-property candidates. |
Unsupervised Graph-Text Mutual Conversion with a Unified Pretrained Language Model (2023.acl-long)
Copied to clipboard
| Challenge: | Existing unsupervised approaches for learning knowledge graphs require multiple modules and require entity information or relation type for training. |
| Approach: | They propose a method that uses a unified pretrained language model to achieve fully unsupervised graph-text mutual conversion for the first time. |
| Outcome: | The proposed method outperforms state-of-the-art methods for G2T and T2G tasks by fine-tuning only one pretrained model. |
INDOORWORLD : Integrating Physical Task Solving and Social Simulation in A Heterogeneous Multi-Agent Environment (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing virtual environments for LLM agent research focus on task solving or social simulation . existing environments for virtual environments lack physical grounding of social behaviors . |
| Approach: | They propose a virtual environment that tightly integrates physical and social dynamics . IndoorWorld is a heterogeneous multi-agent environment that integrates social and physical dynamics based on a simulation of physical environments . |
| Outcome: | The proposed environment integrates physical and social dynamics into a heterogeneous multi-agent environment. |
COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation (2021.naacl-demos)
Copied to clipboard
Qingyun Wang, Manling Li, Xuan Wang, Nikolaus Parulian, Guangxing Han, Jiawei Ma, Jingxuan Tu, Ying Lin, Ranran Haoran Zhang, Weili Liu, Aabhas Chauhan, Yingjun Guan, Bangzheng Li, Ruisong Li, Xiangchen Song, Yi Fung, Heng Ji, Jiawei Han, Shih-Fu Chang, James Pustejovsky, Jasmine Rah, David Liem, Ahmed ELsayed, Martha Palmer, Clare Voss, Cynthia Schneider, Boyan Onyshkevych
| Challenge: | a new framework to digest relevant biomedical knowledge is needed to combat COVID-19 . quantity of research results is a bottleneck, and false information promoted in publications . |
| Approach: | a team of researchers has developed a framework to extract multimedia knowledge elements from scientific literature to combat COVID-19. |
| Outcome: | a new framework extracts fine-grained multimedia knowledge elements from scientific literature . it provides detailed contextual sentences, subfigures, and knowledge subgraphs as evidence . the framework is based on a case study of drug repurposing . |
Punctuation-Steered Representation Fine-Tuning (2026.acl-short)
Copied to clipboard
| Challenge: | Existing methods for parameter-efficient fine-tuning (PeFT) are limited due to their prohibitive size and computational demands. |
| Approach: | They propose a method that fine-tunes punctuation representations to achieve performance improvements. |
| Outcome: | The proposed method improves performance by altering the representation space alone . but it results in suboptimal performance due to the effects of the method on the output . |
Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Value (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing work specifies values as risk criteria formulated in the AI community, e.g., fairness and privacy protection, suffering from poor clarity, adaptability and transparency. |
| Approach: | They propose a value alignment paradigm based on Schwartz's Theory of Basic Values as an instantiation and propose 'BaseAlign' to support this paradigm. |
| Outcome: | The proposed model covers existing risks and anticipates unidentified ones with a low-data set. |
Enhancing Large Language Models Against Inductive Instructions with Dual-critique Prompting (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing studies have focused on how LLMs handle inductive instructions, which may stem from users’ false beliefs or malicious intents. |
| Approach: | They propose a benchmark of Inductive Instructions where false knowledge is incorporated into instructions in multiple different styles. |
| Outcome: | The proposed model improves robustness against inductive instructions, despite different inductive styles and complexity. |
Neural Topic Modeling based on Cycle Adversarial Training and Contrastive Learning (2023.findings-acl)
Copied to clipboard
| Challenge: | Neural topic models have been widely used to extract common topics across documents. |
| Approach: | They propose a framework to apply contrastive learning directly to the decoder . they propose 'self-supervised' contrastive loss to make the generator capture similar topic information . |
| Outcome: | The proposed framework outperforms baselines on four benchmark datasets. |
Autodive: An Integrated Onsite Scientific Literature Annotation Tool (2023.acl-demo)
Copied to clipboard
| Challenge: | Annotating scientific literature directly on PDF documents can greatly improve the labeling efficiency of scientists whose annotation costs are very high. |
| Approach: | They propose an integrated onsite scientific literature annotation tool for natural scientists and Natural Language Processing (NLP) researchers. |
| Outcome: | The proposed tool supports the whole lifecycle of corpus generation including i)project management, ii)resource management, and iv)ontology management, as well as manual annotation, onsite auto annotation, and vi)task statistic. |
ToViLaG: Your Visual-Language Generative Model is Also An Evildoer (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent large-scale Visual-Language Generative Models (VLGMs) generate toxic content, e.g., offensive text and pornography images, raising significant ethical risks. |
| Approach: | They propose a bottleneck-based detoxification method to reduce toxicity while maintaining comparable generation quality. |
| Outcome: | The proposed method could reduce toxicity while maintaining comparable generation quality. |
Natural-Language Policies to Executable Decisions: An Interpretable Large Language Model Framework (2026.acl-industry)
Copied to clipboard
Ziqiang Zhang, Jing Ma, Zilong Wang, Jiayuan Chen, Yi Qiao, Yu He, Wei Zhang, Dai Cheng, Xiaoyu Shen
| Challenge: | a production-grade pricing system for tourism is challenging due to unstructured nature of travel orders and ever-evolving pricing policies. |
| Approach: | They propose a production-grade pricing system with a strict decision boundary . they propose to combine structured extraction and bounded policy/path selection with interpretable condition trees . |
| Outcome: | The proposed system processed 3,960 orders in six months and reduced the order management team from 15-20 to 3 . the system reduced the per-order handling time from 10 minutes to 2 minutes. |
SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding (2026.findings-acl)
Copied to clipboard
Songcheng Cai, Zhiheng Lyu, Yuansheng Ni, Xiangchao Chen, Baichuan Zhou, Shenzhe Zhu, Yi Lu, Haozhe Wang, Chi Ruan, Benjamin Schneider, Weixu Zhang, Xiang Li, Andy Zheng, Yuyu Zhang, Ping Nie, Wenhu Chen
| Challenge: | Existing benchmarks for agentic repository-level code understanding overlook long tail topics and rely on memorized knowledge. |
| Approach: | They propose a repository-level agentic code understanding benchmark that uses long-tail repositories with executable environments to enforce topical balance. |
| Outcome: | Empirically, a Qwen3-8B model trained with the proposed benchmark outperforms GPT-4o by 2.3 points. |
A Two-phase Prototypical Network Model for Incremental Few-shot Relation Classification (2020.coling-main)
Copied to clipboard
| Challenge: | Existing supervised and distantly supervised RC models ignore the emergence of novel relations in open environment. |
| Approach: | They propose a two-phase prototypical network with prototype attention alignment and triplet loss to dynamically recognize the novel relations with a few support instances without catastrophic forgetting. |
| Outcome: | Experiments show that the proposed model performs better on deep learning and few-shot learning . it can recognize the novel relations with a few support instances without catastrophic forgetting . |
TempCompass: Do Video LLMs Really Understand Videos? (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks on video large language models lack a comprehensive feedback on temporal perception ability . current models cannot distinguish between different temporal aspects and are limited in task formats . |
| Approach: | They propose a benchmark to evaluate temporal perception ability of video large language models . they construct conflicting videos that share the same static content but differ in a specific temporal aspect . |
| Outcome: | The proposed benchmarks show that video large language models exhibit poor temporal perception ability. |
R3: End-to-End Reasoning-based Planning for Multi-step Retrosynthesis via Reinforcement Learning (2026.acl-long)
Copied to clipboard
YiFei Wang, Qizhi Pei, Jiangtao Feng, Yuntian Shi, Yi Duan, Lihao Wang, Lei Bai, Lijun Wu, Wei-Ying Ma, Hao Zhou
| Challenge: | Experimental results show that R3 is a superior alternative to traditional search algorithms for multistep retrosynthesis planning. |
| Approach: | They propose a framework that reformulates multistep retrosynthetic planning as a generative reasoning task. |
| Outcome: | The proposed framework achieves state-of-the-art Top-1 accuracy of 43.7% on retrobench . it leverages Large Language Models to reformulate multistep retrosynthesis as a generative reasoning task. |
Training-free LLM Merging for Multi-task Learning (2025.acl-long)
Copied to clipboard
Zichuan Fu, Xian Wu, Yejing Wang, Wanyu Wang, Shanshan Ye, Hongzhi Yin, Yi Chang, Yefeng Zheng, Xiangyu Zhao
| Challenge: | Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse natural language processing tasks. |
| Approach: | They propose a training-free method for unifying different specialized LLMs into a single model using model-wise and layer-wise pruning and scaling. |
| Outcome: | The proposed method outperforms existing merging techniques and surpasses models fine-tuned on combined datasets in most scenarios. |
Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Diffusion large language models (dLLMs) offer bidirectional attention and parallel generation . fixed anchors can enforce constraints, but they often impose rigid spans, leading to truncated reasoning . |
| Approach: | They propose a method that dynamically estimates end-anchor positions to adjust generation length before iterative infilling. |
| Outcome: | The proposed method improves format compliance and answer accuracy on GSM8K and MATH. |
ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)
Copied to clipboard
Ruibin Yuan, Hanfeng Lin, Yi Wang, Zeyue Tian, Shangda Wu, Tianhao Shen, Ge Zhang, Yuhang Wu, Cong Liu, Ziya Zhou, Liumeng Xue, Ziyang Ma, Qin Liu, Tianyu Zheng, Yizhi Li, Yinghao Ma, Yiming Liang, Xiaowei Chi, Ruibo Liu, Zili Wang, Chenghua Lin, Qifeng Liu, Tao Jiang, Wenhao Huang, Wenhu Chen, Jie Fu, Emmanouil Benetos, Gus Xia, Roger Dannenberg, Wei Xue, Shiyin Kang, Yike Guo
| Challenge: | Despite LLMs' impressive capabilities in musical knowledge, music reasoning remains an unsolved task. |
| Approach: | They propose an open-source large language model (LLM) that integrates intrinsic musical abilities into LLaMA2 and GPT-3.5. |
| Outcome: | The proposed model can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers. |
OPT-Tree: Speculative Decoding with Adaptive Draft Tree Structure (2025.tacl-1)
Copied to clipboard
| Challenge: | Autoregressive language models generate one token in one step, limiting inference efficiency . Existing methods do not adapt to different situations to maximize acceptance length . speculative decoding has shown great potential for lossless acceleration . |
| Approach: | They propose an algorithm to construct adaptive and scalable draft trees for autoregressive language models. |
| Outcome: | Experimental results show that OPT-Tree outperforms existing draft trees and achieves speed-up ratio of up to 3.2 compared with autoregressive decoding. |
WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines (2025.naacl-long)
Copied to clipboard
Genta Indra Winata, Frederikus Hudi, Patrick Amadeus Irawan, David Anugraha, Rifki Afina Putri, Wang Yutong, Adam Nohejl, Ubaidillah Ariq Prathama, Nedjma Ousidhoum, Afifa Amriani, Anar Rzayev, Anirban Das, Ashmari Pramodya, Aulia Adila, Bryan Wilie, Candy Olivia Mawalim, Cheng Ching Lam, Daud Abolade, Emmanuele Chersoni, Enrico Santus, Fariz Ikhwantri, Garry Kuwanto, Hanyang Zhao, Haryo Akbarianto Wibowo, Holy Lovenia, Jan Christian Blaise Cruz, Jan Wira Gotama Putra, Junho Myung, Lucky Susanto, Maria Angelica Riera Machin, Marina Zhukova, Michael Anugraha, Muhammad Farid Adilazuarda, Natasha Christabelle Santosa, Peerat Limkonchotiwat, Raj Dabre, Rio Alexander Audino, Samuel Cahyawijaya, Shi-Xiong Zhang, Stephanie Yulia Salim, Yi Zhou, Yinxuan Gui, David Ifeoluwa Adelani, En-Shiun Annie Lee, Shogo Okada, Ayu Purwarianti, Alham Fikri Aji, Taro Watanabe, Derry Tanti Wijaya, Alice Oh, Chong-Wah Ngo
| Challenge: | Vision Language Models struggle with cultural-specific knowledge, especially in languages other than English and in underrepresented cultural contexts. |
| Approach: | They propose a visual question answering (VQA) dataset with text-image pairs across 30 languages and dialects and a training dataset. |
| Outcome: | The proposed model performs better with correct location context, but struggles with adversarial contexts and predicting specific regional cuisines and languages. |
R-Tuning: Instructing Large Language Models to Say ‘I Don’t Know’ (2024.naacl-long)
Copied to clipboard
Hanning Zhang, Shizhe Diao, Yong Lin, Yi Fung, Qing Lian, Xingyao Wang, Yangyi Chen, Heng Ji, Tong Zhang
| Challenge: | Existing methods for instruction tuning force the model to complete a sentence no matter whether it knows the knowledge or not. |
| Approach: | They propose a new approach to tuning large language models to refrain from answering questions beyond its parametric knowledge by identifying the disparity in parametric and parametric information. |
| Outcome: | The proposed approach improves a model’s ability to answer known questions and refrain from answering unknown questions. |
CITE: Benchmarking Heterogeneous Text-Attributed Graph Models (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models and text-aware graph learning have increased interest in reasoning over text-attributed graphs. |
| Approach: | They propose a large-scale heterogeneous text-attributed graph benchmark for catalytic materials that contains over 438K nodes and 1.2M edges . they establish standardized evaluation protocols for node classification and link prediction and conduct ablation studies to assess the impact of graph heterogenity and textual attributes. |
| Outcome: | The proposed benchmarks are compared to existing methods and provide a baseline for the evaluation of four classes of learning paradigms. |
PUPPET: Neural-Symbolic Standardized Patients for Mental Health (2026.acl-long)
Copied to clipboard
Chen Xu, Yu ji, Zhenyu Lv, Yang Yi, Yizhe Yang, Luyao Ji, Chaoyi Chen, Xianyang Wang, Tian Lan, Zhihua Wang, Juan Wang, Xunde Dong, Fuze Tian, Qunxi Dong, Bin Hu
| Challenge: | Existing LLM-based training approaches lack faithful responses to clinical errors and explainable feedback. |
| Approach: | They propose a neural-symbolic virtual standardized patient governed by an OBSERVE-THINK-BEHAVE architecture that embeds LLM reasoning into a symbolic system where experts implant causal associations between intervention logic and patient mental states. |
| Outcome: | The proposed model outperforms baselines in faithfulness and pedagogical value. |
Rethinking-based Code Summarization with Chain of Comments (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods focus on learning a direct mapping from pure code to summaries, overlooking the heterogeneity gap between code and summary. |
| Approach: | They propose a framework that uses chain of comments as auxiliary intermediate information to bridge the gap between code and summaries. |
| Outcome: | The proposed framework outperforms baseline models and multiple code Large Language Models by a large margin. |
Scene Graph Enhanced Pseudo-Labeling for Referring Expression Comprehension (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Referring expression comprehension is a visual-linguistic task that involves localizing objects in images based on textual referring expressions. |
| Approach: | They propose a scene graph-based framework that generates high-quality pseudo region-query pairs . their method captures relationships between objects in images and generates expressions enriched with relation information. |
| Outcome: | The proposed framework outperforms existing methods by 10%, 12%, and 11% on RefCOCO, RefCoCO+, and Ref COCOg datasets. |
Achieving binary weight and activation for LLMs using Post-Training Quantization (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for quantizing large language models suffer from performance degradation when weights are quantized to 1 bit. |
| Approach: | They propose a post-training quantization framework with W(1+1)A(14) configuration . they propose utilizing Hessian-aware fine-grained grouping along with an EM-based quantization scheme . |
| Outcome: | The proposed method surpasses state-of-the-art (SOTA) LLM quantization baselines on W2A4 across multiple tasks. |
Knowledge-Guided Cross-Topic Visual Question Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for visual question generation use answers or question types as constraints to generate questions. |
| Approach: | They propose a knowledge-guided cross-topic visual question generation task to generate unseen topics in cross-section scenarios. |
| Outcome: | The proposed model outperforms baselines and can generate unseen topic-related questions in cross-topic scenarios. |
Non-Autoregressive Math Word Problem Solver with Unified Tree Structure (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing MWP solvers do not handle variants that can be derived via mathematical manipulation. |
| Approach: | They propose a non-autoregressive solver to present a solution expression and decode it from a given problem description. |
| Outcome: | The proposed solver is able to decode multiple expression variants and correct them . it is based on a unified tree structure and is available on Math23K and MAWPS. |
On Orthogonality Constraints for Transformers (2021.acl-short)
Copied to clipboard
Aston Zhang, Alvin Chan, Yi Tay, Jie Fu, Shuohang Wang, Shuai Zhang, Huajie Shao, Shuochao Yao, Roy Ka-Wei Lee
| Challenge: | a dedicated study on orthogonality constraints for transformers has been lacking . plug-and-play constraints increase the BLEU of transformers . |
| Approach: | They propose to use plug-and-play constraints to encourage matrices to be orthogonal for numerical stability. |
| Outcome: | The proposed constraint increases the BLEU on the large-scale WMT’16 EnDe benchmark by a factor of 28.4 to 29.6. |
Do Large Language Models Rank Fairly? An Empirical Study on the Fairness of LLMs as Rankers (2024.naacl-long)
Copied to clipboard
| Challenge: | Recent studies have shown that Large Language Models (LLMs) are more efficient in natural language understanding tasks. |
| Approach: | They evaluate large language models (LLMs) using a TREC Fair Ranking dataset . they assess fairness from both user and content perspectives . |
| Outcome: | The proposed model outperforms the existing models in the fair ranking task. |
Improved Knowledge Distillation for Pre-trained Language Models via Knowledge Selection (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on knowledge distillation have shown that not all knowledge is necessary for learning a good student model. |
| Approach: | They propose an actor-critic approach to selecting appropriate knowledge to transfer during the process of knowledge distillation. |
| Outcome: | The proposed method outperforms several strong knowledge distillation baselines significantly on the GLUE datasets. |
MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)
Copied to clipboard
Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie
| Challenge: | Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models. |
| Approach: | They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts. |
| Outcome: | The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings . |
Learning to Maximize Mutual Information for Chain-of-Thought Distillation (2024.findings-acl)
Copied to clipboard
| Challenge: | Knowledge distillation is a technique of transferring knowledge from large, complex models to smaller ones. |
| Approach: | They propose a method utilizing chain-of-thought distillation to transfer knowledge from large, complex models to smaller ones by maximizing mutual information of the representation features of the two tasks. |
| Outcome: | The proposed method outperforms the state-of-the-art knowledge distillation method on four datasets. |
On Synthetic Data Strategies for Domain-Specific Generative Retrieval (2025.acl-long)
Copied to clipboard
| Challenge: | Generative retrieval models can be used to generate ranked lists of potentially relevant document identifiers for a user query. |
| Approach: | They propose a synthetic data generation strategy for a two-stage training framework that focuses on learning to decode document identifiers from queries and a strategy for mining hard negatives based on initial model's predictions. |
| Outcome: | The proposed model can generate ranked lists of potentially relevant document identifiers for a user query and then refine ranking through preference learning. |
MMLF: Multi-query Multi-passage Late Fusion Retrieval (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches to query expansion are limited in terms of lexical overlap. |
| Approach: | They propose a query expansion pipeline that generates sub-queries, expands them into pseudo-documents, retrieves them individually and aggregates results using reciprocal rank fusion. |
| Outcome: | The proposed pipeline improves on five BEIR benchmark datasets and achieves a maximum gain of up to 8%. |
CoGR-MoE: Concept-Guided Expert Routing with Consistent Selection and Flexible Reasoning for Visual Question Answering (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent work has begun to address routing instability in VQA models by grouping similar concepts or routing based on examples. |
| Approach: | They propose a Concept-Guided Routing framework which incorporates semantics of the answer options to guide expert selection in the training phase. |
| Outcome: | The proposed framework delivers strong performance across multiple VQA tasks, demonstrating the effectiveness of the proposed framework. |
Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization (2026.acl-long)
Copied to clipboard
Shaohua Duan, Pengcheng Huang, Xinze Li, Zhenghao Liu, Xiaoyuan Yi, Yukun Yan, Shuo Wang, Yu Gu, Ge Yu, Maosong Sun
| Challenge: | Recent studies have explored fine-tuning Large Language Models with synthetic data to enhance their long-context capabilities. |
| Approach: | They propose a framework that leverages a Multi-Armed Bandit rollout strategy to identify the most informative chunks from the given long context for sampling high-quality and diverse responses. |
| Outcome: | The proposed framework achieves 4% improvement on long-context reasoning benchmarks on Llama and Qwen. |
Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) often struggle with the issue of generating inaccurate or fabricated content even when they possess correct knowledge. |
| Approach: | They propose a decoding method that mitigates hallucinations without extra training . they propose entropy eNhanced decoding that leverages inner probability changes . |
| Outcome: | The proposed method improves the truthfulness and informativeness of generation while maintaining robust QA accuracy. |
Defining a New NLP Playground (2023.findings-emnlp)
Copied to clipboard
Sha Li, Chi Han, Pengfei Yu, Carl Edwards, Manling Li, Xingyao Wang, Yi Fung, Charles Yu, Joel Tetreault, Eduard Hovy, Heng Ji
| Challenge: | Recent explosion of performance of large language models (LLMs) has changed the field more abruptly and seismically than any other shift in the field’s 80 year history. |
| Approach: | They propose 20+ PhD-dissertation-worthy research directions to define a new NLP playground by combining theoretical analysis, new and challenging problems, learning paradigms and interdisciplinary applications. |
| Outcome: | The proposed research will cover theoretical analysis, new and challenging problems, learning paradigms and interdisciplinary applications. |
Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for GUI understanding ignore a key GUI-referring task: screen reading based on user-indicated points. |
| Approach: | They propose a Tree-of-Lens agent that constructs a Hierarchical Layout Tree based on user input points and a GUI screenshot. |
| Outcome: | The proposed agent can interpret the Screen Point-and-Read task on mobile, web, and operating systems. |
Shoes-ACOSI: A Dataset for Aspect-Based Sentiment Analysis with Implicit Opinion Extraction (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work in ABSA has investigated opinion extraction as an important subtask, but these works only label concise, *explicitly*-stated opinion spans. |
| Approach: | They propose a new ABSA dataset with implicit opinion span annotations . they use paragraph-length inputs and prompted-LLM baselines to evaluate the dataset . |
| Outcome: | The proposed dataset presents significant challenges for fully-supervised models and LLMs. |
Ask Again, Then Fail: Large Language Models’ Vacillations in Judgment (2024.acl-long)
Copied to clipboard
| Challenge: | Existing large language models often waver in their judgments when faced with follow-up questions . this is a challenge for generating reliable responses and building user trust . |
| Approach: | They propose a Follow-up Questioning Mechanism and two metrics to quantify this inconsistency . they also develop a framework that teaches large language models to maintain original correct judgments . |
| Outcome: | The proposed framework improves the general capabilities of large language models by allowing them to maintain original correct judgments. |
Influence-based Online Experience Selection for Effective RLHF (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for RL fail to establish an interpretable connection between data and optimization objectives. |
| Approach: | They propose a data selection method that dynamically estimates the influence of individual training samples on policy optimization. |
| Outcome: | The proposed method significantly improves training effectiveness with fewer optimization steps. |
TISE: A Tripartite In-context Selection Method for Event Argument Extraction (2024.naacl-long)
Copied to clipboard
| Challenge: | Recent studies show that LLMs can finish inference by providing several examples. |
| Approach: | They propose a method which integrates three requirements when selecting an in-context example and integrates them into a set of determinantal point processes to enhance the reasoning capabilities of LLMs. |
| Outcome: | The proposed method can achieve superior performance with fewer examples and outperform some supervised methods. |
Exploring and Verbalizing Academic Ideas by Concept Co-occurrence (2023.acl-long)
Copied to clipboard
| Challenge: | a new framework for academic idea inspiration is being developed for academic research assistants . number of academic publications is increasing exponentially, making it difficult for an independent researcher to understand these papers thoroughly. |
| Approach: | They propose a framework based on concept co-occurrence for academic idea inspiration . they construct evolving concept graphs according to the co-existence relationship of concepts from 20 disciplines or topics . |
| Outcome: | The proposed system can be used to explore connections between academic concepts and verbalize the new ideas. |
TrigReason: Trigger-Based Collaboration between Small and Large Reasoning Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Reasoning Models suffer from high inference latency due to autoregressive reasoning . SpecReason adopts a polling-based design that repeatedly invokes the LRM for verification at every step . |
| Approach: | They propose a trigger-based collaborative reasoning framework that delegates most reasoning to the SRM and activates LRM intervention only when necessary. |
| Outcome: | The proposed framework reduces latency and API cost by 73.3% under edge–cloud conditions. |
Self-Detoxifying Language Models via Toxification Reversal (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to generate toxic content in pretrained language models are resource-intensive and require additional components. |
| Approach: | They propose a method that enables the PLM itself to achieve "self-detoxification" they identify the toxification direction from the normal generation process to the one prompted with the negative prefix and then steer the generation to the reverse direction by manipulating the information movement within the attention layers. |
| Outcome: | The proposed method can achieve comparable performance with state-of-the-art methods without any fine-tuning or extra components. |
Gloss-Free End-to-End Sign Language Translation (2023.acl-long)
Copied to clipboard
| Challenge: | a study of sign language translation without gloss annotations focuses on the problem of gloss annotation . gloss annotation is hard to acquire, especially in large quantities, and limits the domain coverage of translation datasets . |
| Approach: | They propose a gloss-free end-to-end sign language translation framework to solve this problem . gloss annotations are hard to acquire, especially in large quantities, they argue . |
| Outcome: | The proposed framework improves sign language translation performance on large-scale datasets . gloss annotations are hard to acquire, especially in large quantities . |
Semantic-Space Exploration and Exploitation in RLVR for LLM Reasoning (2026.findings-acl)
Copied to clipboard
Fanding Huang, Guanbo Huang, Xiao Fan, Yi He, Xiao Liang, Xiao Chen, Qinting Jiang, Faisal Nadeem Khan, Jingyan Jiang, Zhi Wang
| Challenge: | Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have substantially improved the reasoning abilities of Large Language Models (LLMs). |
| Approach: | They propose a method that balances exploration and exploitation in the hidden-state space of response trajectories. |
| Outcome: | The proposed model yields consistent improvements across models, algorithms and reasoning benchmarks. |
Lightweight and Efficient Neural Natural Language Processing with Quaternion Networks (P19-1)
Copied to clipboard
| Challenge: | Existing models for natural language processing are heavily parameterized and memory inefficient. |
| Approach: | They propose a series of lightweight and memory efficient neural architectures for NLP tasks . they propose quaternion algebra and hypercomplex spaces for computation . |
| Outcome: | The proposed models enable expressive inter-component interactions and significantly reduce parameter size without loss of performance. |
Fin-STAR: Structure-as-Semantics to Resolve Implicitness in Financial Retrieval (2026.findings-acl)
Copied to clipboard
Yu Zou, Yan Chen, Lida He, Qi Zhou, Xiaorui Zhou, Aixi Zhong, Yi Wang, Wei Li, Qingyu Wang, Jiatao Li, Wei Gong, Jialei Zeng, Jingmei Zhao, Ke Jiang, Qing Li
| Challenge: | Existing Retrieval-Augmented Generation systems treat structure as a physical navigational skeleton rather than intrinsic semantic knowledge. |
| Approach: | They propose a framework that redefining hierarchy as intrinsic semantics and uses snippets to enrich hierarchical lineage. |
| Outcome: | The proposed framework outperforms state-of-the-art hierarchical and graph-based benchmarks on FinTierQA Gold. |
SeDev: Structured Semantic Exploration for LLM-Driven Code Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown remarkable capabilities in automating code generation, but they suffer from insufficient exploration of the vast solution space. |
| Approach: | They propose a large-scale LLM-driven code generation framework that efficiently finds high-quality solutions in only a few iterations. |
| Outcome: | The proposed framework outperforms baselines while maintaining reasonable time and computational costs. |
UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision (2026.acl-long)
Copied to clipboard
Zhen Fang, Ruiyan Han, XinYu Sun, Yuchen Ma, Ziheng Wang, Yu Zeng, Zehui Chen, Lin Chen, Wenxuan Huang, Wei-Jie Xu, Yi Cao, Feng Zhao
| Challenge: | Unified Multimodal Models have achieved remarkable success in cross-modal comprehension, but a gap persists in their ability to translate internal knowledge into faithful and controllable synthesis. |
| Approach: | They propose a self-improvement framework that partitions a single UMM into three collaborative roles: Proposer, Solver, and Judge. |
| Outcome: | The proposed framework improves on TIIF, DPG, CompBench and UniCycle benchmarks. |
Domain-Specific Data Generation Framework for RAG Adaptation (2026.findings-acl)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) combines the language understanding and reasoning capabilities of large language models (LLMs) with external retrieval to produce domain-grounded responses. |
| Approach: | They propose a scalable and modular data-centric framework for generating domain-grounded question–answer–context triples tailored to diverse RAG adaptation strategies. |
| Outcome: | The proposed framework generates domain-grounded question–answer–context triples for multiple RAG adaptation strategies. |
Graph-to-Tree Learning for Solving Math Word Problems (2020.acl-main)
Copied to clipboard
| Challenge: | Existing tree-based neural models do not capture the relationships and order information among the quantities well. |
| Approach: | They propose a novel deep learning architecture that combines the merits of the graph-based encoder and tree-based decoder to generate better solution expressions. |
| Outcome: | The proposed framework outperforms the state-of-the-art on two available datasets significantly. |
Fine-Grained Features-based Code Search for Precise Query-Code Matching (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods to locate code snippets from databases represent the semantics of code and query by averaging the features of each token and word. |
| Approach: | They propose a fine-grained code search model that consists of a cross-modal encoder, mapping layer and classification layer to capture fine-granular interactions between code and query. |
| Outcome: | The proposed model significantly outperforms existing methods across multiple programming language datasets. |
Chinese Inertial GAN for Handwriting Signal Generation and Recognition (2025.acl-long)
Copied to clipboard
| Challenge: | Inertial sensors can measure the acceleration and angular velocity of moving objects and are widely used in electronic devices such as smartphones, smartwatches, and fitness bands. |
| Approach: | They propose to use Chinese glyph encoding, forced optimal transport, and semantic relevance alignment to acquire unlimited training samples for Chinese inertial writing recognition. |
| Outcome: | The proposed system improves the performance of six widely used classifiers from 6.7% to 98.4%. |
Measuring and Mitigating Constraint Violations of In-Context Learning for Utterance-to-API Semantic Parsing (2023.findings-emnlp)
Copied to clipboard
| Challenge: | In task-oriented semantic parsing, the system aims to translate users’ utterances in natural language to machine-interpretable programs (API calls) However, Large Language Models (LLMs) are known to hallucinate and therefore pose a formidable challenge in constraining generated content. |
| Approach: | They propose to use large language models to translate user's utterances to machine-interpretable programs (API calls) they identify constraints violations in task-oriented utterrances and define fine-grained metrics that complement traditional ones. |
| Outcome: | The proposed methods reduce constraints violations and improve quality of the generated API calls, but require careful consideration given their implementation complexity and latency. |
Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States (2025.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks assess basic Theory of Mind abilities but neglect temporal evolution of mental states in real-world social contexts. |
| Approach: | They propose a benchmark specifically designed to evaluate Large Language Models' ability to understand and track the temporal progression of mental states across interconnected scenarios. |
| Outcome: | The proposed benchmarks underperform humans by 44.7% and show that they can model the dynamic nature of human mental states better than existing models. |
HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM (2024.naacl-long)
Copied to clipboard
Zhilin Wang, Yi Dong, Jiaqi Zeng, Virginia Adams, Makesh Narsimhan Sreedhar, Daniel Egert, Olivier Delalleau, Jane Scowcroft, Neel Kant, Aidan Swope, Oleksii Kuchaiev
| Challenge: | Existing helpfulness preference datasets do not specify what makes some responses more helpful and others less helpful. |
| Approach: | They use a dataset that has annotated for correctness, coherence, complexity, and verbosity. |
| Outcome: | The dataset has annotations for correctness, coherence, complexity, and verbosity in addition to overall helpfulness of responses. |
HVGuard: Utilizing Multimodal Large Language Models for Hateful Video Detection (2025.emnlp-main)
Copied to clipboard
Yiheng Jing, Mingming Zhang, Yong Zhuang, Jiacheng Guo, Juan Wang, Xiaoyang Xu, Wenzhe Yi, Keyan Guo, Hongxin Hu
| Challenge: | Existing methods for hateful video detection rely on unimodal analysis or feature fusion . Existing tools struggle to capture cross-modal interactions and reason through implicit hate in sarcasm and metaphor . |
| Approach: | They propose a reasoning-based hateful video detection framework with multimodal large language models . they integrate Chain-of-Thought reasoning to enhance multimodal interaction modeling . |
| Outcome: | The proposed framework outperforms existing tools on two public datasets covering English and Chinese. |
DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models (2025.emnlp-industry)
Copied to clipboard
Yi Shen, Jian Zhang, Jieyun Huang, Shuming Shi, Wenjing Zhang, Jiangze Yan, Ning Wang, Kai Wang, Zhaoxiang Liu, Shiguo Lian
| Challenge: | Recent advances in slow-thinking reasoning models have shown exceptional performance in complex reasoning tasks. |
| Approach: | They propose a framework that enables models to automatically adjust Chain-of-Thought (CoT) length based on problem difficulty. |
| Outcome: | The proposed framework penalizes inefficiency on simple problems while incentivizing deep reasoning for complex ones. |
SOAR: Supervision from Observation for Agentic Reinforcement Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Prior work assigns supervision based on outcome rewards or external reward models, but ignores environment observations, a critical source of learning. |
| Approach: | They propose a supervision-based agentic reinforcement learning system that integrates environment observations as an explicit supervision signal. |
| Outcome: | The proposed model improves performance on reasoning and deep research tasks while reducing erroneous and inefficient tool usage. |
AIGT: AI Generative Table Based on Prompt (2025.coling-main)
Copied to clipboard
| Challenge: | Tabular data is an essential resource for many fields, but current methods do not fully utilize the rich information available in tables. |
| Approach: | They propose a method that utilizes metadata information to generate tabular data . they propose long-token partitioning algorithms that enable AIGT to model tables of any scale . |
| Outcome: | The proposed approach achieves state-of-the-art on 14 out of 20 public datasets and two real industry datasets within the Alipay risk control system. |
Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study (2023.emnlp-main)
Copied to clipboard
Boxin Wang, Wei Ping, Peng Xu, Lawrence McAfee, Zihan Liu, Mohammad Shoeybi, Yi Dong, Oleksii Kuchaiev, Bo Li, Chaowei Xiao, Anima Anandkumar, Bryan Catanzaro
| Challenge: | a recent study shows that retrieval-augmented LMs can improve text generation quality and accuracy. |
| Approach: | They propose a model that reproduces RETRO parameters while retrieving a text corpus . they find RETRO outperforms GPT on text generation with less repetition . |
| Outcome: | The proposed model outperforms standard retrieval-augmented GPT and retrieval augmented GTP on text generation and accuracy tasks. |
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. |
FAIRGAMER: Evaluating Social Biases in LLM-Based Video Game NPCs (2026.acl-long)
Copied to clipboard
Bingkang Shi, Jen-tse Huang, Luo Long, Tianyu Zong, Hongzhu Yi, Yuanxiang Wang, Songlin Hu, Xiaodan Zhang, Zhongjiang Yao
| Challenge: | Large Language Models (LLMs) have enhanced or replaced traditional non-player characters in video games. |
| Approach: | They propose a benchmark to evaluate social biases across three interaction patterns: transaction, cooperation, and competition. |
| Outcome: | The proposed benchmark assesses four bias types across transaction, cooperation, and competition using a novel metric, FairMCV. |
MavenCoder: Competitive Code Generation via Model Adaptive Planning Strategies and Multi-Perspective Verification Enhancement (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have significantly enhanced automated program synthesis. |
| Approach: | They propose a model-adaptive and verification–enhanced framework for competition-level code generation that leverages adaptive assessment aligned with the model’s capabilities to select planning strategies while providing timely feedback and correction via multi-perspective verification. |
| Outcome: | The proposed framework outperforms existing state-of-the-art approaches on livecodebench, humanEval+, MBPP+, and codecontests, and achieves pass@1 results exceeding 3%–40%. |
Cognitive Alpha Mining via LLM-Driven Code-Based Evolution (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to finding effective predictive signals from financial data are limited by their complexity and low signal-to-noise ratio. |
| Approach: | They propose a framework that combines code-level alpha representation with LLM-driven reasoning and evolutionary search. |
| Outcome: | The proposed framework combines code-level alpha representation with LLM-driven reasoning and evolutionary search. |
MR-ALIGN: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models (2026.findings-acl)
Copied to clipboard
Xinming Wang, Jian Xu, Bin Yu, Sheng Lian, yi Chen, Boran Wang, Yingjian Zhu, Hongzhu Yi, Hong-Ming Yang, Han Hu, Cheng-Lin Liu, Xu-Yao Zhang
| Challenge: | Large reasoning models (LRMs) show strong capabilities in complex reasoning, yet their marginal gains on evidence-dependent factual questions are limited. |
| Approach: | They propose a Meta-Reasoning informed alignment framework that quantifies state-transition probabilities along the model’s thinking process and constructs a transition-aware implicit reward that reinforces beneficial reasoning patterns while suppressing defective ones at the atomic thinking segments. |
| Outcome: | Empirical evaluations of four factual QA datasets and one long-form factuality benchmark show that MR-ALIGN consistently improves accuracy and truthfulness while reducing misleading reasoning. |
Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Aspect-level sentiment classification (ALSC) is a practical setting in aspect-based sentiment analysis due to no opinion term labeling needed, but it fails to interpret why a sentiment polarity is derived for the aspect. |
| Approach: | They propose a span-based anti-bias aspect representation learning framework that eliminates the sentiment bias in the aspect embedding by adversarial learning against aspects’ prior sentiment. |
| Outcome: | The proposed framework achieves state-of-the-art performance on five benchmarks, with the capability of unsupervised opinion extraction. |
From Short Video to Clickable Search: RLVR-Enabled Listwise Query Suggestion with Retrieval-Augmented Context (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing methods to generate short-video bottom-bar queries are largely retrieval-based. |
| Approach: | They propose to reformulate the task as one-shot list generation, producing multiple queries per video . they also build multi-query ground truth from exposure and CTR logs, and redesign offline evaluation . |
| Outcome: | The proposed system yields strong offline and online improvements . it is deployed on Kuaishou to serve hundreds of millions of users daily . |
WebSynthesis: World Model-Guided Monte Carlo Tree Search for Efficient WebAgent Trajectory Synthesis (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models have enabled increasingly capable web agents . however, training such agents at scale still relies on high-quality interaction trajectories that are difficult to obtain at scale. |
| Approach: | They propose a framework for scalable trajectory synthesis that simulates state transitions without network dependencies and integrates Monte Carlo Tree Search to enable reversible exploration over the simulated state space. |
| Outcome: | Experiments on WebArena, WebVoyager, and Mind2Web-Online show that agents trained exclusively on synthesized trajectories outperform those trained on real-world data. |
A Study of Syntactic Multi-Modality in Non-Autoregressive Machine Translation (2022.naacl-main)
Copied to clipboard
| Challenge: | Non-autoregressive translation models suffer from the multi-modality problem when a source sentence corresponds to multiple correct translations. |
| Approach: | They propose to decompose the syntactic multi-modality problem into short- and long-range models and evaluate them on synthesized and real datasets. |
| Outcome: | The proposed loss functions can handle short- and long-range syntactic multi-modalities better than existing models. |
NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism (2024.acl-long)
Copied to clipboard
Miao Li, Ming-Bin Chen, Bo Tang, ShengbinHou ShengbinHou, Pengyu Wang, Haiying Deng, Zhiyu Li, Feiyu Xiong, Keming Mao, Cheng Peng, Yi Luo
| Challenge: | a novel evaluation framework assesses the capabilities of Large Language Models (LLMs) for editorial capabilities in Chinese journalism. |
| Approach: | They propose to use a benchmark dataset to assess the capabilities of Large Language Models (LLMs) for editorial capabilities in Chinese journalism. |
| Outcome: | The proposed evaluation framework is based on a dataset of 1,267 test samples in 24 news domains. |
EAVE: Efficient Product Attribute Value Extraction via Lightweight Sparse-layer Interaction (2024.findings-emnlp)
Copied to clipboard
Li Yang, Qifan Wang, Jianfeng Chi, Jiahao Liu, Jingang Wang, Fuli Feng, Zenglin Xu, Yi Fang, Lifu Huang, Dongfang Liu
| Challenge: | Existing methods to extract product attribute value require multiple extractions to obtain all corresponding values. |
| Approach: | They propose an Efficient product Attribute Value Extraction approach using lightweight sparse-layer interaction. |
| Outcome: | The proposed method achieves significant efficiency gains with neutral or marginal loss in performance when the context is long and number of attributes is large. |
DroidCall: A Dataset for LLM-powered Android Intent Invocation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | We present DroidCall, the first training and testing dataset for accurate Android intent invocation. |
| Approach: | We introduce DroidCall, the first training and testing dataset for accurate Android intent invocation. |
| Outcome: | The proposed dataset provides a training and testing pipeline for Android intent invocation. |
Towards Better Entity Linking with Multi-View Enhanced Distillation (2023.acl-long)
Copied to clipboard
Yi Liu, Yuan Tian, Jianxun Lian, Xinlong Wang, Yanan Cao, Fang Fang, Wen Zhang, Haizhen Huang, Weiwei Deng, Qi Zhang
| Challenge: | Entity linking is a fundamental task in Natural Language Processing (NLP), connecting mentions within unstructured contexts to their corresponding entities in a Knowledge Base (KB). |
| Approach: | They propose a dual-encoder framework that can efficiently match mentions to two-encoding frameworks by a global-view. |
| Outcome: | The proposed framework achieves state-of-the-art on several entity linking benchmarks. |
CharacterGLM: Customizing Social Characters with Large Language Models (2024.emnlp-industry)
Copied to clipboard
Jinfeng Zhou, Zhuang Chen, Dazhen Wan, Bosi Wen, Yi Song, Jifan Yu, Yongkang Huang, Pei Ke, Guanqun Bi, Libiao Peng, JiaMing Yang, Xiyao Xiao, Sahand Sabour, Xiaohan Zhang, Wenjing Hou, Yijia Zhang, Yuxiao Dong, Hongning Wang, Jie Tang, Minlie Huang
| Challenge: | Character-based dialogue systems (CharacterDial) allow users to customize social characters for social interactions. |
| Approach: | They will collect a large-scale Chinese corpus of characters with diverse categories and behaviors and develop CharacterGLM models to address these challenges. |
| Outcome: | Experiments show that CharacterGLM outperforms most popular open- and closed-source LLMs and performs comparable to GPT-4. |
Target-oriented Proactive Dialogue Systems with Personalization: Problem Formulation and Dataset Curation (2023.emnlp-main)
Copied to clipboard
| Challenge: | a recent study defines a conversation target from the system side to proactively steer conversations toward predefined targets or accomplish specific system-side goals. |
| Approach: | They propose a dataset curation framework that automatically curations a large-scale personalized dialogue dataset using a role-playing approach. |
| Outcome: | The proposed dataset is of high quality and could contribute to exploring personalized target-oriented dialogue. |
GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent reinforcement learning approaches have advanced reasoning in Large Language Models (LLMs), yet their adaptation to multimodal LLMs remains underexplored. |
| Approach: | They propose a reinforcement learning framework that eliminates KL penalties and rewards consistency . they propose GRPO-CARE, which outperforms standard GR PO, with a base reward for accuracy and an adaptive bonus for consistency. |
| Outcome: | The proposed framework outperforms standard GRPO on the most difficult evaluation level and reasoning consistency test benchmarks. |
FlattenQuant: Breaking through the Inference Compute-bound for Large Language Models with Per-tensor Quantization (2024.lrec-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated state-of-the-art accuracies across tasks, but their latency and GPU memory consumption limit their performance. |
| Approach: | They propose a method which flattens the tensor to achieve low bit per-tensori quantization with minimal accuracy loss. |
| Outcome: | The proposed method achieves low bit per-tensor quantization with minimal accuracy loss. |
MicroEdit: Neuron-level Knowledge Disentanglement and Localization in Lifelong Model Editing (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for enhancing large language models are designed for single or limited edits, lacking the capacity to support long-term, multi-round knowledge updates. |
| Approach: | They propose a neuron-level editing method that performs minimal interventions within large language models (LLMs) by leveraging a sparse autoencoder, MicroEdit disentangles knowledge representations and activates only a minimal set of necessary neurons for precise parameter updates. |
| Outcome: | Extensive experiments show that MicroEdit outperforms prior methods and robustly handles lifelong knowledge editing across QA and Hallucination settings on LLaM and Mistral. |
FlipGuard: Defending Preference Alignment against Update Regression with Constrained Optimization (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in preference alignment have significantly improved Large Language Models' ability to generate texts that align with human preferences and values. |
| Approach: | They propose a constrained optimization approach to detect and mitigate update regression with focal attention. |
| Outcome: | The proposed approach detects and mitigates update regression with focal attention while maintaining excellent overall performance. |
OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (2025.acl-long)
Copied to clipboard
Xueyu Hu, Tao Xiong, Biao Yi, Zishu Wei, Ruixuan Xiao, Yurun Chen, Jiasheng Ye, Meiling Tao, Xiangxin Zhou, Ziyu Zhao, Yuhuai Li, Shengze Xu, Shenzhi Wang, Xinchen Xu, Shuofei Qiao, Zhaokai Wang, Kun Kuang, Tieyong Zeng, Liang Wang, Jiwei Li, Yuchen Eleanor Jiang, Wangchunshu Zhou, Guoyin Wang, Keting Yin, Zhou Zhao, Hongxia Yang, Fan Wu, Shengyu Zhang, Fei Wu
| Challenge: | a new generation of (M)LLMs is enabling the creation of superintelligent AI assistants . OS Agents can complete tasks autonomously and have the potential to significantly enhance the lives of billions of users worldwide. |
| Approach: | They propose to build OS Agents that operate within operating systems' GUIs and GUIs . they examine evaluation metrics and benchmarks to identify promising directions . |
| Outcome: | The proposed agents are based on operating systems (OS) and operating systems frameworks. |
OAgents: An Empirical Study of Building Effective Agents (2025.findings-emnlp)
Copied to clipboard
He Zhu, Tianrui Qin, King Zhu, Heyuan Huang, Yeyi Guan, Jinxiang Xia, Hanhao Li, Yi Yao, Ningning Wang, Pai Liu, Tianhao Peng, Xin Gui, Li Xiaowan, Yuhui Liu, Xiangru Tang, Jian Yang, Ge Zhang, Xitong Gao, Yuchen Eleanor Jiang, Changwang Zhang, Jun Wang, Jiaheng Liu, Wangchunshu Zhou
| Challenge: | a recent study shows that agent research practices are far from standard, rigorous . lack of a standard evaluation protocol makes previous works not reproducible, authors say . |
| Approach: | They conduct an empirical study on the GAIA benchmark to investigate agent design choices . they find that lack of a standard evaluation protocol makes previous works not reproducible . |
| Outcome: | The proposed framework achieves state-of-the-art performance among open-source projects. |
Retrieval-free Knowledge Injection through Multi-Document Traversal for Dialogue Models (2023.acl-long)
Copied to clipboard
Rui Wang, Jianzhu Bao, Fei Mi, Yi Chen, Hongru Wang, Yasheng Wang, Yitong Li, Lifeng Shang, Kam-Fai Wong, Ruifeng Xu
| Challenge: | Existing research on retrieval-augmented and retrieval free dialogue models focuses on retrieving knowledge from external sources and rely on finely annotated retrieval training data and knowledge-grounded responses. |
| Approach: | They propose a retrieval-free approach by turning knowledge documents into simulated multi-turn dialogues using a Multi-Document Traversal algorithm. |
| Outcome: | The proposed approach outperforms retrieval-augmented models while being cheaper and faster at domain transfer. |
Do Code Semantics Help? A Comprehensive Study on Execution Trace-Based Information for Code Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Code Large Language Models have limited ability to reason about runtime behavior and understand functionality . authors present a generic framework to support integrating semantic information to code task-relevant prompts . |
| Approach: | a study examines the role of trace-based semantic information in boosting supervised fine-tuning and post-phase inference of Code LLMs. |
| Outcome: | a new framework integrates semantic information to code task-relevant prompts . the proposed framework shows that trace-based semantic information boosts reasoning ability . |
LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for implementing large language models are limited by high computational and memory requirements. |
| Approach: | They propose a lightweight binarization framework that achieves effective W(1+1)A4 quantization through a novel three-stage quantization strategy. |
| Outcome: | The proposed framework surpasses state-of-the-art methods on W2A4 quantization settings across languages. |
An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint (2025.emnlp-main)
Copied to clipboard
Yi Sun, Han Wang, Jiaqiang Li, Jiacheng Liu, Xiangyu Li, Hao Wen, Yizhen Yuan, Huiwen Zheng, Yan Liang, Yuanchun Li, Yunxin Liu
| Challenge: | Large Language Models (LLMs) are a powerful tool for test-time scaling, but they are often used under time constraints. |
| Approach: | They propose to use LLMs to make models think before answering questions . they also use self-correction and best-of-N decoding to encourage deeper thinking . |
| Outcome: | The proposed models are able to achieve higher inference accuracy with extra inference computation under time constraints. |
Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent work has shown that pruning can reduce model performance, but it can also lead to degradation in safety performance. |
| Approach: | They propose a hierarchical safety realignment approach to prune large vision-Language Models . they quantify contribution of each attention head to safety and restore neurons . |
| Outcome: | The proposed approach achieves significant safety improvements in LVLMs pruned post pruning. |
IoTMigrator: LLM-driven Embedded IoT Code Migration across Different OSes for Cloud-device Integration (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Neither outline-based code generation nor common code translation techniques can adequately address this challenge, despite their prevalence in existing systems. |
| Approach: | They have developed an algorithm that employs a multi-agent pipeline to handle embedded code migration under the TSL paradigm. |
| Outcome: | The proposed algorithm outperforms the baseline by 50.5% for pass rate and 13.0% for completeness across all tasks in RIOT and Zephyr. |
PaperRobot: Incremental Draft Generation of Scientific Ideas (P19-1)
Copied to clipboard
| Challenge: | a paper robot can read existing papers and create new nodes or links in the knowledge graphs. |
| Approach: | They propose to automate the creation of new ideas by predicting links from the background KGs. |
| Outcome: | The proposed paper automates three tasks: read existing papers, create new ideas, predict links . the paper generated abstracts, conclusion and future work sections, and new titles are chosen over human-written ones up to 30%, 24% and 12% of the time. |
VLMInferSlow: Evaluating the Efficiency Robustness of Large Vision-Language Models as a Service (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies evaluate efficiency robustness of vision-language models under unrealistic assumptions, requiring access to model architecture and parameters. |
| Approach: | They propose a novel approach to evaluate VLM efficiency robustness in a realistic black-box setting. |
| Outcome: | The proposed approach generates adversarial images with imperceptible perturbations, increasing the computational cost by up to 128.47%. |
Role Prompting Guided Domain Adaptation with General Capability Preserve for Large Language Models (2024.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) suffer catastrophic forgetting when tailored to specific domains . authors present a novel approach to manage multi-domain LLM adaptation . |
| Approach: | They propose a strategy to manage multi-domain LLM adaptation using self-distillation and role integration. |
| Outcome: | The proposed model alleviates catastrophic forgetting and inter-domain confusion while maintaining robust general capabilities. |
Chain-of-Question: A Progressive Question Decomposition Approach for Complex Knowledge Base Question Answering (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to answer complex questions rely on decomposition of complex questions into sub-questions . Existing approaches to decompose complex questions are limited by the original question . |
| Approach: | They propose a question decomposition approach to decompose semantically clear questions . they use the decomposed sub-questions to select relevant patterns as auxiliary information . |
| Outcome: | The proposed method achieves state-of-the-art performance on multiple datasets. |
Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Empirical results show misalignment at greater reasoning depths is driven mainly by alignment errors such as thematic shift and redundant reasoning. |
| Approach: | They propose a method to quantitatively assess the alignment between multi-step, structured reasoning in large language models and human preferences by constructing semantic-entropy-based matrices over intermediate steps and measuring their divergence. |
| Outcome: | The proposed method shows that it is consistent with previous studies and can be used as a diagnostic signal. |
A Novel Cascade Binary Tagging Framework for Relational Triple Extraction (2020.acl-main)
Copied to clipboard
| Challenge: | Existing approaches to extract relational triples from unstructured text are inadequate to solve the overlapping triple problem. |
| Approach: | They propose a cascade binary tagging framework that models relations as functions that map subjects to objects in a sentence. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on two datasets . it outperformed baseline methods by 17.5 and 30.2 absolute gains . |
OneRec-Think: In-Text Reasoning for Generative Recommendation (2026.acl-long)
Copied to clipboard
Zhanyu Liu, Shiyao Wang, Xingmei Wang, Rongzhou Zhang, Jiaxin Deng, Honghui Bao, Jinghao Zhang, Wuchao Li, PengFei Zheng, Xiangyu Wu, Yifei Hu, Qigen Hu, Xinchen Luo, Lejian Ren, Zhang Zixing, Qianqian Wang, Kuo Cai, Yunfan Wu, Hongtao Cheng, Zexuan Cheng, Lu Ren, Huanjie Wang, Yi Su, Ruiming Tang, Kun Gai, Guorui Zhou
| Challenge: | Existing generative models lack the capacity for explicit and controllable reasoning, a key advantage of LLMs. |
| Approach: | They propose a framework that integrates dialogue, reasoning, and personalized recommendation. |
| Outcome: | Experiments across public benchmarks show state-of-the-art performance. |
Investigating Human and LLMs’ Decisions in Unverifiable Environments: A Case Study with GitHub Activity Overview (2026.findings-acl)
Copied to clipboard
| Challenge: | examining the behaviors of Large Language Models as artificial social actors is underexplored, especially in unverifiable scenarios where conventional benchmarking has little to help improve their abilities. |
| Approach: | They propose a method to collect, compare, and reason about human and LLMs' decisions in an unverifiable scenario and use it to examine their behaviors. |
| Outcome: | The proposed method compared human and LLM decisions in an unverifiable scenario on GitHub and found that proprietary LLMs behave more like humans than open-source LLM systems. |
Improving Entity Linking through Semantic Reinforced Entity Embeddings (2020.acl-main)
Copied to clipboard
| Challenge: | Existing entity embeddings are effective, but too distinctive for linking models to learn contextual commonality. |
| Approach: | They propose a method to inject fine-grained semantic information into entity embeddings . they use word embedds of type words to generate semantic embeddngs based on existing embeddables a sample of semantic information is injected into the embedded entities . |
| Outcome: | The proposed method reduces the distinctiveness of existing embeddings and improves performance. |
Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning (2024.findings-acl)
Copied to clipboard
Kung-Hsiang Huang, Mingyang Zhou, Hou Pong Chan, Yi Fung, Zhenhailong Wang, Lingyu Zhang, Shih-Fu Chang, Heng Ji
| Challenge: | LVLMs are known for producing text that is factually inconsistent with visual input . factuality of generated captions for structured visuals has not been studied as much . |
| Approach: | They propose a typology of factual errors in captions generated by large vision-language models . they propose CHOCOLATE, a visual entailment model that outperforms current models based on this analysis . |
| Outcome: | The proposed model outperforms current models in evaluating caption factuality. |
UMPIRE: Unveiling LLM-generated Posts via Redundant Expressions (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods to verify the provenance of multimodal content fall into two categories: traditional methods rely on low-level artifacts or unimodal statistics. |
| Approach: | They propose a semantic decomposition mechanism that disentangles textual embeddings into redundant and complementary components and a latent redundancy regularization loss to encourage LLM-generated content to exhibit high semantic redundancies. |
| Outcome: | The proposed method outperforms state-of-the-art detection methods across multiple datasets and achieves 5.38% improvement in accuracy. |
DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for enhancing large language models (LLMs) lack explicit mechanisms for guiding diverse exploration and instead prioritize efficiency and performance over diversity. |
| Approach: | They propose a reinforcement learning-based framework that decomposes the generation process into explicitly planned intermediate steps and introduces divergence at the planning phase based on diversity variation. |
| Outcome: | The proposed method significantly outperforms existing baselines on creative writing benchmarks on a semi-structured long chain-of-thought (CoT) it introduces divergence at the planning phase based on diversity variation, alongside a group-aware diversity reward to encourage distinct trajectories. |
SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF (2023.findings-emnlp)
Copied to clipboard
| Challenge: | supervised fine-tuning and reinforcement learning from human feedback (RLHF) are not effective in generating useful and high-quality responses. |
| Approach: | They propose a supervised fine-tuning method that empowers end-users to control responses during inference. |
| Outcome: | Experiments show that supervised fine-tuning and reinforcement learning from human feedback (RLHF) can generate helpful and high-quality responses while maintaining customizability. |
Automated Tone Transcription and Clustering with Tone2Vec (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Lexical tones play a crucial role in Sino-Tibetan languages, but current phonetic fieldwork relies on manual effort. |
| Approach: | They propose a pitch-based similarity representations for tone transcription called Tone2Vec . they propose an open-source package that facilitates automated fieldwork and analysis . |
| Outcome: | Experiments on dialect clustering and variance show that Tone2Vec captures fine-grained tone variation. |
Generative Personality Simulation via Theory-Informed Structured Interview (2026.eacl-long)
Copied to clipboard
Pengda Wang, Huiqi Zou, Han Jiang, Hanjie Chen, Tianjun Sun, Xiaoyuan Yi, Ziang Xiao, Frederick L. Oswald
| Challenge: | Personality structured interviews are often lacking in advancing social science research. |
| Approach: | They propose a method to incorporate psychological insights into LLM simulations . they use a measure theory grounded evaluation procedure to evaluate reliability and validity . |
| Outcome: | The proposed method improves human-like heterogeneity in LLM-simulated personality data and predicts personality-related behavioral outcomes. |
TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents (2026.findings-acl)
Copied to clipboard
Kai Li, Xuanqing Yu, Ziyi Ni, Yi Zeng, Yao Xu, Zheqing Zhang, Xin Li, Jitao Sang, Xiaogang Duan, Xuelei Wang, Chengbao Liu, Jie Tan
| Challenge: | Existing memory frameworks provide limited support for temporally structured information across hierarchical levels, leading to fragmented memories and unstable long-horizon personalization. |
| Approach: | They propose a temporal–hierarchical memory framework that organizes conversations through a Temporal Memory Tree. |
| Outcome: | The proposed framework outperforms baselines while reducing the recalled memory length by 52.20%. |
ReviewGrounder: Improving Review Substantiveness with Rubric-Guided, Tool-Integrated Agents (2026.acl-long)
Copied to clipboard
Zhuofeng Li, Yi Lu, Dongfu Jiang, Haoxiang Zhang, Yuyang Bai, Chuan Li, Yu Wang, Shuiwang Ji, Jianwen Xie, Yu Zhang
| Challenge: | Rapid rise in AI conference submissions has driven increasing exploration of large language models (LLMs) for peer review support. |
| Approach: | They propose a peer review benchmarking tool based on paper-specific rubrics and a rubric-guided framework that decomposes reviewing into drafting and grounding stages. |
| Outcome: | The proposed framework outperforms baselines with stronger/larger backbones in both alignment with human judgments and rubric-based review quality across 8 dimensions. |
DP-CRE: Continual Relation Extraction via Decoupled Contrastive Learning and Memory Structure Preservation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for learning relational knowledge are replay-based and prioritize data uniformly . a pronounced bias towards new tasks can be caused by the introduction of new tasks . |
| Approach: | They propose a framework that decouples the process of prior information preservation and new knowledge acquisition. |
| Outcome: | Extensive experiments show that the framework outperforms baselines across two datasets. |
AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing (2023.findings-acl)
Copied to clipboard
Asaad Alghamdi, Xinyu Duan, Wei Jiang, Zhenhai Wang, Yimeng Wu, Qingrong Xia, Zhefeng Wang, Yi Zheng, Mehdi Rezagholizadeh, Baoxing Huai, Peilun Cheng, Abbas Ghaddar
| Challenge: | Developing monolingual large Pre-trained Language Models (PLMs) is shown to be very successful in handling different tasks in Natural Language Processing (NLP). |
| Approach: | They present AraMUS, the largest Arabic PLM with 11B parameters trained on 529GB of high-quality Arabic textual data. |
| Outcome: | The proposed model achieves state-of-the-art performance on a diverse set of Arabic classification and generative tasks. |
Towards Unified Representations of Knowledge Graph and Expert Rules for Machine Learning and Reasoning (2022.aacl-main)
Copied to clipboard
| Challenge: | Empirical study shows superiority of proposed method over time-tested knowledge-driven and data-driven methods. |
| Approach: | They propose a cognitive knowledge graph that unifies expert rules and relational facts as the substrate of machine learning and reasoning models. |
| Outcome: | Empirical results show the proposed method superior to time-tested methods . the proposed model can perform both learning and reasoning with labeled data . |
DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation (2022.acl-long)
Copied to clipboard
Wei Chen, Yeyun Gong, Song Wang, Bolun Yao, Weizhen Qi, Zhongyu Wei, Xiaowu Hu, Bartuer Zhou, Yi Mao, Weizhu Chen, Biao Cheng, Nan Duan
| Challenge: | Existing pre-trained dialog models shed light on various downstream tasks in natural language processing (NLP). |
| Approach: | They propose a dialog pre-training framework that introduces latent variables into the enhanced encoder-decoder pre-train framework to increase relevance and diversity of responses. |
| Outcome: | The proposed model achieves state-of-the-art on personaChat, DailyDialog, and DSTC7-AVSD datasets. |
SEARCH-R: Structured Entity-Aware Retrieval with Chain-of-Reasoning Navigator for Multi-hop Question Answering (2026.findings-acl)
Copied to clipboard
FU Yuqing, Yimin Deng, Wanyu Wang, Yuhao Wang, Yejing Wang, Hongshi Liu, Yiqi Wang, Xiao Han, Maolin Wang, Guoshuai Zhao, Yi Chang, Xiangyu Zhao
| Challenge: | Existing approaches to multi-hop question answering lack effective control over reasoning paths, leading to astray results. |
| Approach: | They propose a framework for multi-hop question answering that trains an end-to-end reasoning path navigator to provide a powerful sub-question decomposer by fine-tuning the Llama3.1-8B model. |
| Outcome: | The proposed framework trains an end-to-end reasoning path navigator . it is able to provide a powerful sub-question decomposer by fine-tuning the Llama3.1-8B model . |
TextObfuscator: Making Pre-trained Language Model a Privacy Protector via Obfuscating Word Representations (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing inference services are plagued by privacy concerns, such as sharing sensitive data with service providers. |
| Approach: | They propose a framework for protecting inference privacy by applying random perturbations to clustered representations. |
| Outcome: | The proposed framework protects inference privacy by applying random perturbations to clustered representations. |
Evolutionary Negative Module Pruning for Better LoRA Merging (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for integrating multiple low-rank Adaptation experts into a single backbone are limited by negative modules. |
| Approach: | They propose a plug-and-play LoRA pruning method to locate and exclude negative modules prior to merging. |
| Outcome: | The proposed method boosts the performance of existing merging algorithms across languages and vision domains. |
LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics (2026.findings-acl)
Copied to clipboard
| Challenge: | Current research hinders the development of unified Time Series Reasoning Models (TSRMs) time series data are a fundamental modality for capturing the temporal dynamics of complex systems. |
| Approach: | They propose a time series reasoning model that integrates visualized patterns with precision-calibrated numerical tables to enhance the temporal perception of Vision-Language Models. |
| Outcome: | The proposed model outperforms existing models and exhibits robust out-of-distribution generalization across diverse tasks and real-world scenarios. |
Transformer-based Speech Model Learns Well as Infants and Encodes Abstractions through Exemplars in the Poverty of the Stimulus Environment (2025.coling-main)
Copied to clipboard
| Challenge: | Existing theories of language learning for infants are inadequate, according to Chomsky . infants learn language in impoverished environments, according a new study . |
| Approach: | They designed a series of tasks, scenarios, and metrics to simulate the POS . they found that the emerging speech model wav2vec2.0 can learn well in noisy Mandarin environments. |
| Outcome: | The proposed model can learn in noisy and sparse Mandarin environments. |
Diverse Few-Shot Text Classification with Multiple Metrics (N18-1)
Copied to clipboard
Mo Yu, Xiaoxiao Guo, Jinfeng Yi, Shiyu Chang, Saloni Potdar, Yu Cheng, Gerald Tesauro, Haoyu Wang, Bowen Zhou
| Challenge: | Existing methods for few-shot learning are insufficient to capture task variations in natural language domains. |
| Approach: | They propose an adaptive metric learning approach that automatically determines the best weighted combination from a set of metrics obtained from meta-training tasks for a newly seen few-shot task. |
| Outcome: | The proposed method performs favorably against state-of-the-art few shot learning algorithms on real-world sentiment analysis and dialog intent classification datasets. |
ReAugKD: Retrieval-Augmented Knowledge Distillation For Pre-trained Language Models (2023.acl-short)
Copied to clipboard
Jianyi Zhang, Aashiq Muhamed, Aditya Anantharaman, Guoyin Wang, Changyou Chen, Kai Zhong, Qingjun Cui, Yi Xu, Belinda Zeng, Trishul Chilimbi, Yiran Chen
| Challenge: | Knowledge distillation (KD) is an effective compression technique to derive a smaller student model from a larger teacher model by transferring the knowledge embedded in the teacher's network. |
| Approach: | They propose a framework and loss function that preserves the semantic similarities of teacher and student training examples to enable the student to retrieve from the knowledge base effectively. |
| Outcome: | The proposed framework preserves the semantic similarities of teacher and student training examples to achieve state-of-the-art performance on the GLUE benchmark. |