Papers by Shuo Yang
Exploring the Impact of Personality Traits on LLM Toxicity and Bias (2025.emnlp-main)
Copied to clipboard
| Challenge: | anthropomorphic LLMs are being developed to serve diversified roles, but content safety concerns remain regarding their toxicity and toxicity. |
| Approach: | They propose to assign personality traits to large language models (LLMs) to reduce toxic language and social biases in their outputs by using the widely accepted HEXACO personality framework developed in social psychology. |
| Outcome: | The proposed model is able to perform on three toxic and bias benchmarks and shows that assigning personality traits reduces bias and toxicity similar to humans’ correlations between personality traits and toxic behaviors. |
OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory (2026.acl-long)
Copied to clipboard
| Challenge: | Existing LLMs are limited by text-context budgets, resulting in token-expensive storage of raw trajectories . Optical Context Retrieval Memory (OCR-Memory) renders historical tra-jectorios into images annotated with unique visual identifiers. |
| Approach: | They propose a framework that leverages the visual modality as a high-density representation of agent experience. |
| Outcome: | Optical Context Retrieval Memory (OCRM) renders historical trajectories into images annotated with unique visual identifiers. |
On LLM-Based Scientific Inductive Reasoning Beyond Equations (2025.emnlp-main)
Copied to clipboard
Brian S. Lin, Jiaxin Yuan, Zihan Zhou, Shouli Wang, Shuo Wang, Cunliang Kong, Qi Shi, Yuxuan Li, Liner Yang, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing research on inductive reasoning models emphasizes rule design without grounding them in specific scenarios. |
| Approach: | They propose to use LLMs to learn underlying patterns from limited examples in entirely new environments. |
| Outcome: | The proposed benchmark evaluates the inductive reasoning abilities of large language models in scientific settings. |
MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators (2022.acl-long)
Copied to clipboard
| Challenge: | Prompting has been shown to be a promising approach for applying pre-trained language models to perform downstream tasks. |
| Approach: | They propose a method that divides the translation process into three stages using pre-trained language models. |
| Outcome: | The proposed method significantly improves translation performance of pre-trained language models on three translation tasks. |
MCTS: A Multi-Reference Chinese Text Simplification Dataset (2024.lrec-main)
Copied to clipboard
Ruining Chong, Luming Lu, Liner Yang, Jinran Nie, Zhenghao Liu, Shuo Wang, Shuhan Zhou, Yaoxin Li, Erhong Yang
| Challenge: | Existing studies on text simplification systems have focused on unsupervised methods due to the limited evaluation data in language and domain. |
| Approach: | They propose a Chinese text simplification dataset that provides a detailed analysis and an annotation process. |
| Outcome: | The proposed dataset evaluates the performance of unsupervised methods and advanced large language models. |
CURE: Controlled Unlearning for Robust Embeddings — Mitigating Conceptual Shortcuts in Pre-Trained Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models are susceptible to spurious, concept-driven correlations that impair robustness and fairness. |
| Approach: | They propose a framework that disentangles and suppresses conceptual shortcuts while preserving essential content information. |
| Outcome: | The proposed framework improves on IMDB and Yelp datasets with minimal computational overhead. |
ATFormer: A Learned Performance Model with Transfer Learning Across Devices for Deep Learning Tensor Programs (2023.emnlp-main)
Copied to clipboard
| Challenge: | Compilation-based methods with performance models have poor measurement accuracy and transferability between platforms. |
| Approach: | They propose a compiler that automatically generates tensors and automatically tunes them for different hardware platforms. |
| Outcome: | The proposed model reduces inference time and costs on modern DNN benchmarks. |
Improving Back-Translation with Uncertainty-based Confidence Estimation (D19-1)
Copied to clipboard
| Challenge: | Despite the success of low-resource neural machine translation, there is a data scarcity problem in many languages . large-scale, high-quality, and widecoverage bilingual corpora do not exist for most language pairs . |
| Approach: | They propose to quantify confidence of NMT models based on model uncertainty . they propose to use uncertainty-based confidence measures to improve back-translation . |
| Outcome: | The proposed model outperforms conventional statistical machine translation (SMT) on Chinese-English and English-German translation tasks. |
Teaching Vision-Language Models to Ask: Resolving Ambiguity in Visual Questions (2025.acl-long)
Copied to clipboard
| Challenge: | Existing research addresses ambiguous visual questions by rephrasing questions, but it fails to address the inherently interactive nature of user interactions with visual language models (VLMs). Existing studies focus on re-phrase questions, and lack of a benchmark to assess VLMs’ capacity for resolving ambiguities through interaction. |
| Approach: | They propose a visual question answering task that provides a natural language answer to a question based on a given image and an automated pipeline to generate ambiguity-clarification question pairs. |
| Outcome: | The proposed benchmark targets three common categories of ambiguity in visual question answering (VQA) context and encompasses various VQA scenarios. |
DAEA: Enhancing Entity Alignment in Real-World Knowledge Graphs Through Multi-Source Domain Adaptation (2025.coling-main)
Copied to clipboard
| Challenge: | Entity Alignment (EA) is a critical task in Knowledge Graph (KG) integration. |
| Approach: | They propose a novel approach that leverages the data characteristics of synthetic benchmarks to improve performance in real-world datasets. |
| Outcome: | The proposed approach outperforms state-of-the-art models on real-world datasets and achieves a 29.94% improvement in Hits@1 on DOREMUS and 5.64% improvement on AGROLD. |
Large-Scale Multimodal Knowledge Graph about Classical Chinese Poetry: Fine-grained Method and Comprehensive Evaluation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on classical Chinese poetry are limited by modality constraints, dataset size, or the level of refinement. |
| Approach: | They propose to construct a large-scale and fine-grained multimodal knowledge graph of classical Chinese poetry using an informative ontology graph and a text-image alignment method. |
| Outcome: | The proposed method collects knowledge about classical Chinese poetry from ontology graphs and performs four tasks that demonstrate its comprehensiveness and high quality. |
Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have impressive moral reasoning abilities, yet they often diverge when confronted with complex, multi-factor moral dilemmas. |
| Approach: | They propose a framework that synthesizes multiple LLMs’ moral judgments into a collectively formulated moral judgment, realigning models that deviate significantly from this consensus. |
| Outcome: | The proposed framework synthesizes multiple LLMs’ moral judgments into a collectively formulated moral judgment, realigning models that deviate significantly from this consensus. |
MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing Large Vision-Language Models (LVLMs) lack integrated commonsense knowledge . lack of integrated common knowledge limits their robustness and accuracy in VQA . |
| Approach: | They propose a framework to enhance multimodal inference by integrating commonsense reasoning. |
| Outcome: | MAGIC-VQA improves comprehensive benchmark datasets, surpassing existing models in tasks requiring advanced commonsense reasoning. |
SPARK: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for training large language models waste computation budget on trivial steps while failing to guarantee sample quality. |
| Approach: | They propose a framework that selectively branches at critical decision states for resource-efficient exploration. |
| Outcome: | The proposed framework activates adaptive branching exploration at critical decision states to probe promising trajectories, thereby achieving precise resource allocation that prioritizes sampling quality over blind coverage. |
PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning (2026.findings-acl)
Copied to clipboard
Ruixiang Feng, Yuntao Wen, Silin Zhou, Ke Shi, Yifan Wang, Ran Le, Zhenwei An, Zongchao Chen, Chen Yang, Guangyue Peng, Yiming Jia, Dongsheng Wang, Tao Zhang, Lisi Chen, Yang Song, Shen Gao, Shuo Shang
| Challenge: | Existing LRMs often suffer from "overthinking" and excessively long reasoning traces . a dual-level framework for length compression of LRM is proposed . |
| Approach: | They propose a framework for prefix-protected and difficulty-aware compression under hierarchical supervision. |
| Outcome: | The proposed framework reduces token usage while improving accuracy on math benchmarks. |
Is Crowdsourcing Breaking Your Bank? Cost-Effective Fine-Tuning of Pre-trained Language Models with Proximal Policy Optimization (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to improve language models require manual ranking and annotators. |
| Approach: | They propose a self-supervised text ranking approach for applying Proximal-Policy-Optimization to fine-tune language models while eliminating the need for human annotators. |
| Outcome: | The proposed method significantly outperforms baselines regarding BLEU, GLEU, and METEOR scores on three tasks and is consistent with humans. |
MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking, which can elicit harmful or unsafe behaviors. |
| Approach: | They propose a multilingual guardrail with reasoning for prompt classification that integrates culturally and linguistically nuanced variants and supervised fine-tuning. |
| Outcome: | The proposed guardrail outperforms baselines across in-domain and out-of-domain languages by more than 15%. |
Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric (2025.acl-long)
Copied to clipboard
Yuming Yang, Yang Nan, Junjie Ye, Shihan Dou, Xiao Wang, Shuo Li, Huijie Lv, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing studies have explored various diversity-aware data selection methods to construct high-quality datasets and enhance model performance. |
| Approach: | They propose to use data diversity to measure instruction tuning of large language models. |
| Outcome: | The proposed diversity metric outperforms existing methods on simulated and real-world data and shows that it captures diversity variations and achieves a 0.97 correlation with instruction tuning. |
Can Large Language Models Translate Unseen Languages in Underrepresented Scripts? (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated impressive performance in machine translation, but struggle with unseen low-resource languages. |
| Approach: | They propose a benchmark to evaluate translation for Mongolian and Yi using linguistic resources. |
| Outcome: | The proposed model can translate Mongolian (in traditional script) and Yi with the help of linguistic resources, but is limited in its ability to handle these languages effectively. |
MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization (2024.findings-acl)
Copied to clipboard
Zhiyu Yang, Zihan Zhou, Shuo Wang, Xin Cong, Xu Han, Yukun Yan, Zhenghao Liu, Zhixing Tan, Pengyuan Liu, Dong Yu, Zhiyuan Liu, Xiaodong Shi, Maosong Sun
| Challenge: | Scientific data visualization is an essential process in research, but its use of large language models remains unexplored. |
| Approach: | They propose a model-agnostic LLM agent framework to automate scientific data visualization tasks. |
| Outcome: | The proposed framework improves performance of commercial and open-source models. |
MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing memory systems can support long-horizon human-LLM interactions by persisting historical interactions beyond limited context windows. |
| Approach: | They propose a framework that augments memory systems with a self-evolving meta-memory . meta-meso is iteratively distilling transferable knowledge utilization experiences . results show MetaMem outperforms strong baselines by over 3.6% . |
| Outcome: | The proposed framework outperforms baselines by over 3.6% in the long-horizon human-LLM interaction. |
Integrating Vectorized Lexical Constraints for Neural Machine Translation (2022.acl-long)
Copied to clipboard
| Challenge: | Existing studies focus on integrating discrete lexical constraints into neural machine translation models. |
| Approach: | They propose to integrate constraints into NMT models by integrating them into keys and values . they show that their method outperforms representative baselines on four language pairs . |
| Outcome: | The proposed method outperforms baselines on four language pairs, showing superiority . |
RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine (2026.findings-acl)
Copied to clipboard
Jiatan Huang, Mingchen Li, Zonghai Yao, Dawei Li, Yuxin Zhang, Zhichao Yang, Yongkang Xiao, Feiyun Ouyang, Xiaohan Li, Shuo Han, Hong yu
| Challenge: | Existing methods for retrieving medical textual knowledge Graphs struggle to perform well, a study finds . existing methods struggle to provide accurate answers to complex questions, he says . |
| Approach: | They synthesize user queries integrating diverse topological structures, relational information, and complex textual descriptions. |
| Outcome: | a new dataset for medical textual knowledge graphs shows that existing methods struggle to perform well . main bottlenecks lie in the scarcity of existing medical TKGs and the limited expressiveness of their topological structures . |
Why Stop at One Error? Benchmarking LLMs as Data Science Code Debuggers for Multi-Hop and Multi-Bug Errors (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have significantly reshaped software development practices, particularly in automating code generation and debugging. |
| Approach: | They propose to evaluate LLMs' capabilities on multi-hop error tracing and multi-bug detection in data science code debugging. |
| Outcome: | DSDBench adapts datasets from existing data science task benchmarks, such as DABench and MatPlotBench, featuring realistic data science debugging tasks with automatically synthesized multi-hop, multi-bug code snippets. |
VehicleWorld: A Highly Integrated Multi-Device Environment for Intelligent Vehicle Interaction (2025.findings-emnlp)
Copied to clipboard
Jie Yang, Jiajun Chen, Zhangyue Yin, Shuo Chen, Yuxin Wang, Yiran Guo, Yuan Li, Yining Zheng, Xuanjing Huang, Xipeng Qiu
| Challenge: | Traditional Function Calling (FC) approaches operate statelessly, requiring multiple exploratory calls to build environmental awareness before execution, leading to inefficiency and limited error recovery. |
| Approach: | They propose a state-based function call approach that maintains explicit system state awareness and implements direct state transitions to achieve target conditions. |
| Outcome: | The proposed approach outperforms traditional function calling approaches, achieving superior execution accuracy and reduced latency. |
Pluggable Neural Machine Translation Models via Memory-augmented Adapters (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent years, neural machine translation systems are often developed with large-scale parallel data extracted from the Web. |
| Approach: | They propose a memory-augmented adapter to steer pretrained neural machine translation models in a pluggable manner by combining model representations and retrieved results. |
| Outcome: | The proposed method outperforms several representative pluggable baselines on style- and domain-specific experiments. |
QAEval: Mixture of Evaluators for Question-Answering Task Evaluation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing QA evaluation methods struggle with open-ended and unstructured responses. |
| Approach: | They propose a hybrid framework that combines rule-based reliability with LLM-based adaptability to overcome these challenges. |
| Outcome: | The proposed framework outperforms existing models like GPT-4o and Claude-3 in accuracy and cost. |
EVOTOOL: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selection (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to optimize tool-use policies are monolithic and prone to entangling behaviors. |
| Approach: | They propose a framework that decomposes agent’stool-use policy into four modules and improves them via three mechanisms. |
| Outcome: | The proposed framework outperforms strong baselines on bothGPT-4.1 and Qwen3-8B while maintaining superior efficiency and transferability. |
Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers (2026.acl-long)
Copied to clipboard
| Challenge: | Existing reasoning-oriented LLMs lack a blind self-thinking paradigm . current models fail to recognize when their reasoning is underinformed or based on ambiguous user instructions . |
| Approach: | They propose a new reasoning paradigm that transforms LLMs into proactive inquirers that interleave reasoning with clarification. |
| Outcome: | The proposed model outperforms baseline models on mathematical reasoning, code generation, and document editing. |
AwarenessBench: Assessing Cognitive Capabilities of Language Models (2026.acl-long)
Copied to clipboard
Xiaojian Li, Rongwu Xu, Tianyun Zhang, Yue Wang, Shuo Chen, Qiner Lyu, Briana Zhang, Peiran Yang, Kyle Xue Chen, Haoyuan Shi, Yu Wang, Wei Xu
| Challenge: | Language models exhibit increasingly consciousness-like behaviors, requiring a baseline to evaluate their cognitive abilities. |
| Approach: | They propose a benchmark to assess the cognitive abilities of language models (LMs) they compare 18 state-of-the-art LMs to human models in metacognition, self-awareness, social awareness and situational awareness . |
| Outcome: | Evaluating 18 state-of-the-art LMs, they find they consistently surpass baselines . but most models fall short in metacognition and self-awareness, the study finds . |
Not All Features Deserve Attention: Graph-Guided Dependency Learning for Tabular Data Generation with Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown strong potential for tabular data generation by modeling textualized feature-value pairs. |
| Approach: | They propose a method that explicitly integrates sparse dependency graphs into LLMs’ attention mechanism. |
| Outcome: | The proposed method outperforms existing LLM-based approaches by up to 12% on complex datasets while achieving competitive results with state-of-the-art approaches in synthetic data quality. |
Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large vision-language models produce hallucinations that compromise output reliability. |
| Approach: | They propose a dual-stage framework for mitigating hallucinations without performance degradation . they propose semantic-aware component disentanglement and interpretable parameter updates . |
| Outcome: | The proposed model reduces hallucinations by 23.4% while maintaining 97.4% of general generative capability. |
On the Inference Calibration of Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing studies show that NMT models trained with label smoothing are well-calibrated on ground-truth training data, but miscalibration remains a challenge during inference due to the discrepancy between training and inference. |
| Approach: | They propose a graduated label smoothing method that can improve inference calibration and translation performance. |
| Outcome: | The proposed method improves both inference calibration and translation performance. |
Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages (2024.acl-long)
Copied to clipboard
| Challenge: | Contemporary large language models (LLMs) are pre-trained on multilingual corpora, but their performance lags behind in most languages compared to a few resource-rich languages. |
| Approach: | They propose a method that leverages the internal capabilities of large language models on resource-rich languages to enhance multilingual performance. |
| Outcome: | The proposed method improves multilingual performance while minimizing impact on original performance in resource-rich languages. |
Boosting LLM Agents with Recursive Contemplation for Effective Deception Handling (2024.findings-acl)
Copied to clipboard
Shenzhi Wang, Chang Liu, Zilong Zheng, Siyuan Qi, Shuo Chen, Qisen Yang, Andrew Zhao, Chaofei Wang, Shiji Song, Gao Huang
| Challenge: | Recent advances in large language models (LLMs) have led to significant success in using LLMs as agents. |
| Approach: | They propose a cognitive framework that incorporates first-order and second-order perspective transitions into LLMs to enhance their ability to identify and counteract deceptive information. |
| Outcome: | The proposed framework enhances LLMs’ ability to identify and counteract deceptive information without extra fine-tuning and data. |
GenomeQA: Benchmarking General Large Language Models for Genome Sequence Understanding (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks focus on specialized DNA models trained for sequence prediction or evaluate biological knowledge using text-only questions. |
| Approach: | They propose a benchmark to evaluate general-purpose LLMs on sequence-based genome inference tasks. |
| Outcome: | The proposed benchmark outperforms baseline models on sequence-based genome inference tasks. |
RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models (2025.acl-long)
Copied to clipboard
Hieu Tran, Zonghai Yao, Zhichao Yang, Junda Wang, Yifan Zhang, Shuo Han, null Feiyun Ouyang, Hong Yu
| Challenge: | Existing work aims to improve reasoning accuracy and factual integrity across large language models for knowledge-intensive tasks such as medical and commonsense reasoning. |
| Approach: | They propose a versatile extension to the mutual reasoning framework (rStar) that enhances reasoning accuracy and factual integrity across large language models. |
| Outcome: | The proposed extension to the mutual reasoning framework improves reasoning accuracy and factual integrity across large language models for complex, knowledge-intensive tasks. |
On the Language Coverage Bias for Neural Machine Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | Language coverage bias is important for neural machine translation because of the target-original training data. |
| Approach: | They propose two approaches to alleviate the language coverage bias problem by explicitly distinguishing between the source-and target-original training data. |
| Outcome: | The proposed methods improve translation tasks on both back-and forward-translation and their tagged variants. |
TemplateGEC: Improving Grammatical Error Correction with Detection Template (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for grammatical error correction (GEC) have been developed. |
| Approach: | They propose a method which integrates the detection labels from a Seq2Edit model to construct a template as the input. |
| Outcome: | The proposed method can perform human-in-the-loop error correction tasks. |
A Trusted Multi-View Evidential Fusion Framework for Commonsense Reasoning (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing models that provide evidence for commonsense reasoning tasks have limitations . evidence is often interpreted in ways that are not directly available in the input. |
| Approach: | They propose a trusted multi-view evidential fusion framework that assesses the confidence of evidence and combines different views in a trustworthy manner. |
| Outcome: | The proposed framework can reason with multi-view evidence and compete with state-of-the-art models. |
CoLLiE: Collaborative Training of Large Language Models in an Efficient Way (2023.emnlp-demo)
Copied to clipboard
Kai Lv, Shuo Zhang, Tianle Gu, Shuhao Xing, Jiawei Hong, Keyu Chen, Xiaoran Liu, Yuqing Yang, Honglin Guo, Tengxiao Liu, Yu Sun, Qipeng Guo, Hang Yan, Xipeng Qiu
| Challenge: | Large language models (LLMs) are increasingly pivotal in a wide range of tasks . however, the resources required for training these models necessitate efficient solutions . |
| Approach: | They propose a library that facilitates collaborative training of large language models . they use 3D parallelism, parameter-efficient fine-tuning methods and optimizers . |
| Outcome: | The proposed library has proven superior training efficiency in comparison with prevalent solutions in pre-training and fine-tuning scenarios. |
UltraLink: An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset (2024.acl-long)
Copied to clipboard
Haoyu Wang, Shuo Wang, Yukun Yan, Xujia Wang, Zhiyu Yang, Yuzhuang Xu, Zhenghao Liu, Liner Yang, Ning Ding, Xu Han, Zhiyuan Liu, Maosong Sun
| Challenge: | Open-source large language models (LLMs) have gained strength across diverse fields, but the majority of studies focus on English. |
| Approach: | They propose a knowledge-grounded data augmentation approach to elicit more language-specific knowledge of LLMs by enhancing their ability to serve users from different countries. |
| Outcome: | The proposed method can prune the language-agnostic supervised fine-tuning dataset without any performance degradation. |
ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development (2026.findings-acl)
Copied to clipboard
Jie Yang, Honglin Guo, Li Ji, Jiazheng Zhou, Rui Zheng, Zhikai Lei, Shuo Zhang, Zhiheng Xi, Shichun Liu, Yuxin Wang, Bo Wang, Yining Zheng, Tao Gui, Xipeng Qiu
| Challenge: | Large Language Models (LLMs) have redefined the role of AI in software engineering . current benchmarks focus on localized code generation, but neglect dynamic, full-process requirements of real-world engineering. |
| Approach: | They propose a benchmark to evaluate agentic backend coding within a realistic, executable workflow. |
| Outcome: | The ABC-Bench benchmark evaluates agentic backend coding within a realistic, executable workflow. |
Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels (2025.emnlp-main)
Copied to clipboard
Junjie Ye, Yuming Yang, Yang Nan, Shuo Li, Qi Zhang, Tao Gui, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan
| Challenge: | Large language models (LLMs) acquire substantial world knowledge during pretraining, which is further shaped by post-training techniques such as supervised fine-tuning (SFT). |
| Approach: | They evaluate closed-book question answering (CBQA) performance across five LLMs from the LLaMA-2 and LLama-3 families and examine the impact of supervised fine-tuning on model knowledge. |
| Outcome: | The proposed model performance is 14% worse than models fine-tuned on 1,920 samples and 12% worse on 240 samples. |
COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis (2025.findings-naacl)
Copied to clipboard
Weiqing Yang, Hanbin Wang, Zhenghao Liu, Xinze Li, Yukun Yan, Shuo Wang, Yu Gu, Minghe Yu, Zhiyuan Liu, Ge Yu
| Challenge: | Existing code debugging benchmarks focus on the Code Repair stage of the code generation process. |
| Approach: | They propose a framework to evaluate the debugging abilities of large language models by emulating the human debug process. |
| Outcome: | The proposed framework outperforms human-curated and GPT-4-generated training data, enabling 7B-scale LLMs to achieve comparable debugging performance to GPT-3.5. |
Learning from Textual Radiology Reports: A Benchmark Dataset for Coronary CT Angiography (2026.acl-industry)
Copied to clipboard
Sudharshan Balaji, Zhiyu Liu, Zhengyuan Jiang, Shuo Lei, Yimin Chen, Yang Xiao, Shone O. Almeida, Mathew Joseph Karivelil, Christopher Malanga, Ning Wang
| Challenge: | CCTA reports provide an assessment of coronary disease severity to guide patient management. |
| Approach: | They propose a pipeline that decouples structuring from classification by an LLM-based parser . CCTA-RADS is the largest publicly available dataset of CCDA reports . |
| Outcome: | The proposed approach improves the F1-score by 6%-13% compared with direct methods. |
P-TA: Using Proximal Policy Optimization to Enhance Tabular Data Augmentation via Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Contemporary approaches to generate tabular data are limited due to the lack of external knowledge. |
| Approach: | They propose to use proximal policy optimization to apply GANs and fine-tune Large Language Models to enhance the probability distribution of tabular features. |
| Outcome: | The proposed method improves accuracy of GANs and LLMs over state-of-the-art over three real-world datasets. |
Lock on Target! Precision Unlearning via Directional Control (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for unlearning harmful, sensitive, or outdated knowledge suffer from two critical limitations: (1) collateral forgetting, where erasing target data inadvertently removes related but desirable knowledge, and (2) generality forgetting degrades the model’s general capabilities. |
| Approach: | They propose a method that identifies and leverages a targeted "unlearning direction" in the model's parameter space and selectively updates along this direction. |
| Outcome: | Experiments show that the proposed method achieves state-of-the-art unlearning precision while preserving both related knowledge and general capabilities. |
DongbaMIE: A Multimodal Information Extraction Dataset for Evaluating Semantic Understanding of Dongba Pictograms (2025.findings-emnlp)
Copied to clipboard
Xiaojun Bi, Shuo Li, Junyao Xing, Ziyue Wang, Fuwen Luo, Weizheng Qiao, Lu Han, Ziwei Sun, Peng Li, Yang Liu
| Challenge: | Dongba pictographic is the only pictograph script still in use in the world. |
| Approach: | DongbaMIE is the first dataset focusing on multimodal information extraction of Dongbe pictographs. |
| Outcome: | The dataset contains 23,530 sentence-level and 2,539 paragraph-level high-quality text-image pairs. |
Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations (2025.findings-emnlp)
Copied to clipboard
Shuo Li, Jiajun Sun, Guodong Zheng, Xiaoran Fan, Yujiong Shen, Yi Lu, Zhiheng Xi, Yuming Yang, Wenming Tan, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Multimodal large language models have demonstrated remarkable performance in visual-language tasks, but their authenticity is often compromised by object hallucinations. |
| Approach: | They propose a multi-frequency perturbation method that leverages both low-frequency and high-frequency features of images to perturb visual feature representations and explicitly suppress redundant frequency-domain features during inference. |
| Outcome: | The proposed method significantly mitigates object hallucinations across various model architectures. |
A Template-based Method for Constrained Neural Machine Translation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to solve this problem can not satisfy the following three desiderata: (1) high translation quality, (2) high match accuracy, and (3) low latency. |
| Approach: | They propose a template-based method that can provide high translation quality and match accuracy and a low latency inference. |
| Outcome: | The proposed method outperforms baselines in lexically and structurally constrained translation tasks and can be used in a variety of applications. |
GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) fine-tuning techniques require large Floating Point(FP) computation and are impractical for resource-constrained edge devices. |
| Approach: | They propose a framework for on-device LLM fine-tuning that eliminates the need for floating-point operations in both inference and training. |
| Outcome: | The proposed framework reduces memory and compute costs while reducing memory usage. |
Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Tabular data is critical across diverse domains, yet high-quality tabular datasets remain scarce due to privacy concerns and the cost of collection. |
| Approach: | They propose a lightweight generative framework that captures sparse dependencies via an LLM-induced graph. |
| Outcome: | The proposed framework reduces constraint violations by 4% and accelerates generation by nearly 9,500 over diffusion-based methods. |
Is Parameter Collision Hindering Continual Learning in LLMs? (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods to learn multiple tasks in parallel often lead to catastrophic forgetting, resulting in overwriting knowledge. |
| Approach: | They propose a non-collision low-rank Adaptation approach that leverages low collision rates to enhance continual learning (CL) in large language models. |
| Outcome: | The proposed approach achieves better task orthogonality and higher task orthognality than existing SOTA methods. |
ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web (2026.acl-long)
Copied to clipboard
Zhiyuan Yao, Zishan Xu, Yifu Guo, Zhiguang Han, Cheng Yang, Shuo Zhang, Weinan Zhang, Xingshan Zeng, Weiwen Liu
| Challenge: | Existing routers that use hardcoded tools are limited by scalability and generality bottlenecks. |
| Approach: | They propose a pipeline for training history-aware routers to empower precise navigation in large-scale ecosystems. |
| Outcome: | The proposed pipeline can train routers with dynamic context understanding to create the plug-and-play Light Routing Agent. |
SAGE: Sparse Adaptive Guidance for Dependency-Aware Tabular Data Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Recent approaches to generate tabular data are limited by their static dependences and lack of fidelity. |
| Approach: | They propose a novel LLM-based generation framework that enforces sparse and dynamic dependency guidance. |
| Outcome: | The proposed framework boosts F1 scores by 10% and reduces policy violations by one point. |