Papers by Liu Chu
ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for code execution reasoning are limited by the difficulty of the training data. |
| Approach: | They propose a model that uses reinforcement learning to reward correct answers from execution traces. |
| Outcome: | The proposed model improves pass@1 by up to 5.9% on code generation tasks over strong baselines. |
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. |
AnRe: Analogical Replay for Temporal Knowledge Graph Forecasting (2025.acl-long)
Copied to clipboard
| Challenge: | Temporal Knowledge Graphs (TKGs) are vital for event prediction, yet current methods face limitations. |
| Approach: | They propose a training-free Analogical Replay reasoning framework that uses LLMs to extract historical contexts and generate analogical reasoning examples as contextual inputs. |
| Outcome: | The proposed model outperforms existing training-free methods on four benchmarks. |
Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to augment pre-trained large language models require extensive computational efforts and massive data volumes, challenging the widespread accessibility of LLM research. |
| Approach: | They propose a post-pretraining strategy of selectively enhancing shallow layers while pruning less effective deep ones to augment pretrained large language models. |
| Outcome: | The proposed approach improves performance on the corpus of code & math and a legal corpus and is widely applicable. |
FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning (2026.acl-long)
Copied to clipboard
Yujie Feng, Hao Wang, Jian Li, Xu Chu, Zhaolu Kang, Yiran Liu, Yasha Wang, Philip S. Yu, Xiao-Ming Wu
| Challenge: | Continual learning (CL) for large language models (LLMs) aims to enable sequential knowledge acquisition without catastrophic forgetting. |
| Approach: | They propose a framework that aligns replay schedules with a model-centric notion of time. |
| Outcome: | Experiments on three benchmarks show that FOREVER consistently mitigates catastrophic forgetting. |
MalURLBench: A Benchmark Evaluating Agents’ Vulnerabilities When Processing Web URLs (2026.findings-acl)
Copied to clipboard
Dezhang Kong, Zhuxi Wu, Shiqi Liu, ZhiCheng Tan, Kuichen Lu, Minghao Li, Qichen Liu, Shengyu Chu, Zhenhua Xu, Xuan Liu, Meng Han
| Challenge: | Existing models struggle to detect elaborately disguised malicious URLs, despite their ability to process malicious URL's. |
| Approach: | They propose a benchmark to evaluate LLMs’ vulnerabilities to malicious URLs and a lightweight defense module to mitigate the vulnerability. |
| Outcome: | The proposed framework analyzes 61,845 attack instances spanning 10 real-world scenarios and 7 categories of real malicious websites. |
Ask-Before-Detection: Identifying and Mitigating Conformity Bias in LLM-Powered Error Detector for Math Word Problem Solutions (2025.acl-long)
Copied to clipboard
| Challenge: | Recent studies have demonstrated the potential of large language models (LLMs) for automatic error detection in math word problems (MWPs). |
| Approach: | They propose a framework that generates adaptive reference solutions using LLMs to enhance error detection by reducing conformity bias in MWPs. |
| Outcome: | The proposed framework mitigates the performance gap between conventional and alternative solutions in MWPs, especially when combined with reasoning-enhancing techniques like chain-of-thought prompting. |
Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-training (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have impressive capabilities across a wide range of domains, but their generalpurpose pre-training objectives often leave them illsuited for specialized applications such as healthcare. |
| Approach: | They propose a perplexity-aware data scaling law that establishes a predictive relationship between the perplexities of domain-specific data and the test loss. |
| Outcome: | Experiments on medical and general-domain benchmarks show that the proposed scaling law consistently identifies near-optimal training subsets with significantly reduced data consumption. |
Analyzing Chain-of-thought Prompting in Black-Box Large Language Models via Estimated V-information (2024.lrec-main)
Copied to clipboard
| Challenge: | Chain-of-Thought (CoT) prompting and large language models (LLMs) have shown great potential in improving performance on challenging reasoning tasks. |
| Approach: | They propose a new metric which extends the concept of pointwise V-information to black-box models and quantifies label-relevant new information introduced by CoT prompting. |
| Outcome: | The proposed metric extends the concept of pointwise V-information to black-box models, quantifying label-relevant new information introduced by CoT prompting beyond pre-existing label information. |
Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models can lead to undesired consequences when misaligned with human values . previous studies have shown misalignment of LLMs with human value using expert-designed or agent-based emulated bias scenarios . |
| Approach: | They investigate whether large language models (LLMs) are misaligned with human values . they find no significant differences in understanding of HVSB between LLMs . |
| Outcome: | The results show that large language models do not have lower misalignment rates and attack success rates . the study also shows that smaller language models have the ability to explain HVSB . |
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)
Copied to clipboard
Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He
| Challenge: | Document images are characterized by higher resolutions, denser content, and more complex structural layouts. |
| Approach: | They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition. |
| Outcome: | The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead. |
Balancing Knowledge Breadth and Task Depth for Effective Domain Adaptation Fine-Tuning (2026.findings-acl)
Copied to clipboard
| Challenge: | a lack of knowledge breadth and task depth can hinder curriculum learning in domains such as medicine and finance. |
| Approach: | They propose a two-dimensional curriculum learning framework that coordinates model training along two orthogonal axes: the knowledge dimension and the task dimension. |
| Outcome: | The proposed framework improves accuracy on medical evaluations by 2.49% and on financial evaluations 1.2% compared with the second-best method. |
A Unified Framework for Modeling Heterogeneous Financial Data via Dual-Granularity Prompting (2026.acl-industry)
Copied to clipboard
| Challenge: | Recent industrial credit scoring models rely heavily on manually tuned statistical learning methods due to the complexity of heterogeneous financial data and the challenge of modeling evolving creditworthiness. |
| Approach: | They propose a framework that reformulates credit scoring as a multi-scale sequential learning problem. |
| Outcome: | FinLangNet improves KS and bad debt rate by 6.3 pp in real world deployments. |
Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models (2026.acl-long)
Copied to clipboard
Runxuan Liu, Xianhao Ou, Xinyan Ma, Jiyuan Wang, Jiafeng Liang, Jiaqi Li, Tao He, Zheng Chu, Rongchuan Mu, Zekun Wang, Baoxin Wang, Dayong Wu, Ming Liu, Shijin Wang, Guoping Hu, Bing Qin
| Challenge: | Existing methods for long chain-of-thought (LCoT) are coarse-grained, reward hacking, and poor generalization. |
| Approach: | They propose a Long Chain-of-Thought (LCoT) model that integrates reinforcement learning with verifiable rewards with a process-aware verification approach. |
| Outcome: | The proposed model improves reasoning and code generation tasks while reducing the cost of training and performance bottlenecks. |
JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have been used to mitigate misuse and to align with human values. |
| Approach: | They propose to use large-scale evaluations of various jailbreak attacks to identify key patterns and test them under eight advanced defenses. |
| Outcome: | The proposed attacks achieve high success rates but are easy to mitigate by defenses. |
DialogGen: Multi-modal Interactive Dialogue System with Multi-turn Text-Image Generation (2025.findings-naacl)
Copied to clipboard
Minbin Huang, Yanxin Long, Xinchi Deng, Ruihang Chu, Jiangfeng Xiong, Xiaodan Liang, Hong Cheng, Qinglin Lu, Wei Liu
| Challenge: | Text-to-image (T2I) generation models have advanced in recent years, but effective interaction with these models is challenging for average users due to the need for specialized prompt engineering knowledge and the inability to perform multi-turn image generation. |
| Approach: | They propose to use off-the-shelf MLLMs and T2I models to build a multi-modal interactive dialogue system (MIDS) that can generate correct output modalities and coherence of output images. |
| Outcome: | The proposed pipeline can generate correct output modalities and coherent multi-modal outputs compared with other state-of-the-art models. |
Memory-Guided Hard Data Augmentation for Multimodal Named Entity Recognition (2026.findings-acl)
Copied to clipboard
Xinyu Liu, Kai fu, Yinghan Shi, Quanyou Chu, Ming Du, Hongya Wang, Xiaojun Meng, Jiansheng Wei, Yanghua Xiao, Bo Xu
| Challenge: | Existing methods for Named Entity Recognition (NER) ignore the internal state of the target model. |
| Approach: | They propose a framework to repair model-specific errors by using a model-based approach . they employ cross-validation to identify model- specific Hard Data and a memory tree to induce macro-level error patterns from micro-level failures. |
| Outcome: | The proposed framework yields significant performance gains on Twitter and other platforms. |
Editing the Moving World: Model Editing for Video LLMs (2026.acl-long)
Copied to clipboard
Qian Zhang, Xinye Li, Xiaokai Wu, Junhao Xu, Zhanyue Qin, Qingbin Liu, Junxian Cai, Xi Chen, Bolin Zhang, Zhiying Tu, Dianhui Chu, Xiaoyan Yu, Dianbo Sui
| Challenge: | Existing models for knowledge editing focus on knowledge-level or static visual domains, overlooking dynamic semantics. |
| Approach: | They propose a benchmark for modeling large language models using six representative models . they analyze the strengths and limitations of existing models and identify new directions . |
| Outcome: | The proposed benchmark extends existing models from static modalities to dynamic video scenarios. |
What Language Do Non-English-Centric Large Language Models Think in? (2025.findings-acl)
Copied to clipboard
Chengzhi Zhong, Qianying Liu, Fei Cheng, Junfeng Jiang, Zhen Wan, Chenhui Chu, Yugo Murawaki, Sadao Kurohashi
| Challenge: | Despite their robust performance in English, these models often exhibit reduced proficiency in non-English languages, and their outputs may reflect an inherent bias toward English-centric perspectives. |
| Approach: | They categorize non-English-centric large language models into two groups: CPMs and BLMs, which are pre-trained on a balanced mix of multiple languages from scratch. |
| Outcome: | The proposed models exhibit a pronounced internal preference for English tokens when projected into the vocabulary space. |
MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation (2025.findings-emnlp)
Copied to clipboard
Chenghao Yang, Yinbo Luo, Zhoufutu Wen, Qi Chu, Tao Gong, Longxiang Liu, Kaiyuan Zhang, Jianpeng Jiao, Ge Zhang, Wenhao Huang, Nenghai Yu
| Challenge: | Large Language Models (LLMs) have been widely adopted in real-world dialogue applications, but their robustness is criticized all along. |
| Approach: | They propose to use play-by-play text commentary to build a multi-turn athletic real-world scenario dialogue benchmark to evaluate three critical aspects of multi-turned conversations: ultra multi- turn, interactive multi-twist, and cross-turn tasks. |
| Outcome: | The proposed benchmarks outperform open-source LLMs on three critical aspects of multi-turn conversations: ultra multi-turned, interactive multi- turn, and cross-turn tasks. |
Language Lives in Sparse Dimensions: Toward Interpretable and Efficient Multilingual Control for Large Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Prior studies show that large language models map multilingual content into English-aligned representations at intermediate layers before projecting them back into target-language token spaces in the later layers. |
| Approach: | They propose a method to identify and manipulate dimensions that are sparse and sparsity-based . they propose to use as few as 50 sentences of either parallel or monolingual data to manipulate these dimensions . |
| Outcome: | Experiments on a multilingual generation control task show the interpretability of these dimensions. |
Analyzing and Mitigating Inconsistency in Discrete Speech Tokens for Neural Codec Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have demonstrated significant strides in generating high-quality speech . discretizing speech by neural audio codecs often results in sequences that differ from text sequences . |
| Approach: | They quantitatively analyze the Discrete Representation Inconsistency phenomenon within popular audio tokenizers such as EnCodec. |
| Outcome: | The proposed method mitigates the DRI phenomenon within popular audio tokenizers such as EnCodec. |
Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging (2024.emnlp-main)
Copied to clipboard
Deyuan Liu, Zhanyue Qin, Hairu Wang, Zhao Yang, Zecheng Wang, Fangying Rong, Qingbin Liu, Yanchao Hao, Bo Li, Xi Chen, Cunhang Fan, Zhao Lv, Dianhui Chu, Zhiying Tu, Dianbo Sui
| Challenge: | Existing methods for parameter pruning fail to utilize the knowledge from pruned parameters. |
| Approach: | They propose a method that uses manifold learning and the Information Bottleneck measure to merge similar layers to preserve model performance. |
| Outcome: | The proposed method outperforms pruning methods on multiple datasets and LLMs with quantization and achieves substantial compression ratios. |
UnrealLLM: Towards Highly Controllable and Interactable 3D Scene Generation by LLM-powered Procedural Content Generation (2025.findings-acl)
Copied to clipboard
SongTang SongTang, Kaiyong Zhao, Lei Wang, Yuliang Li, Xuebo Liu, Junyi Zou, Qiang Wang, Xiaowen Chu
| Challenge: | UnrealLLM is a novel framework that connects natural language descriptions with the professional PCG system (Unreal Engine 5) to automate scene generation. |
| Approach: | They propose a novel multi-agent framework that connects natural language descriptions with the professional PCG system (Unreal Engine 5) to automate scene generation. |
| Outcome: | The proposed framework achieves competitive performance in technical metrics and aesthetic quality, offering unique advantages in generation scale and interactivity. |
Towards Benchmarking Situational Awareness of Large Language Models:Comprehensive Benchmark, Evaluation and Analysis (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Situational awareness is crucial for decision-making, anticipating potential issues, and adapting to dynamic circumstances. |
| Approach: | They propose a benchmark that covers three tiers of situational awareness capabilities . they conduct extensive experiments on advanced LLMs including GPT-4, LLaMA3, Qwen1.5 . |
| Outcome: | The proposed benchmark covers environment perception, situation comprehension and future projection. |
ScEdit: Script-based Assessment of Knowledge Editing (2025.findings-acl)
Copied to clipboard
Xinye Li, Zunwen Zheng, Qian Zhang, Dekai Zhuang, Jiabao Kang, Liyan Xu, Qingbin Liu, Xi Chen, Zhiying Tu, Dianhui Chu, Dianbo Sui
| Challenge: | Knowledge Editing (KE) has gained increasing attention, yet current evaluation frameworks do not integrate KE into real-world application scenarios. |
| Approach: | They propose a script-based benchmark which encompasses both counterfactual and temporal edits and integrates token-level and text-level evaluation methods. |
| Outcome: | The proposed method combines token-level and text-level evaluation methods with a new fact-based evaluation framework. |
CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges (2025.acl-long)
Copied to clipboard
| Challenge: | Empirical evaluations of large language models demonstrate that they improve performance in a wide range of tasks. |
| Approach: | They propose a label-free method for mitigating selection bias during inference by reformulating debiasing as an optimization task. |
| Outcome: | The proposed method mitigates selection bias and improves performance compared to existing methods. |
Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation (2022.acl-long)
Copied to clipboard
Mingzhe Li, XieXiong Lin, Xiuying Chen, Jinxiong Chang, Qishen Zhang, Feng Wang, Taifeng Wang, Zhongyi Liu, Wei Chu, Dongyan Zhao, Rui Yan
| Challenge: | Existing studies focus on contrastive learning on the instance level without discriminating the contribution of each word. |
| Approach: | They propose a hierarchical contrastive learning mechanism which can unify semantic meaning in the input text. |
| Outcome: | The proposed model outperforms baselines on storytelling, paraphrasing, dialogue generation, and storytelling tasks. |
Incorporating Causal Analysis into Diversified and Logical Response Generation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing generation-based models generate generic and safe responses such as "So am I" or "I don't know" |
| Approach: | They propose to predict the mediators to preserve relevant information and auto-regressively incorporate the mediator into generating process. |
| Outcome: | The proposed model generates relevant and informative responses and outperforms the state-of-the-art in terms of automatic metrics and human evaluations. |
Breaking the Reasoning Barrier A Survey on LLM Complex Reasoning through the Lens of Self-Evolution (2025.findings-acl)
Copied to clipboard
Tao He, Hao Li, Jingchang Chen, Runxuan Liu, Yixin Cao, Lizi Liao, Zihao Zheng, Zheng Chu, Jiafeng Liang, Ming Liu, Bing Qin
| Challenge: | OpenAI's O1 and subsequent projects like DeepSeek R1 have significantly advanced research on complex reasoning in LLMs. |
| Approach: | They analyze existing reasoning studies from the perspective of self-evolution and summarize O1-like works from open-source projects like DeepSeek R1 and Kimi-k1.5. |
| Outcome: | The proposed models are based on open-source models and pioneer advanced methodologies like Scaling Reinforcement Learning (RL). |
AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension (2024.acl-long)
Copied to clipboard
Qian Yang, Jin Xu, Wenrui Liu, Yunfei Chu, Ziyue Jiang, Xiaohuan Zhou, Yichong Leng, Yuanjun Lv, Zhou Zhao, Chang Zhou, Jingren Zhou
| Challenge: | Existing benchmarks for audio-centric interaction have impeded advancements in this field . AIR-Bench evaluates LALMs' ability to understand audio signals and interact with humans . |
| Approach: | They propose a benchmark to evaluate the ability of large audio-language models to understand audio signals . they use 19 tasks with approximately 19k single-choice questions to examine single-task ability . |
| Outcome: | The proposed framework evaluates the ability of large audio-language models to understand audio signals and interact with humans in the textual format. |
Exploring Deductive and Inductive Reasoning Capabilities of Large Language Models in Procedural Planning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Deductive and inductive reasoning are fundamental components of human cognition . authors present a benchmark to assess their performance in procedural planning . |
| Approach: | They propose a benchmark to assess the deductive and inductive reasoning abilities of LLMs . they propose IMSE to enable LLM to generate multiple similar procedural plans . |
| Outcome: | The proposed method improves inductive reasoning abilities of LLMs, the authors show . they show that LLM models show excellent deductive reasoning capabilities but suboptimal inductive performance. |
Advancing Topic Segmentation and Outline Generation in Chinese Texts: The Paragraph-level Topic Representation, Corpus, and Benchmark (2024.lrec-main)
Copied to clipboard
| Challenge: | Compared with sentence-level topic structure, paragraph-level topics can grasp and understand the context of a document from a higher level. |
| Approach: | They propose a hierarchical paragraph-level topic structure representation with three layers to guide corpus construction. |
| Outcome: | The proposed method achieves the largest Chinese paragraph-level topic structure corpus, achieving high quality. |
Probing the Plasticity and Correlation of LLM Value Systems: LLM Value Rankings are Not Stable (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have similar value rankings but little is known about how susceptible they are to external influence and how different values are correlated with each other. |
| Approach: | They propose to use 6 different value transformation prompting methods to examine the plasticity of LLM value systems by comparing them with 8 LLMs. |
| Outcome: | The proposed methods are effective on 8 LLMs and 3 families. |
Teaching Your Models to Understand Code via Focal Preference Alignment (2025.emnlp-main)
Copied to clipboard
Jie Wu, Haoling Li, Xin Zhang, Xiao Liu, Yangyu Huang, Jianwen Luo, Yizhen Zhang, Zuchao Li, Ruihang Chu, Yujiu Yang, Scarlett Li
| Challenge: | Existing methods for supervised fine-tuning focus on unit test feedback to construct preference pairs. |
| Approach: | They propose a preference alignment framework that mimics human iterative debugging to refine Code LLMs. |
| Outcome: | Experiments show that Preference Learning improves on BigCodeBench and BigCodeBind tasks. |
MADNet: Maximizing Addressee Deduction Expectation for Multi-Party Conversation Generation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for multi-party conversations rely on addressee labels and can only be applied to an ideal setting where addresses are missing. |
| Approach: | They propose a method that maximizes addressee deduction expectation in heterogeneous graph neural networks for MPC generation. |
| Outcome: | The proposed method outperforms baseline models on Ubuntu IRC channel benchmarks on the task of MPC generation under a common and challenging setting where addressee labels are missing. |
Self-Critique Guided Iterative Reasoning for Multi-hop Question Answering (2025.findings-acl)
Copied to clipboard
Zheng Chu, Huiming Fan, Jingchang Chen, Qianyu Wang, Mingda Yang, Jiafeng Liang, Zhongjie Wang, Hao Li, Guo Tang, Ming Liu, Bing Qin
| Challenge: | Large language models (LLMs) have demonstrated remarkable reasoning capabilities, but they still face challenges in knowledge-intensive multi-hop reasoning. |
| Approach: | They propose a method that uses self-critique feedback to guide iterative reasoning by enabling iteration and self-evaluation of its intermediate reasoning steps. |
| Outcome: | The proposed method surpasses the previous SOTA by 8.6% on three multi-hop reasoning datasets. |
LPZero: Language Model Zero-cost Proxy Search from Zero (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing zero-cost (ZC) proxies rely on expert knowledge and incur significant trial-and-error costs. |
| Approach: | They propose a framework that automatically designs zero-cost (ZC) proxies for various tasks and incorporates genetic programming to find the optimal symbolic composition. |
| Outcome: | The proposed framework achieves higher ranking consistency than human-designed proxies on NLP tasks. |
Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research (2025.findings-emnlp)
Copied to clipboard
Xiang Liu, Penglei Sun, Shuyan Chen, Longhan Zhang, Peijie Dong, Huajie You, Yongqi Zhang, Chang Yan, Xiaowen Chu, Tong-yi Zhang
| Challenge: | a rapid advancement of perovskite solar cells has led to an exponential growth in research publications. |
| Approach: | They propose a knowledge-enhanced system for perovskite solar cells that integrates three key components. |
| Outcome: | The proposed system outperforms existing models in domain-specific knowledge retrieval and scientific reasoning tasks. |
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models (2025.acl-long)
Copied to clipboard
Siming Huang, Tianhao Cheng, Jason Klein Liu, Weidi Xu, Jiaran Hao, Liuyihan Song, Yang Xu, Jian Yang, Jiaheng Liu, Chenchen Zhang, Linzheng Chai, Ruifeng Yuan, Xianzhen Luo, Qiufeng Wang, YuanTao Fan, Qingfu Zhu, Zhaoxiang Zhang, Yang Gao, Jie Fu, Qian Liu, Houyi Li, Ge Zhang, Yuan Qi, Xu Yinghui, Wei Chu, Zili Wang
| Challenge: | Code LLMs lack reproducible data pipelines and training protocols for reproducible advancements in code intelligence. |
| Approach: | They propose a top-tier code LLM that releases model weights and inference code . reproducible data pipelines, rigorous experimental ablation results and training protocols are included . |
| Outcome: | The proposed model achieves comparable performance to leading models and serves as an "open cookbook" reproducible training data, rigorous experimental ablation results, and detailed training protocols are also included in the model. |
UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Models (2024.emnlp-main)
Copied to clipboard
Zhanyue Qin, Haochuan Wang, Deyuan Liu, Ziyang Song, Cunhang Fan, Zhao Lv, Jinlin Wu, Zhen Lei, Zhiying Tu, Dianhui Chu, Xiaoyan Yu, Dianbo Sui
| Challenge: | Existing LLMs demonstrate powerful capabilities between tasks, but can they make sequential decisions? |
| Approach: | They propose to evaluate sequential decision-making capability of large language models (LLMs) using novel metrics based Monte Carlo methods. |
| Outcome: | The proposed benchmark improves sequential decision-making performance compared to the vanilla LLM player. |
TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Grasping the concept of time is a fundamental facet of human cognition. |
| Approach: | They propose a hierarchical temporal reasoning benchmark that covers a broad spectrum of temporal phenomena. |
| Outcome: | The proposed benchmark shows that state-of-the-art LLMs are still far behind humans in temporal reasoning . |
TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation (2024.acl-long)
Copied to clipboard
| Challenge: | Current methods for Continual Dialogue State Tracking (DST) struggle with catastrophic forgetting and knowledge transfer between tasks. |
| Approach: | They propose a framework for task skill localization and consolidation that enables effective knowledge transfer without relying on memory replay. |
| Outcome: | The proposed framework shows a 7.6% increase in Avg. JGA and 11% rise in BWT metrics over existing state-of-the-art methods. |
Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future (2024.acl-long)
Copied to clipboard
Zheng Chu, Jingchang Chen, Qianglong Chen, Weijiang Yu, Tao He, Haotian Wang, Weihua Peng, Ming Liu, Bing Qin, Ting Liu
| Challenge: | Recent studies have revealed that chain-of-thought prompting significantly enhances LLM’s reasoning capabilities, which attracts widespread attention from both academics and industry. |
| Approach: | They propose to summarize advanced methods through a taxonomy that offers novel perspectives. |
| Outcome: | The proposed method delineates the challenges and future directions, thereby shedding light on future research. |
Understanding the Prompt Sensitivity (2026.acl-long)
Copied to clipboard
| Challenge: | Prompt sensitivity is a measure of how strongly the output of a large language model (LLM) depends on the exact wording of its input prompt. |
| Approach: | They consider LLMs as multivariate functions and perform a first-order Taylor expansion to analyze the relationship between meaning-preserving prompts, their gradients, and log probabilities of the model’s next token. |
| Outcome: | The proposed model disperses meaning-preserving inputs, making it difficult to reduce to 0. The proposed models also dispersing prompt variants are more likely to introduce prompt sensitivity risks in LLMs. |
Towards Faithful Multi-step Reasoning through Fine-Grained Causal-aware Attribution Reasoning Distillation (2025.coling-main)
Copied to clipboard
| Challenge: | Recent advances have witnessed large language models (LLMs) achieving significant milestones across various domains of natural language processing. |
| Approach: | They introduce fine-grained attribution reasoning distillation (FARD) which incorporates grounded citations to consolidate the relationships between reasoning steps. |
| Outcome: | The proposed method outperforms CoT distillation methods on mathematical and general reasoning benchmarks. |
Towards Adaptive Memory-Based Optimization for Enhanced Retrieval-Augmented Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for enhancing response accuracy and accuracy struggle with open-domain QA tasks because they perform independent retrieval operations without maintaining a summarizing memory or using adaptive retrieval strategies. |
| Approach: | They propose a method that integrates non-parametric knowledge from external knowledge bases into models to enhance response accuracy while mitigating factual errors and hallucinations. |
| Outcome: | The proposed method improves on open-domain QA datasets and reduces noise and hallucinations due to redundant information and insufficient information integration. |
BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering (2024.acl-long)
Copied to clipboard
Zheng Chu, Jingchang Chen, Qianglong Chen, Haotian Wang, Kun Zhu, Xiyuan Du, Weijiang Yu, Ming Liu, Bing Qin
| Challenge: | Large language models (LLMs) have demonstrated strong reasoning capabilities, but they still suffer from factual errors when tackling knowledge-intensive tasks. |
| Approach: | They propose a reasoning framework for knowledge-intensive multi-hop QA that prioritizes promising answers at each hop of question. |
| Outcome: | The proposed framework outperforms SOTA methods on four open-domain multi-hop reasoning datasets by 8.5%. |
Exploring the Impact of Layer Normalization for Zero-shot Neural Machine Translation (2023.acl-short)
Copied to clipboard
| Challenge: | Recent studies have shown that layer normalization (LayerNorm) overfits training data and therefore has low generalizability for ZST. |
| Approach: | They propose to use the Transformer architecture to set the default layer normalization setting for zero-shot translation (ZST) they also propose to set LayerNorm after residual connections to outperform PreNorm by 12.3 BLEU points. |
| Outcome: | The proposed model outperforms the current model by 12.3 BLEU points on 54 directions on OPUS, IWSLT, and Europarl datasets. |
Investigating and Enhancing the Robustness of Large Multimodal Models Against Temporal Inconsistency (2025.acl-long)
Copied to clipboard
Jiafeng Liang, Shixin Jiang, Xuan Dong, Ning Wang, Zheng Chu, Hui Su, Jinlan Fu, Ming Liu, See-Kiong Ng, Bing Qin
| Challenge: | Large Multimodal Models (LMMs) have demonstrated impressive performance on general video comprehension benchmarks, but their robustness needs to be thoroughly investigated for broader applications. |
| Approach: | They propose a temporal robustness benchmark which introduces temporal inconsistency perturbations separately at the visual and textual modalities to assess the robustness of models. |
| Outcome: | The proposed method improves the model’s robustness and reliability in temporal analysis. |
LongGenBench: Long-context Generation Benchmark (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Current long-context benchmarks focus on retrieval-based tests, requiring Large Language Models to locate specific information within extensive input contexts. |
| Approach: | They propose a long-context generation benchmark that allows for flexible configurations of customized generation context lengths. |
| Outcome: | The proposed benchmark improves performance on NIAH and other retrieval-based tests. |
When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors (2026.acl-long)
Copied to clipboard
| Challenge: | Existing metrics fail to distinguish mandatory behaviors required for task success from non-mandatory patterns that reflect a model’s autonomous preferences. |
| Approach: | They propose to use response pattern similarity and action graph similarity to isolate non-mandatory behaviors from mandatory behaviors. |
| Outcome: | Evaluating 18 models from 8 providers on -Bench and 2-Bench against Claude Sonnet 4.5, the authors find that within-family model pairs score 5.9 pp higher in response pattern similarity and action graph similarity . |
MTGER: Multi-view Temporal Graph Enhanced Temporal Reasoning over Time-Involved Document (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work models time implicitly, making it difficult to handle complex relationships . a novel temporal reasoning framework explicitly models the temporal relationships among facts by multi-view temporal graphs . |
| Approach: | They propose a multi-view temporal graph-based temporal reasoning framework that explicitly models the temporal relationships among facts by multi-visit temporal charts. |
| Outcome: | The proposed framework gives more consistent answers under question perturbations. |
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. |