Papers by Zhi Zhang
Capability Salience Vector: Fine-grained Alignment of Loss and Capabilities for Downstream Task Scaling Law (2025.acl-long)
Copied to clipboard
Qiming Ge, Shuhao Xing, Songyang Gao, Yunhua Zhou, Yicheng Zou, Songyang Zhang, Zhi Chen, Hang Yan, Qi Zhang, Qipeng Guo, Kai Chen
| Challenge: | Large language models have demonstrated impressive performance across a wide range of tasks, but this achievement comes with the trade-off of significant computational demands. |
| Approach: | They propose a scaling law that decomposes the overall validation loss and assigns different importance weights to tokens to assess a specific meta-capability. |
| Outcome: | The proposed model can predict the loss trending of models across different levels of computation without a gap between validation loss and model's downstream capabilities. |
Beyond Words: Exploring Cultural Value Sensitivity in Multimodal Models (2025.findings-naacl)
Copied to clipboard
| Challenge: | Using large vision-language models to understand cultural contexts is a critical area of research. |
| Approach: | They conduct a thorough evaluation of multimodal models at different scales, focusing on their alignment with cultural values. |
| Outcome: | The proposed models show that they exhibit sensitivity to cultural values but their performance is highly context-dependent. |
VideoEraser: Concept Erasure in Text-to-Video Diffusion Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show that VideoEraser outperforms prior methods regarding efficacy, integrity, fidelity, robustness, and generalizability. |
| Approach: | They propose a training-free framework that prevents T2V diffusion models from generating videos with undesirable concepts even when explicitly prompted with those concepts. |
| Outcome: | The proposed framework outperforms existing methods in erasure, celebrity erasion, and explicit content erasing tasks. |
Improving Faithfulness of Large Language Models in Summarization via Sliding Generation and Self-Consistency (2024.lrec-main)
Copied to clipboard
| Challenge: | Abstractive summarization models (LLMs) have demonstrated impressive performance in various tasks, but they are still suffering from factual inconsistency problem called hallucination. |
| Approach: | They propose to improve the faithfulness of large language models by impelling them to process the entire article more fairly and faithfully. |
| Outcome: | The proposed strategy improves the faithfulness of large language models in summarization while maintaining their fluency and informativeness. |
DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories (2024.findings-acl)
Copied to clipboard
Jia Li, Ge Li, Yunfei Zhao, Yongmin Li, Huanyu Liu, Hao Zhu, Lecheng Wang, Kaibo Liu, Zheng Fang, Lanshen Wang, Jiazheng Ding, Xuanming Zhang, Yuqi Zhu, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li, Bin Gu, Mengfei Yang
| Challenge: | Existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of Large Language Models (LLMs). |
| Approach: | They propose a repository-level benchmark named DevEval to evaluate LLMs' coding abilities in real-world code repositories. |
| Outcome: | The proposed benchmarks show that the LLMs perform better in real-world code repositories than existing benchmarks. |
Exploring Schema Generalizability of Text-to-SQL (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing text-to-SQL models are limited in their generalizability, despite their performance being over-estimated. |
| Approach: | They propose a framework to generate novel text-to-SQL data via automatic and synchronous (DS, SQL) pair altering. |
| Outcome: | The proposed framework generates text-to-SQL data via automatic and synchronous (DS, SQL) pair altering. |
From Detection to Understanding: Multi-Turn Reasoning for Video Misinformation Analysis (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks focus on binary veracity judgments and do not evaluate process-level justifications for misinformation models. |
| Approach: | They propose a video misinformation analysis benchmark that assesses reasoning in video misinterpretation. |
| Outcome: | The proposed framework improves reasoning accuracy and explanation quality compared to existing models . it covers 12 fine-grained deception categories and progresses from perceptual attribution to intent and persuasion analysis. |
SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility (2026.acl-long)
Copied to clipboard
Xuyang Zhi, Peilun Zhou, Chengqiang Lu, Hang Lv, Yiwei Liang, Rongyang Zhang, Yan Gao, null Yiwu, Yao Hu, Hongchao Gu, Defu Lian, Hao Wang, Enhong Chen
| Challenge: | Large Language Models (LLMs) are shifting the focus from single verifiable tasks toward complex, open-ended real-world scenarios. |
| Approach: | They propose a framework that automatically adjusts reward weights and data importance to synchronize learning intent with data utility for optimal performance. |
| Outcome: | The proposed framework improves model capabilities across all domains and scales. |
UnClE: Explicitly Leveraging Semantic Similarity to Reduce the Parameters of Word Embeddings (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to reduce word embedding parameters ignore semantic information . existing methods do not consider semantic information, allowing for performance degradation . |
| Approach: | They propose a method that leverages semantic similarity with weight sharing to reduce dimensionality of word embeddings. |
| Outcome: | The proposed method reduces word embedding parameters by more than 11x on a standard English-German dataset. |
MEEL: Multi-Modal Event Evolution Learning (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing models fail to grasp the principles governing event evolution in various scenarios. |
| Approach: | They propose a multi-modal event evolution learning approach to grasp event evolution . they propose an instruction encapsulation process that transforms evolving graphs into instruction-tuning data . |
| Outcome: | The proposed model grasps the event evolution mechanism yielding advanced MMER ability. |
Self-Edit: Fault-Aware Code Editor for Code Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing Large language models (LLMs) have low pass rates and accuracy on competitive programming tasks. |
| Approach: | They propose a generate-and-edit approach that uses execution results of generated code from LLMs to improve code quality on competitive programming tasks. |
| Outcome: | The proposed method improves pass@1 by 89% on APPS-dev, 31% on apps-test, and 48% on HumanEval over nine popular code generation LLMs with parameter sizes ranging from 110M to 175B. |
ExploraCoder: Advancing Code Generation for Multiple Unseen APIs via Planning and Chained Exploration (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models face intrinsic limitations in coding with unseen APIs in training corpora. |
| Approach: | They propose a training-free framework that empowers LLMs to invoke multiple unseen APIs in code solution by planning a complex problem into several API invocation subtasks and experimenting with correct API usage at intermediate steps. |
| Outcome: | The proposed framework significantly improves performance for models lacking prior API knowledge, achieving 11.99% over retrieval-based approaches and 17.28% over pretraining-based methods in pass@10. |
Time-for-Accuracy: Formalizing Chain-of-Thought as an Expansion of Logical Depth (2026.findings-acl)
Copied to clipboard
| Challenge: | Chain-of-thought (CoT) prompting can improve multi-step reasoning, but it is unclear what kind of additional sequential computation longer traces actually enable. |
| Approach: | They propose a deletion-based measure of step necessity under a specified inference interface to operationalize realized depth beyond raw length. |
| Outcome: | The proposed method combines effective logical depth with Bennett's logical depth to show that it is more efficient than a linear model. |
CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges (2024.acl-long)
Copied to clipboard
| Challenge: | Large Language Models excel in simple tasks such as generating standalone code units, but real-world software development often involves complex code repositories with complex dependencies and extensive documentation. |
| Approach: | They propose a novel LLM-based agent framework that employs external tools for effective repo-level code generation. |
| Outcome: | The proposed framework outperforms commercial products like Github Copilot in the humanEval benchmark and shows that it is adaptable and efficient across multiple code generation tasks. |
Finite State Automata Inside Transformers with Chain-of-Thought: A Mechanistic Study on State Tracking (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies show that Chain-of-thought (CoT) can enhance the performance of large language models (LLMs) however, there is limited understanding of the algorithms that Transformer+CoT can learn. |
| Approach: | They propose two metrics to evaluate Transformer+CoT's state tracking capabilities and identify the circuit responsible for tracking the world state. |
| Outcome: | The proposed model achieves 100% accuracy for each state, highlighting an implicit finite state automaton (FSA) embedded within the model. |
M3CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thought (2024.acl-long)
Copied to clipboard
| Challenge: | MCoT requires models to leverage knowledge from both textual and visual modalities for step-by-step reasoning. |
| Approach: | They propose a benchmark to address the challenges of MCoT, and evaluate it using vision large language models. |
| Outcome: | The proposed benchmark addresses the above challenges and shows that current models still struggle to reason in M3CoT. |
A Novel Matching Paradigm: Unified Generative and Discriminative LLM with Prompt Compression for Relevance Learning (2026.acl-industry)
Copied to clipboard
Guoliang Zhao, Zixin Cui, Chao Ye, Dengwu He, Fei Huang, Yubo Liu, Shuanglong Li, Tzungren Kuo, Bin Ding, Shuang Zhang, null KunhongZhu, Zhi Guo, Liu Lin
| Challenge: | Existing approaches to matching use Large Language Models as feature extractors, underutilizing their full modeling capabilities. |
| Approach: | They propose a matching paradigm that integrates two-tower, single-towing, and generative tasks within a unified LLM framework via attention-mask partitioning. |
| Outcome: | The proposed model achieves superior performance and strong practical value in an industrial search engine. |
Guide the Many-to-One Assignment: Open Information Extraction via IoU-aware Optimal Transport (2023.acl-long)
Copied to clipboard
Kaiwen Wei, Yiran Yang, Li Jin, Xian Sun, Zequn Zhang, Jingyuan Zhang, Xiao Li, Linhao Zhang, Jintao Liu, Guo Zhi
| Challenge: | Open Information Extraction (OIE) aims to extract structured information from text without the limitations of close ontology. |
| Approach: | They propose a method to assign ground truth labels to parallelly generated tuple proposals . they leverage intersection-over-union (IoU) as assignment quality measurement . |
| Outcome: | The proposed method outperforms the state-of-the-art models on three benchmarks. |
Focus-Constrained Attention Mechanism for CVAE-based Response Generation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models generate high-frequency but trivial responses such as "I don't know" or "I'm ok" due to the discrepancy in discourse-level information, standard models generate one-to-many relationships. |
| Approach: | They propose to transform coarse-grained discourse-level information into fine-grounded word-level knowledge by introducing a fine-grain focus signal and a focus-constrained attention mechanism to take full advantage of focus. |
| Outcome: | The proposed model can generate more diverse and informative responses compared with state-of-the-art models. |
On Safety Risks in Experience-Driven Self-Evolving Agents (2026.findings-acl)
Copied to clipboard
Weixiang Zhao, Yichen Zhang, Yingshuo Wang, Yang Deng, Yanyan Zhao, Xuda Zhi, Yongbo Huang, Hao He, Wanxiang Che, Bing Qin, Ting Liu
| Challenge: | Experience-driven self-evolution has emerged as a promising paradigm for improving the autonomy of large language model agents, yet its reliance on self-curated experience introduces underexplored safety risks. |
| Approach: | They investigate how experience accumulation and utilization in self-evolving agents affect safety performance across web-based and embodied environments. |
| Outcome: | The findings expose inherent limitations of current self-evolving agents and call for more principled strategies to ensure safe and reliable adaptation. |
HiRoPE: Length Extrapolation for Code Models Using Hierarchical Position (2024.acl-long)
Copied to clipboard
| Challenge: | Existing LLMs are constrained by their pre-trained context lengths, leading to performance issues . elucidating this limitation, we propose a training-free solution to the context length limitation in LLM applications . |
| Approach: | They propose a method that integrates hierarchical rotary position embedding into LLMs without extra training costs. |
| Outcome: | The proposed method improves performance on language modeling and long code completion tasks. |
SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment (2025.findings-emnlp)
Copied to clipboard
Yuqing Huang, Rongyang Zhang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Xuyang Zhi, Guiquan Liu, Xin Li, Hao Wang, Enhong Chen
| Challenge: | Existing solutions for supervised fine-tuning often lead to catastrophic forgetting, where models lose their previously acquired knowledge and general capabilities. |
| Approach: | They propose a self-distribution alignment method that aligns input sequence logits to preserve the model’s semantic distribution, thereby mitigating catastrophic forgetting and improving downstream performance. |
| Outcome: | The proposed method achieves a superior balance between downstream learning and general capability retention. |
LLM-Driven Implicit Target Augmentation and Fine-Grained Contextual Modeling for Zero-Shot and Few-Shot Stance Detection (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies on zero-shot and few-shot stance detection neglect implicit yet semantically important targets. |
| Approach: | They propose a framework that uses Large Language Models to annotate implicit targets . they also propose 'DyMCA' to dynamically adjust text-target contributions based on context . |
| Outcome: | The proposed framework achieves state-of-the-art on a benchmark dataset. |
Benchmarking Long-Context Language Models on Long Code Understanding (2025.acl-long)
Copied to clipboard
Jia Li, Xuyuan Guo, Lei Li, Kechi Zhang, Ge Li, Jia Li, Zhengwei Tao, Fang Liu, Chongyang Tao, Yuqi Zhu, Zhi Jin
| Challenge: | Currently, long-context language models are limited by the lack of a rigorous evaluation framework for long code understanding. |
| Approach: | They propose to use a long code understanding benchmark LongCodeU to evaluate LCLMs' long code comprehension ability for practical applications. |
| Outcome: | The proposed benchmarks show that current LCLMs are limited in their long code understanding ability, particularly when the long code length is greater than 32K, falling far short of their claimed 128K to 1M context windows. |
AutoEvolve: Automatically Evolving Queries for Applicable and Scalable Retrieval-Augmented Generation Benchmarking (2025.findings-emnlp)
Copied to clipboard
Ding-Chu Zhang, Xiaowen Zhang, Yue Fei, Renjun Hu, Xiao-Wen Yang, Zhi Zhou, Baixuan Li, Yu-Feng Li, Xing Shi, Wei Lin
| Challenge: | Existing automated generation methods exhibit Weak Applicability and Weak Scalability . existing methods are limited by their reliance on metadata from specific corpora . |
| Approach: | They propose an approach to generate scalable RAG benchmarks using corpus-agnostic methods . they propose a difficulty-guided metric that directs query evolution process . |
| Outcome: | The proposed approach evolves queries significantly more challenging than existing methods . it is able to dynamically increase difficulty, limiting scalability of the query . |
Detection, Diagnosis, and Explanation: A Benchmark for Chinese Medial Hallucination Evaluation (2024.lrec-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have made significant progress in recent years, but their practical use is hindered by their tendency to generate hallucinations. |
| Approach: | They propose to use ICD-10 and MeSH to evaluate LLMs' ability to detect medical hallucinations and make accurate diagnoses in noisy environments. |
| Outcome: | The proposed benchmark can be used to evaluate LLMs’ ability to detect medical hallucinations, make accurate diagnoses in noisy conditions, and provide plausible explanations. |
NL2Lean: Translating Natural Language into Lean 4 through Multi-Aspect Reinforcement Learning (2025.emnlp-main)
Copied to clipboard
Yue Fang, Shaohan Huang, Xin Yu, Haizhen Huang, Zihan Zhang, Weiwei Deng, Furu Wei, Feng Sun, Qi Zhang, Zhi Jin
| Challenge: | Existing formal proof assistants rely on instruction tuning and lack fine-grained structural and semantic alignment. |
| Approach: | They propose a reinforcement learning framework that enables LLMs to translate natural language into formal language such as Lean 4 . they use a model with basic translation ability to refine the model's reinforcement learning . |
| Outcome: | The proposed method outperforms baseline models on NL-to-Lean 4 tasks. |
Trigger is Not Sufficient: Exploiting Frame-aware Knowledge for Implicit Event Argument Extraction (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods to extract event arguments focus on learning pair-wise information between arguments and the given trigger. |
| Approach: | They propose a framework to extract event-related arguments from a given event frame-level scope. |
| Outcome: | The proposed method achieves state-of-the-art on the RAMS dataset. |
Revisit Self-Debugging with Self-Generated Tests for Code Generation (2025.acl-long)
Copied to clipboard
Xiancai Chen, Zhengwei Tao, Kechi Zhang, Changzhi Zhou, Xinyu Zhang, Wanli Gu, Yuanpeng He, Mengdi Zhang, Xunliang Cai, Haiyan Zhao, Zhi Jin
| Challenge: | Large language models (LLMs) have made significant advances in code generation, but they still face challenges when tackling complex programming tasks beyond their basic capabilities. |
| Approach: | They propose to integrate self-generated tests into the code generation process . they propose to use post-execution and in-exection self-debugging to mitigate test bias . |
| Outcome: | The proposed method improves the performance of large language models in code generation tasks by leveraging execution feedback from tests. |
Focused-DPO: Enhancing Code Generation Through Focused Preference Optimization on Error-Prone Points (2025.findings-acl)
Copied to clipboard
| Challenge: | Current code generation models produce errors concentrated at specific error-prone points, affecting accuracy of code. |
| Approach: | They propose a framework that focuses preference optimization on error-prone areas . focused-DPO improves the accuracy and reliability of code generation by reducing common errors . |
| Outcome: | The proposed framework improves code generation by focusing on error-prone areas. |
Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree Search (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Extensive research has highlighted the quality of instruction data is essential for the success of this alignment. |
| Approach: | They propose a framework for iteratively improving existing instruction data by using Monte Carlo tree search to find suitable prompts that align the language model to effectively learn multiple skills. |
| Outcome: | The proposed framework improves the evaluation scores of seed instruction data, raising the average evaluation scores from 2.19 to 3.81. |
Integrating Physician Diagnostic Logic into Large Language Models: Preference Learning from Process Feedback (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have shown that large language models can enhance response richness and coherence, but there is a pressing need to bolster the model’s capacity for diagnostic logic to ensure patient safety. |
| Approach: | They propose an approach termed preference learning from process feedback (PLPF) that integrates the doctor’s diagnostic logic into LLMs. |
| Outcome: | The proposed approach improves the diagnostic accuracy of the baseline model in medical conversations by 17.6%, surpassing the performance of traditional approaches. |
CK-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing frameworks for referring expression comprehension with commonsense knowledge are lacking in the field of multimodal referring . |
| Approach: | They propose a framework for commonsense knowledge Enhanced Transformers which integrates commonsensible knowledge into representations of objects in an image. |
| Outcome: | The proposed framework improves on the existing state of the art in referring expression comprehension with commonsense knowledge (CK-Transformer) it achieves 3.14% accuracy over the existing framework. |
Cultural Concept Adaptation on Multimodal Reasoning (2023.emnlp-main)
Copied to clipboard
| Challenge: | Past methods focused on multilingual and multimodal capabilities, and the improvement of multicultural competence is still an unexplored problem. |
| Approach: | They propose an annotation-free method for cultural-concept adaptation and construct a concept mapping set to facilitate model's comprehension of cultural-consensual mappings. |
| Outcome: | The proposed method outperforms baseline models on zero-shot and few-shot settings on five languages and cultures. |
Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs (2024.lrec-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have made significant advances in code generation through the ‘Chain-of-Thought’ prompting technique. |
| Approach: | They propose a framework which aims to transfer LLMs’ reasoning capabilities to smaller models through distillation. |
| Outcome: | The proposed framework improves the smaller model's code generation performance by over 130% on the APPS benchmark. |
Towards Autonomous Tool Utilization in Language Models: A Unified, Efficient and Scalable Framework (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent advances in tool learning for large language models have led to a new trend to allow LLMs to leverage external tools. |
| Approach: | They propose a framework for fine-tuning language models that categorizes queries into three different types . they also introduce an "instruct, execute, and reformat" strategy specifically designed for efficient data annotation . |
| Outcome: | The proposed framework surpasses open-source language models and GPT-3.5/4 on multiple evaluation metrics. |
Event Causality Extraction via Implicit Cause-Effect Interactions (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have not exploited the interactions between the cause and effect event that could provide crucial clues for causality reasoning. |
| Approach: | They propose an Implicit Cause-Effect interaction framework which captures the implicit intra- and inter-event interactions by incorporating the privileged information for reasoning. |
| Outcome: | The proposed framework captures the implicit intra- and inter-event interactions by incorporating the privileged information (ground truth event types and arguments) for reasoning. |
Ted-Tok: Maintaining an Evolving Vocabulary for Lifelong Learning (2026.acl-long)
Copied to clipboard
| Challenge: | a static tokenizer fragments newly emerging lexical items as language evolves . as language grows, a dynamic tokenizer reduces compression efficiency and performance . |
| Approach: | They propose a Temporal Drift Tokenizer that maintains an evolving vocabulary that adapts to emerging linguistic patterns over time. |
| Outcome: | The proposed tokenizer maintains an evolving vocabulary that adapts to emerging linguistic patterns over time. |
KoCo-Bench: Can Large Language Models Leverage Domain Knowledge in Software Development? (2026.acl-long)
Copied to clipboard
Xue Jiang, Ge Li, Jiaru Qian, Xianjie Shi, Chenjie Li, Hao Zhu, Ziyu Wang, Jielun Zhang, Zeyu Zhao, Kechi Zhang, Jia Li, Wenpin Jiao, Zhi Jin, Yihong Dong
| Challenge: | Existing domain-specific code benchmarks focus on assessing what knowledge LLMs possess rather than how they acquire and apply new knowledge. |
| Approach: | They propose a benchmark to evaluate domain specialization methods in real-world software development. |
| Outcome: | KOCO-bench is a new benchmark for evaluating domain specialization methods in real-world software development. |
MusTQ: A Temporal Knowledge Graph Question Answering Dataset for Multi-Step Temporal Reasoning (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on fact-centered reasoning with limited attention to temporal reasoning. |
| Approach: | They propose a new TKGQA dataset, MusTQ, which contains 666K multi-step temporal reasoning questions and a TKG. |
| Outcome: | The proposed model achieves state-of-the-art multi-step temporal reasoning ability with entity-time attention mechanism and optimized temporal knowledge graph representation. |
Basic Reading Distillation (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models require high computational resources which limits their deployment in real-world applications. |
| Approach: | They propose to distill large language models into smaller language models by either knowledge distillation or task distillation. |
| Outcome: | The proposed model outperforms or performs comparable to over 20x bigger LLMs on language inference benchmarks and BIG-bench tasks. |
GUI0: Self-Evolving Foundational GUI Agents in Super App Ecosystems (2026.acl-long)
Copied to clipboard
Xinyi Wang, Wei Dai, Kyle Qiao, Ke Wang, Peng Chen, Gang Cao, null Kangqin, Zhongpu Wang, Xiaode Zhang, Yanming Liu, Jihao Gu, Jingtao Xu, Gong Zhi
| Challenge: | Automated interaction with graphical user interfaces (GUIs) is central to general artificial intelligence, but remains challenging within Super App ecosystems. |
| Approach: | They propose a framework synergizing autonomous data synthesis with dual-agent co-evolution . GUI0 establishes a domain-aware foundation model via synthesized corpora and employs curriculum-driven reinforcement learning . |
| Outcome: | The proposed framework outperforms Gemini-2.5-Pro and Claude-4-Sonnet in the SuperAPP benchmark and has universal efficacy across base models. |
CodeDPO: Aligning Code Models with Self Generated and Verified Source Code (2025.acl-long)
Copied to clipboard
| Challenge: | Existing training methods for code generation do not improve code correctness and efficiency. |
| Approach: | They propose a framework that integrates preference learning into code generation to improve code correctness and efficiency. |
| Outcome: | The proposed framework improves code correctness and efficiency by integrating preference learning into code generation. |
FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models (2025.naacl-long)
Copied to clipboard
Xin Guo, Haotian Xia, Zhaowei Liu, Hanyang Cao, Zhi Yang, Zhiqiang Liu, Sizhe Wang, Jinyi Niu, Chuqi Wang, Yanhui Wang, Xiaolong Liang, Xiaoming Huang, Bing Zhu, Zhongyu Wei, Yun Chen, Weining Shen, Liwen Zhang
| Challenge: | Large language models have demonstrated outstanding performance in various natural language processing tasks, but their security capabilities in the financial domain have not been explored. |
| Approach: | They propose to use a benchmark to evaluate large language models' financial domain knowledge and practical abilities. |
| Outcome: | The proposed benchmark evaluates large language models' financial domain knowledge and practical abilities. |
RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization (2026.acl-long)
Copied to clipboard
Yihong Dong, Xue Jiang, Yongding Tao, Huanyu Liu, Kechi Zhang, Lili Mou, Rongyu Cao, Yingwei MA, Jue Chen, Binhua Li, Zhi Jin, Fei Huang, Yongbin Li, Ge Li
| Challenge: | Reinforcement Learning with Verifiable Reward (RLVR) has significantly advanced the complex reasoning abilities of Large Language Models (LLMs). |
| Approach: | They propose a hybrid-policy optimization approach that synergizes internal exploitation with external data to achieve stronger reasoning capabilities. |
| Outcome: | The proposed approach achieves state-of-the-art performance on six math reasoning benchmarks and superior performance on out-of distribution reasoning tasks. |
NeuroAda: Activating Each Neuron’s Potential for Parameter-Efficient Fine-Tuning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for parameter-efficient fine-tuning are limited and require computational and memory resources. |
| Approach: | They propose a parameter-efficient fine-tuning method that enables fine-grained model finetunation while maintaining high memory efficiency. |
| Outcome: | The proposed method reduces CUDA memory usage by up to 60% while maintaining high performance. |