Papers by Yuxiang Liu
RSMeM: Knowledge-Enhanced Memory Evolution for Remote Sensing Agents with Systematic Evaluation (2026.acl-long)
Copied to clipboard
Bingxian Wu, Yu Zhang, Zonghao Guo, Tang Liu, Chen Qian, Yuxiang Lu, Xingbo Du, Yanghao Li, Yidan Zhang, Chi Chen, Ling Yao, Chenghu Zhou, Maosong Sun
| Challenge: | Existing RS agents built on general-purpose LLMs are domain-agnostic, resulting in brittle and error-prone workflows. |
| Approach: | They propose a knowledge-enhanced memory evolution mechanism that bootstraps RS agents with pre-distilled domain knowledge and iteratively integrates online experience for robust multi-step tool execution. |
| Outcome: | Experiments show that the new model improves tool-use performance and accuracy . iteratively, iteration of the model integrates online experience for robust multi-step tool execution . |
Ask To The Point: Open-Domain Entity-Centric Question Generation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | *entity-centric question generation (ECQG) is a task motivated by real-world applications such as topic-specific learning, assisted reading, and fact-checking. |
| Approach: | They propose a PLM-based framework GenCONE with two modules: content focusing and question verification. |
| Outcome: | The proposed framework outperforms baselines and is effective and complementary in generating high-quality questions. |
PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them (2021.tacl-1)
Copied to clipboard
Patrick Lewis, Yuxiang Wu, Linqing Liu, Pasquale Minervini, Heinrich Küttler, Aleksandra Piktus, Pontus Stenetorp, Sebastian Riedel
| Challenge: | Open-domain Question Answering models that directly leverage question-answer (QA) pairs show promise in terms of speed and memory compared with conventional models which retrieve and read from text corpora. |
| Approach: | They propose a question-answer (QA)-pair retriever to facilitate improved QA-patch models by introducing Probably Asked Questions (PAQ) they propose QA pair retriever, RePAQ, which preempts and caches test questions, enabling it to match the accuracy of recent retrieve-and-read models, whilst being significantly faster. |
| Outcome: | The proposed model outperforms baseline models by 5% but trails RePAQ by 15% . it can be configured for size (under 500MB) or speed (over 1K questions per second) while retaining high accuracy. |
SILC-EFSA: Self-aware In-context Learning Correction for Entity-level Financial Sentiment Analysis (2025.coling-main)
Copied to clipboard
Senbin Zhu, ChenYuan He, Hongde Liu, Pengcheng Dong, Hanjie Zhao, Yuchen Yan, Yuxiang Jia, Hongying Zan, Min Peng
| Challenge: | Currently, most sentiment analysis corpora use sequence-level annotation. |
| Approach: | They propose a two-stage approach to financial entity-level sentiment analysis called Self-aware In-context Learning Correction. |
| Outcome: | The proposed approach achieves state-of-the-art on the largest English and Chinese financial entity-level sentiment analysis datasets to date. |
ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models (2024.emnlp-main)
Copied to clipboard
Yuxiang Zhang, Jing Chen, Junjie Wang, Yaxin Liu, Cheng Yang, Chufan Shi, Xinyu Zhu, Zihao Lin, Hanwen Wan, Yujiu Yang, Tetsuya Sakai, Tian Feng, Hayato Yamana
| Challenge: | Currently, tool-augmented large language models (LLMs) only achieve total scores of 45.3 and 37.0, respectively, on a scale of 100. |
| Approach: | They propose a multi-level diagnostic process to assess the LLM's hallucinations through two perspectives: depth and breadth. |
| Outcome: | The proposed diagnostic process assesses the hallucinations of large language models through two perspectives: depth and breadth. |
GEMS: Generation-Based Event Argument Extraction via Multi-perspective Prompts and Ontology Steering (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for event argument extraction rely on a single prompt . existing methods ignore complex structural and dynamic interdependencies between event arguments . |
| Approach: | They propose a multi-prompt learning framework that generates event arguments via multi-perspective prompts and ontology steering. |
| Outcome: | The proposed framework captures interrelationships between arguments and ontology steering . it uses multiple unfilled prompts for each sentence to generate event arguments . |
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. |
APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs (2025.acl-long)
Copied to clipboard
Yuxiang Huang, Mingye Li, Xu Han, Chaojun Xiao, Weilin Zhao, Sun Ao, Hao Zhou, Jie Zhou, Zhiyuan Liu, Maosong Sun
| Challenge: | Long-context inference is crucial for advancing large language models, but its prefill speed remains a bottleneck. |
| Approach: | They propose an efficient long-context inference framework that leverages multi-host approximate attention to enhance prefill speed. |
| Outcome: | The proposed framework achieves speedups of 9.2, 4.2, and 1.6 without any degradation in performance. |
STORM-BORN: A Challenging Mathematical Derivations Dataset Curated via a Human-in-the-Loop Multi-Agent Framework (2025.findings-acl)
Copied to clipboard
Wenhao Liu, Zhenyi Lu, Xinyu Hu, Jerry Zhang, Dailin Li, Jiacheng Cen, Huilin Cao, Haiteng Wang, Yuhan Li, Xie Kun, Dandan Li, Pei Zhang, Chengbo Zhang, Yuxiang Ren, Xiaohong Huang, Yan Ma
| Challenge: | Existing datasets suffer from outdated and insufficient challenging content, neglecting human-like reasoning, and limited reliability due to single-LLM generation. |
| Approach: | They propose a human-in-the-loop, multi-agent data generation framework that integrates reasoning-dense filters, multiagent collaboration, and human mathematicians’ evaluations to ensure the reliability and quality of the dataset. |
| Outcome: | The proposed framework improves accuracy and quality of the 2,000-synthesized datasets by integrating reasoning-dense filters, multi-agent collaboration, and human mathematicians’ evaluations. |
\mathcal XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies focus on the data perspectives of instruction tuning, leaving room for exploring advanced training schemes. |
| Approach: | They argue that prior works overlook the possibility of improving code instruction tuning by advancing existing training schemes. |
| Outcome: | The proposed model is dense because all parameters are activated to predict the next token (assuming it is a decoder-only LLM). |
Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding (2024.emnlp-main)
Copied to clipboard
Weilin Zhao, Yuxiang Huang, Xu Han, Wang Xu, Chaojun Xiao, Xinrong Zhang, Yewei Fang, Kaihuo Zhang, Zhiyuan Liu, Maosong Sun
| Challenge: | Speculative decoding is a widely used method that accelerates the generation process of large language models (LLMs) drafting efficiency has become a bottleneck in the final speedup of speculative drafting, therefore generating longer drafts at less cost can lead to better speedup. |
| Approach: | They propose a method that uses existing model to drafting and target LLM to verify draft in a low-cost parallel manner. |
| Outcome: | The proposed method can achieve speedups of up to 2.4 over speculative decoding and 3.9 over vanilla decoding without fine-tuning draft and target models. |
DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) with web search capabilities show significant potential for deep research. |
| Approach: | They introduce a framework for end-to-end training of LLM-based deep research agents . they implement a specialized multi-agent architecture where browsing agents extract relevant information from various webpage structures. |
| Outcome: | The proposed framework improves on open-domain research tasks by 28.9 points over prompt engineering and 7.2 points over RAG-based RL agents. |
APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention (2026.acl-long)
Copied to clipboard
Yuxiang Huang, Mingye Li, Xu Han, Chaojun Xiao, Weilin Zhao, Ao Sun, Ziqi Yuan, Hao Zhou, Fandong Meng, Zhiyuan Liu
| Challenge: | Existing methods for long-video inference use compression or sparse attention . existing methods restrict LMMs from handling longer, more complex videos . |
| Approach: | They propose a sequence-parallel framework with optimized attention that accelerates long-video inference across multiple GPUs. |
| Outcome: | The proposed framework delivers speedups of 12.72x, 1.70x, and 1.18x over FlashAttn, ZigZagRing, and APB without significant performance loss. |
AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents (2025.findings-acl)
Copied to clipboard
Yuxiang Chai, Siyuan Huang, Yazhe Niu, Han Xiao, Liang Liu, Guozhi Wang, Dingyu Zhang, Shuai Ren, Hongsheng Li
| Challenge: | a new dataset is being developed to improve the capabilities of mobile GUI-control agents. |
| Approach: | They propose a dataset designed for generalist mobile GUI-control agents . they use screenshots from popular mobile applications to create a detailed GUI-annotated dataset . |
| Outcome: | The Android Multi-annotation EXpo (AMEX) is a large-scale dataset for generalist mobile GUI-control agents . it includes screenshots from popular mobile applications, which are annotated at multiple levels . |
DRAGON: Domain-specific Robust Automatic Data Generation for RAG Optimization (2026.findings-eacl)
Copied to clipboard
Haiyang Shen, Hang Yan, Zhongshi Xing, Mugeng Liu, Yue Li, Zhiyang Chen, Yuxiang Wang, Jiuzheng Wang, Yun Ma
| Challenge: | Existing retrieval-augmented generation paradigms rely heavily on public knowledge . Existing RAGs reliant on public information and often falter when faced with domain-specific queries. |
| Approach: | They propose a framework that combines a data-construction modeling approach with a scalable synthetic data-generation pipeline to optimize domain-specific retrieval performance. |
| Outcome: | The proposed framework optimizes domain-specific retrieval performance and bolsters retriever robustness. |
FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling (2025.acl-long)
Copied to clipboard
Weilin Zhao, Tengyu Pan, Xu Han, Yudi Zhang, Sun Ao, Yuxiang Huang, Kaihuo Zhang, Weilun Zhao, Yuxuan Li, Jie Zhou, Hao Zhou, Jianyong Wang, Maosong Sun, Zhiyuan Liu
| Challenge: | Speculative sampling is an efficient way to accelerate the auto-regressive generation process of large language models. |
| Approach: | They propose a frequency-ranked speculative sampling framework that optimizes draft candidate selection through vocabulary space compression. |
| Outcome: | Experiments show that FR-Spec reduces LM Head computation overhead by 75% while ensuring the equivalence of the final output distribution. |
TempCompass: Do Video LLMs Really Understand Videos? (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks on video large language models lack a comprehensive feedback on temporal perception ability . current models cannot distinguish between different temporal aspects and are limited in task formats . |
| Approach: | They propose a benchmark to evaluate temporal perception ability of video large language models . they construct conflicting videos that share the same static content but differ in a specific temporal aspect . |
| Outcome: | The proposed benchmarks show that video large language models exhibit poor temporal perception ability. |
LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark (2026.findings-acl)
Copied to clipboard
Guangyi Liu, Pengxiang Zhao, Liang Liu, Zhiming Chen, Yuxiang Chai, Yaozhen Liang, WenHao Wang, Siheng Chen, Zhengxi Lu, Shuai Ren, Hao Wang, Shibo He, Yong Liu, Wenchao Meng
| Challenge: | Mobile GUI agents show promise in automating tasks but face significant generalization challenges in long-tail scenarios. |
| Approach: | They propose a benchmark framework for mobile GUI agents that measures the performance of GUI agents by analyzing their performance. |
| Outcome: | The LearnGUI benchmark outperforms existing methods in offline and online evaluations and demonstrates consistent gains across model architectures. |
FaiMA: Feature-aware In-context Learning for Multi-domain Aspect-based Sentiment Analysis (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for aspect-based sentiment analysis are limited and integrating with existing techniques is difficult. |
| Approach: | They propose a framework that utilizes in-context learning as a feature-aware mechanism that facilitates adaptive learning in multi-domain ABSA tasks. |
| Outcome: | The proposed framework achieves significant performance improvements in multiple domains compared to baselines, increasing F1 by 2.07% on average. |
A3: Android Agent Arena for Mobile GUI Agents with Essential-State Procedural Evaluation (2026.findings-acl)
Copied to clipboard
Yuxiang Chai, Shunye Tang, Han Xiao, Weifeng Lin, Hanhao Li, Jiayu Zhang, Liang Liu, Pengxiang Zhao, Guangyi Liu, Guozhi Wang, Shuai Ren, Rongduo Han, Haining Zhang, Siyuan Huang, Hongsheng Li
| Challenge: | Existing evaluation methods for mobile GUI agents rely on static frame assessments or offline static apps. |
| Approach: | They propose an evaluation system that leverages large language models as reward models to verify task completion and process achievement. |
| Outcome: | The proposed system addresses the limitations of traditional function based evaluation methods on online dynamic apps. |
Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding (2026.eacl-long)
Copied to clipboard
| Challenge: | Autoregressive (AR) models excel at generating temporally coherent audio by producing tokens sequentially, yet they often falter in faithfully following complex textual prompts. |
| Approach: | They propose a lightweight auxiliary model trained with a GAE-inspired objective to predict final instruction-following quality from partial generations. |
| Outcome: | The proposed model achieves 10 points improvement in CLAP score over baseline AR models while maintaining computational parity with best-of-N decoding. |
Negative-Aware Diffusion Process for Temporal Knowledge Graph Extrapolation (2026.findings-eacl)
Copied to clipboard
| Challenge: | Temporal Knowledge Graphs (TKGs) are dynamic structures representing entities and their evolving relationships through time. |
| Approach: | They propose a non-parametric model that encodes subject-centric histories into sequential embeddings. |
| Outcome: | The proposed model encodes subject-centric histories of entities, relations and temporal intervals into sequential embeddings. |
OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems (2024.acl-long)
Copied to clipboard
Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen Thai, Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, Jie Liu, Lei Qi, Zhiyuan Liu, Maosong Sun
| Challenge: | Large Language Models (LLMs) and Large Multimodal Models have exceeded general human capabilities in various tasks. |
| Approach: | They present an Olympiad-level bilingual multimodal scientific benchmark featuring 8,476 problems from Olympiad level mathematics and physics competitions. |
| Outcome: | The best performing model, GPT-4V, attains an average score of 17.97% on OlympiadBench, with a mere 10.74% in physics, highlighting the benchmark rigor and the intricacy of physical reasoning. |
Black-Box Tuning of Vision-Language Models with Effective Gradient Approximation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large vision-language models are often not open-source due to preventing abuse or commercial factors. |
| Approach: | They propose a method for parameter-efficient fine-tuning to improve model accessibility . large models are often not open-source due to preventing abuse or commercial factors . they propose implementing a lightweight adapter over the output feature of an inaccessible model . |
| Outcome: | The proposed methods improve on 11 benchmarks and are made publicly available. |
SAFETY-J: Evaluating Safety with Critique (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Current methods focus on binary safety classifications and lack detailed critique, limiting their utility for model improvement and user trust. |
| Approach: | They propose a bilingual generative safety evaluator for English and Chinese with critique-based judgment that utilizes a robust training dataset and augmented query-response pairs to assess safety across various scenarios comprehensively. |
| Outcome: | The proposed model improves safety evaluations by assessing the quality of critiques with minimal human intervention. |
OpenResearcher: Unleashing AI for Accelerated Scientific Research (2024.emnlp-demo)
Copied to clipboard
Yuxiang Zheng, Shichao Sun, Lin Qiu, Dongyu Ru, Cheng Jiayang, Xuefeng Li, Jifan Lin, Binjie Wang, Yun Luo, Renjie Pan, Yang Xu, Qingkai Min, Zizhao Zhang, Yiwen Wang, Wenjie Li, Pengfei Liu
| Challenge: | Global scientific publications are growing annually by about 4%-5% (Pinedo et al., 2024). |
| Approach: | They introduce an AI-assisted platform that answers diverse questions from researchers using Retrieval-Augmented Generation (RAG) they develop various tools to understand queries, search from the scientific literature, filter retrieved information, provide accurate and comprehensive answers, and self-refine answers. |
| Outcome: | OpenResearcher is built on Retrieval-Augmented Generation (RAG) to integrate Large Language Models (LLMs) with up-to-date, domain-specific knowledge. |
Task-aware Contrastive Mixture of Experts for Quadruple Extraction in Conversations with Code-like Replies and Non-opinion Detection (2025.emnlp-main)
Copied to clipboard
| Challenge: | Applying Large Language Models (LLMs) for this specific task presents two primary challenges: the accurate extraction of multiple elements and the understanding of complex dialogue reply structure. |
| Approach: | They propose a novel LLM-based multi-task approach to extract sentiment quadruples from conversations by integrating expert-level contrastive loss within task-oriented mixture of experts layer. |
| Outcome: | The proposed method outperforms existing fine-tuning techniques in terms of accuracy and computational efficiency. |
DiFiNet: Boundary-Aware Semantic Differentiation and Filtration Network for Nested Named Entity Recognition (2024.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to Named Entity Recognition focus on identifying non-nested entities, but there is no explicit guidance for boundary detection. |
| Approach: | They propose a Boundary-aware Semantic Differentiation and Filtration Network for nested NER that leverages a biaffine attention mechanism to generate a span representation matrix. |
| Outcome: | Extensive experiments on three benchmark datasets demonstrate the proposed model yields a new state-of-the-art performance. |
MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents (2026.acl-long)
Copied to clipboard
Pengxiang Zhao, Guangyi Liu, Yaozhen Liang, Weiqing He, Zhengxi Lu, WenHao Wang, Yuehao Huang, Yuxiang Chai, Zhaolu Kang, Yaxuan Guo, Hao Wang, Kexin Zhang, Liang Liu, Yong Liu
| Challenge: | Shortcuts such as APIs and deep-links have emerged as efficient complements to flexible GUI operations, but systematic evaluation of GUI–shortcut hybrid agents remains underexplored. |
| Approach: | They propose a benchmark that evaluates GUI-shortcut hybrid agents with a specific focus on the mobile domain. |
| Outcome: | MAS-Bench evaluates agent's ability to generate shortcuts by discovering and creating reusable, low-cost workflows. |
Beyond Modality Collapse: Taming Guided Modality Entropy for Omni-modal Emotion Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | EmoOmni is a data paradigm for omni-modal large language models that can be used for emotion reasoning. |
| Approach: | They propose a data paradigm that interleaves guided tokens into reasoning traces to enforce structured evidence extraction. |
| Outcome: | The proposed paradigm over-relys on a dominant modality while neglecting complementary cues. |
Libra-VLA: Achieving Learning Equilibrium via Asynchronous Coarse-to-Fine Dual-System (2026.acl-long)
Copied to clipboard
| Challenge: | Vision-Language-Action models ground high-level semantic instructions into executable physical actions. |
| Approach: | They propose a Coarse-to-Fine Dual-System VLA architecture that decouples learning complexity into a coarse-to fine hierarchy while leveraging structural modularity to implement an asynchronous execution strategy. |
| Outcome: | The proposed architecture decouples learning complexity into a coarse-to-fine hierarchy while leveraging structural modularity to implement an asynchronous execution strategy. |
GenWebNovel: A Genre-oriented Corpus of Entities in Chinese Web Novels (2025.coling-main)
Copied to clipboard
| Challenge: | Existing literature on nested entity recognition is insufficient partly due to insufficient annotated data. |
| Approach: | They propose a method that utilizes a pre-trained language model as an In-context learning example retriever to boost the performance of large language models. |
| Outcome: | The proposed method significantly enhances entity recognition, matching state-of-the-art (SOTA) models without additional training data. |
Writing Like the Best: Exemplar-Based Expository Text Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for expository text generation rely on extensive domain corpora and are difficult to adapt topic-specific content. |
| Approach: | They propose a task to generate an expository text on a new topic using an exemplar on . they propose Adaptive Imitation and a Recurrent Plan-then-Adapt framework that leverages large language models for effective adaptive imitation. |
| Outcome: | The proposed framework surpasses existing baselines in producing factual, consistent, and relevant texts for this task. |
Predicting the Unpredictable: Uncertainty-Aware Reasoning over Temporal Knowledge Graphs via Diffusion Process (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for Temporal Knowledge Graph reasoning capture indeterminacy in future events, but they are limited in capturing it. |
| Approach: | They propose a Temporal Knowledge Graph reasoning process that denoises historical events and introduces Gaussian noise to corrupt target facts. |
| Outcome: | Empirical results show that DiffuTKG outperforms state-of-the-art methods on four real-world datasets. |
DialogueMMT: Dialogue Scenes Understanding Enhanced Multi-modal Multi-task Tuning for Emotion Recognition in Conversations (2025.coling-main)
Copied to clipboard
| Challenge: | Existing ERC methods fail to handle emotional cues from both visual sources and discourse structures due to the complexity of visual scenes and contextual dependencies in conversations. |
| Approach: | They propose a framework for Emotion Recognition in conversations that utilizes multi-task instruction tuning to enhance the model's understanding of multi-modal dialogue scenes. |
| Outcome: | The proposed framework outperforms existing state-of-the-art models on three benchmark ERC datasets and is based on a video-language connector and a chain-of thought strategy. |
Analysing The Impact of Sequence Composition on Language Model Pre-Training (2024.acl-long)
Copied to clipboard
Yu Zhao, Yuanbin Qu, Konrad Staniszewski, Szymon Tworkowski, Wei Liu, Piotr Miłoś, Yuxiang Wu, Pasquale Minervini
| Challenge: | Existing studies show that pretraining sequence composition strategy can lead to distracting information from previous documents. |
| Approach: | They propose to use a sequence construction method to concatenate documents into fixed-length sequences to compute the likelihood of each token given its context. |
| Outcome: | The proposed method can improve in-context learning, knowledge memorisation and context utilisation without sacrificing efficiency. |
Synergetic Interaction Network with Cross-task Attention for Joint Relational Triple Extraction (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing approaches to joint entity-relation extraction are limited in their ability to capture the interdependence between the two sub-tasks. |
| Approach: | They propose a synergistic approach to capture interdependence between named entity recognition and relation extraction sub-tasks in a Synergetic Interaction Network. |
| Outcome: | The proposed model achieves significantly better performance on three benchmark datasets. |
Exploration-Exploitation Reshaping towards Efficient Reasoning for Large Language Models (2026.findings-acl)
Copied to clipboard
Yufeng Shi, Weilin Luo, Yuxiang Zhang, Zongmeng Zhang, Haoyang Liu, Yubing Wang, Bin Wang, Wengang Zhou, Houqiang Li
| Challenge: | Large Reasoning Models (LRMs) are constrained by the overthinking issue. |
| Approach: | They propose a policy optimization framework that reshapes the exploration and exploitation through two core components: self-imitation and self-guidance exploration. |
| Outcome: | The proposed model achieves superior reasoning efficiency without compromising overall accuracy. |
TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles (2026.acl-long)
Copied to clipboard
Yirong Zeng, Yufei Liu, Xiao Ding, Yutai Hou, Yuxian Wang, Wu Ning, Haonan Song, Dandan Tu, Qixun Zhang, Yuxiang He, Bibo Cai, Ting Liu
| Challenge: | Instruction Following (IF) is a core capability of LLMs, requiring strict adherence to diverse constraints. |
| Approach: | They propose a framework that uses tiny language models to evaluate instruction following . they propose to use a set of specialized tiny language model to provide rewards for soft constraints. |
| Outcome: | The proposed framework outperforms baseline models by 12% and speeds up training time by 3. |