Papers by Yike Guo
Omni-RewardBench: Toward a Comprehensive Evaluation of Generative Reward Models Across Modalities (2026.acl-long)
Copied to clipboard
Chi-Min Chan, Yujin Zhou, Pengcheng Wen, Boqin Yin, Jiaming Ji, Juntao Dai, Wei Xue, Sirui Han, Yike Guo
| Challenge: | Existing evaluation benchmarks for ORMs are largely text-centric or limited to bimodal tasks . a new study examines the effectiveness of Omni-RewardBench for ORms across modalities . |
| Approach: | They propose a hybrid automatic-annotation and human-verification pipeline to construct high-quality evaluation data. |
| Outcome: | The proposed model is the first benchmark for comprehensive evaluation of ORMs across modalities. |
Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving (2025.emnlp-main)
Copied to clipboard
Chuxue Cao, Mengze Li, Juntao Dai, Jinluan Yang, Zijian Zhao, Shengyu Zhang, Weijie Shi, Chengzhong Liu, Sirui Han, Yike Guo
| Challenge: | Large language models (LLMs) have shown promising first-order logic (FOL) reasoning capabilities with applications in various areas, but their effectiveness in complex mathematical reasoning involving multi-step FOL deductions remains under-explored. |
| Approach: | They propose a self-adaptive solution that enhances the Diversity and REAsonability of LLMs’ generation strategies by introducing an Axiom-Driven Strategy Diversification mechanism and a Sub-Proposition Error Feedback to help LLM reflect on and correct their proofs. |
| Outcome: | The proposed model improves diversity and REAsonability of LLMs’ generation strategies by introducing an Axiom-Driven Strategy Diversification mechanism and a Sub-Proposition Error Feedback to help LLM reflect on and correct proofs. |
BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook (2026.acl-long)
Copied to clipboard
Hao Gu, Lujun Li, Hao Wang, Lei Wang, Zheyu Wang, Bei Liu, Jiacheng Liu, Qiyuan Zhu, Sirui Han, Yike Guo
| Challenge: | Recent sparsity-aware binarization approaches can achieve sub-1-bit compression, but they face performance degradation, mask-management overhead, and limited hardware compatibility. |
| Approach: | They propose a binary quantization framework that leverages binary pattern clustering and weight transformation to overcome performance degradation and mask-management overhead. |
| Outcome: | The proposed framework achieves state-of-the-art compression (1.11–0.7 bits) it maintains high performance with only a 3.1% accuracy drop in zero-shot benchmarks while delivering a 1.6 speedup over FP16. |
InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents (2026.findings-acl)
Copied to clipboard
Zhenghao Zhu, Yuanfeng Song, Xing Chen, Chengzhong Liu, Cui Yakun, Caleb Chen Cao, Sirui Han, Yike Guo
| Challenge: | Existing frameworks for data analysis and insight exploration are lacking in terms of benchmarks . existing frameworks suffer from format inconsistencies, poorly conceived objectives, and redundant insights. |
| Approach: | They propose a data-curation pipeline to construct a new dataset named InsightEval. |
| Outcome: | The proposed benchmarks highlight prevailing challenges in automated insight discovery and raise key findings to guide future research. |
SWAM: Adaptive Sliding Window and Memory-Augmented Attention Model for Rumor Detection (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for rumor detection on social media focus on static graphs, ignoring dynamic and incremental propagation . rumour detection on the social media platform is crucial to mitigating harmful effects of rumors. |
| Approach: | They propose a sliding window and memory-augmented attention model for rumor detection . they use a dynamic propagation graph and memory to capture the long-term dependency . |
| Outcome: | The proposed model is compared with the state-of-the-art models on two public datasets. |
Task-wrapped Continual Learning in Task-Oriented Dialogue Systems (2025.findings-naacl)
Copied to clipboard
| Challenge: | Continual learning is vital for task-oriented dialogue systems (ToDs), but its performance is limited by training separate adapters for each task, preventing global knowledge sharing. |
| Approach: | They propose a framework that employs task-wrapped Adapters to learn global and task-specific information through parameter sharing. |
| Outcome: | The proposed framework outperforms AdapterCL in 37 domains while using only 46% of the parameters. |
Learning While Staying Curious: Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models (2026.acl-long)
Copied to clipboard
Hao Wang, Hao Gu, Hongming Piao, Kaixiong Gong, Yuxiao Ye, Xiangyu Yue, Sirui Han, Yike Guo, Dapeng Wu
| Challenge: | Recent advances establish "SFT-then-RL" as the defacto paradigm for enhancing large reasoning mod- els on automatically verifiable tasks. |
| Approach: | They propose an entropy-preserving SFT method to enhance exploration capabilities through intrinsic curiosity. |
| Outcome: | The proposed method outperforms the vanilla method on reasoning tasks by 2.5 points . it also outperformed the vanilla SFT by 2.9 points on out-of-distribution tasks . |
Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs (2026.acl-long)
Copied to clipboard
Binxing Xu, Hao Gu, Lujun Li, Hao Wang, Bei Liu, Jiacheng Liu, Qiyuan Zhu, Xintong Yang, Chao Li, Sirui Han, Yike Guo
| Challenge: | Existing approaches to training LLMs at ultra-low precisions suffer from convergence instability and substantial training costs. |
| Approach: | They propose a progressive QAT framework with outlier channel splitting to address these issues . they use nested structure of integer quantization grids to enable a "train once, deploy any precision" paradigm . |
| Outcome: | The proposed framework outperforms baselines on both Llama2/3 and W2A16, with an 11 speedup over BF16. |
Sparse Adapter Fusion for Continual Learning in NLP (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing methods for learning continuously face challenges such as inefficient parameter reuse across tasks and catastrophic forgetting when tasks are dissimilar. |
| Approach: | They propose a Sparse Adapter Fusion Method which dynamically fuses old and new adapters to address these challenges. |
| Outcome: | The proposed method outperforms state-of-the-art methods while utilizing less than 60% of the parameters. |
VizoMem: A Visual-Textual Memory Framework for Efficient Long-Horizon Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing systems that use long-context modeling incur computational and memory overhead. |
| Approach: | They propose a visual memory framework that pre-rendered text into structured images and stored as visual notes for agentic systems. |
| Outcome: | The proposed system reduces token consumption while preserving effective long-term memory recall. |
SafeMT: Multi-turn Safety for Multimodal Language Models (2026.acl-long)
Copied to clipboard
Han Zhu, Juntao Dai, Jiaming Ji, Haoran Li, Chengkun Cai, Pengcheng Wen, Chi-Min Chan, Boyuan Chen, Yaodong Yang, Sirui Han, Yike Guo
| Challenge: | Multi-turn dialogues pose a greater risk than single prompts, but existing safety benchmarks do not account for this situation. |
| Approach: | They propose a benchmark that features dialogues of varying lengths generated from harmful queries accompanied by images. |
| Outcome: | The proposed model reduces multi-turn Attack Success Rate (ASR) compared to existing guard models. |
Improving Deep Embedded Clustering via Learning Cluster-level Representations (2022.coling-1)
Copied to clipboard
| Challenge: | Existing efforts to learn meaningful representations at the instance level are limited. |
| Approach: | They propose a deep embedded clustering model with cluster-level representation learning to jointly learn cluster and instance level representations. |
| Outcome: | The proposed model produces meaningful clusters on real-world short text datasets. |
Glance-or-Gaze: Incentivizing LMMs to Adaptively Focus Search via Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing search-augmented approaches rely on indiscriminate whole-image retrieval and lack deep iterative reflection, limiting their effectiveness on complex visual queries. |
| Approach: | They propose a fully autonomous framework that shifts from passive perception to active visual planning and introduces a Selective Gaze mechanism that dynamically chooses whether to glance at global context or gaze into high-value regions. |
| Outcome: | Experiments across six benchmarks demonstrate state-of-the-art performance. |
Boosting Policy and Process Reward Models with Monte Carlo Tree Search in Open-Domain QA (2025.findings-acl)
Copied to clipboard
Chi-Min Chan, Chunpu Xu, Junqi Zhu, Jiaming Ji, Donghai Hong, Pengcheng Wen, Chunyang Jiang, Zhen Ye, Yaodong Yang, Wei Xue, Sirui Han, Yike Guo
| Challenge: | Experimental results show that our approach can effectively improve the performance of both the policy model and the reward model. |
| Approach: | They propose to use Monte Carlo Tree Search for both policy model improvement and reward model improvement to bridge it to more subtle open-domain question answering. |
| Outcome: | The proposed approach surpasses existing methods for annotation and training data with fewer data points and achieves better performance in test-time scaling strategies. |
ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)
Copied to clipboard
Ruibin Yuan, Hanfeng Lin, Yi Wang, Zeyue Tian, Shangda Wu, Tianhao Shen, Ge Zhang, Yuhang Wu, Cong Liu, Ziya Zhou, Liumeng Xue, Ziyang Ma, Qin Liu, Tianyu Zheng, Yizhi Li, Yinghao Ma, Yiming Liang, Xiaowei Chi, Ruibo Liu, Zili Wang, Chenghua Lin, Qifeng Liu, Tao Jiang, Wenhao Huang, Wenhu Chen, Jie Fu, Emmanouil Benetos, Gus Xia, Roger Dannenberg, Wei Xue, Shiyin Kang, Yike Guo
| Challenge: | Despite LLMs' impressive capabilities in musical knowledge, music reasoning remains an unsolved task. |
| Approach: | They propose an open-source large language model (LLM) that integrates intrinsic musical abilities into LLaMA2 and GPT-3.5. |
| Outcome: | The proposed model can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers. |
Domain-Invariant Feature Distillation for Cross-Domain Sentiment Classification (D19-1)
Copied to clipboard
| Challenge: | Existing approaches to cross-domain sentiment classification focus on domain-invariant representations, but few focus on the domain-specific information. |
| Approach: | They propose to distill domain-invariant sentiment features with an orthogonal domain-dependent task . the orthogonalist task is built on the aspects varying widely in different domains . |
| Outcome: | The proposed method improves domain-invariant features and transfer performance on three public datasets. |
FGDGNN: Fine-Grained Dynamic Graph Neural Network for Rumor Detection on Social Media (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for detecting rumors on social media focus on coarse-grained temporal information and ignore fine-grain temporal dynamics. |
| Approach: | They propose a fine-grained dynamic graph neural network model which incorporates fine-grain temporal information into a unified framework for rumor detection. |
| Outcome: | The proposed model improves on three public real-world datasets. |
Benchmarking Fine-Grained Error Detection in Multimodal Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Multimodal Process Reward Models (MPRMs) have emerged as a pivotal framework for enhancing the reasoning capabilities of Multimodal Large Language Models. |
| Approach: | They propose a benchmark specifically designed to evaluate MPRMs’ proficiency in detecting erroneous reasoning steps across diverse error categories. |
| Outcome: | The proposed model achieves up to 4.8% performance improvement through test-time scaling. |
ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing work on role-playing focuses on textual modalities, neglecting speech . et al., 2025) show that speech role-players can generate spontaneous responses with personalized traits based on the context. |
| Approach: | They propose a framework that allows models to deliver spontaneous responses with personalized verbal traits based on their role, scene, and spoken dialogue. |
| Outcome: | The proposed framework enhances speech role-playing by generating spontaneous responses with personalized traits based on their role, scene, and spoken dialogue. |
PyramidCodec: Hierarchical Codec for Long-form Music Generation in Audio Domain (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to generate long music are inefficient and lack of structured representation. |
| Approach: | They propose a hierarchical discrete representation of audio for long audio-domain music generation using residual vector quantization on different levels of features. |
| Outcome: | The proposed method achieves competitive performance in terms of reconstruction quality and token per second (TPS) the proposed method facilitates training a language model that can generate well-structured long-form music for up to 3 minutes. |
Automate Strategy Finding with LLM in Quant Investment (2025.findings-emnlp)
Copied to clipboard
Zhizhuo Kou, Holam Yu, Junyu Luo, Jingshu Peng, Xujia Li, Chengzhong Liu, Juntao Dai, Lei Chen, Sirui Han, Yike Guo
| Challenge: | Experimental results demonstrate robust performance of the strategy in Chinese & US market regimes compared to established benchmarks. |
| Approach: | They propose a framework leveraging Large Language Models within a risk-aware multi-agent system for automate strategy finding in quantitative finance. |
| Outcome: | The proposed framework outperforms all benchmarks in Chinese & US market regimes with 53.17% cumulative return on SSE50. |
QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training–Inference Mismatch (2026.findings-acl)
Copied to clipboard
Hao Gu, Hao Wang, Jiacheng Liu, Lujun Li, Qiyuan Zhu, Bei Liu, Binxing Xu, Lei Wang, Xintong Yang, Sida Lin, Sirui Han, Yike Guo
| Challenge: | Recent work has shown that reinforcement learning with simple rule-based reward functions (RLVR) can induce emergent reasoning behaviors and yield gains in challenging domains such as math problem solving. |
| Approach: | They propose a rollout-alignment-quantization-aware RL which aligns training-side forward with the quantized rollout to minimize mismatch. |
| Outcome: | The proposed approach outperforms quantized-rollout training by +5.5 on Qwen3-30B-A3B MoE for math problems while maintaining low-bit throughput. |
LegalReasoner: Step-wised Verification-Correction for Legal Judgment Reasoning (2025.acl-long)
Copied to clipboard
Weijie Shi, Han Zhu, Jiaming Ji, Mengze Li, Jipeng Zhang, Ruiyuan Zhang, Jia Zhu, Jiajie Xu, Sirui Han, Yike Guo
| Challenge: | Existing legal judgment prediction methods struggle with logical errors when conducting complex legal reasoning. |
| Approach: | They propose a method which enhances LJP reliability through step-wise verification and correction of the reasoning process. |
| Outcome: | The proposed model significantly improves concordance with court decisions from 72.37 to 80.27 on LLAMA-3.1-70B. |
PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference (2025.acl-long)
Copied to clipboard
Jiaming Ji, Donghai Hong, Borong Zhang, Boyuan Chen, Josef Dai, Boren Zheng, Tianyi Alex Qiu, Jiayi Zhou, Kaile Wang, Boxun Li, Sirui Han, Yike Guo, Yaodong Yang
| Challenge: | Using large-scale annotation data, large language models can generate noise, errors and biases, leading to unexpected behaviours. |
| Approach: | They propose a dataset to promote safety alignment in large language models . they separate helpfulness and harmlessness annotations for question-answering pairs . |
| Outcome: | The proposed dataset provides 44.6k prompts and 265k question-answer pairs with safety meta-labels for 19 harm categories and three severity levels, with answers generated by Llama-family models. |
SafeLawBench: Towards Safe Alignment of Large Language Models (2025.findings-acl)
Copied to clipboard
Chuxue Cao, Han Zhu, Jiaming Ji, Qichao Sun, Zhenghao Zhu, Wu Yinyu, Josef Dai, Yaodong Yang, Sirui Han, Yike Guo
| Challenge: | Recent studies indicate that large language models (LLMs) may exhibit risks, including threats to the protection of private data and the generation of hallucinations. |
| Approach: | They propose to evaluate LLMs from a legal perspective using the SafeLawBench benchmark. |
| Outcome: | The proposed framework categorizes safety risks into three levels based on legal standards and includes 24,860 multi-choice questions and 1,106 open-domain question-answering tasks. |
When Slower Isn’t Truer: Inverse Scaling Law of Truthfulness in Multimodal Reasoning (2026.findings-acl)
Copied to clipboard
Sitong Fang, Wenjing Cao, Jiahao Li, Xuyao Wang, Chi-Min Chan, Sirui Han, Juntao Dai, Yike Guo, Yaodong Yang, Jiaming Ji
| Challenge: | a study of slow reasoning models for multimodal reasoning finds that they are more prone to fabricating plausible yet false details when confronted with incomplete or misleading visual inputs. |
| Approach: | They conduct the first systematic study of the inverse scaling law in slow-thinking paradigms for multimodal reasoning. |
| Outcome: | The findings suggest that slower reasoning models are more prone to fabricating false details . the study analyzed 5,000-sample hierarchical prompt dataset by 50 participants . |
Self-Supervised Detection of Contextual Synonyms in a Multi-Class Setting: Phenotype Annotation Use Case (2021.emnlp-main)
Copied to clipboard
Jingqing Zhang, Luis Bolanos Trujillo, Tong Li, Ashwani Tanwar, Guilherme Freire, Xian Yang, Julia Ive, Vibhor Gupta, Yike Guo
| Challenge: | Contextualised word embeddings are powerful tool to detect contextual synonyms, but most of the current SOTA methods are supervised and underexploit the potential of the context. |
| Approach: | They propose a self-supervised approach which detects contextual synonyms of concepts being trained on the data created by shallow matching. |
| Outcome: | The proposed approach outperforms the previous SOTA with gains of up to 4.5 and 4.0 absolute points after fine-tuning with as little as 20% of the labelled data. |
BayesKD: Bayesian Knowledge Distillation for Compact LLMs in Constrained Fine-tuning Scenarios (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have revolutionized various domains with their remarkable capabilities, but their massive parameter sizes pose significant challenges for fine-tuning and inference. |
| Approach: | They propose a Bayesian Knowledge Distillation framework for compact Large Language Models in resource-constrained fine-tuning scenarios that employs Logits Dual-Scaling, Knowledge Alignment Module, and Bayes Distillations Optimization. |
| Outcome: | The proposed framework outperforms baseline methods on various state-of-the-art LLMs, including LLaMA, Qwen2, Bloom, and Vicuna. |
Benchmarking Multi-National Value Alignment for Large Language Models (2025.findings-acl)
Copied to clipboard
Chengyi Ju, Weijie Shi, Chengzhong Liu, Jiaming Ji, Jipeng Zhang, Ruiyuan Zhang, Jiajie Xu, Yaodong Yang, Sirui Han, Yike Guo
| Challenge: | Existing studies on large language models focus on ethical reviews, failing to capture the diversity of national values. |
| Approach: | They propose a national value extraction pipeline to efficiently construct value assessment datasets and a model-based model with instruction tagging to process raw data sources. |
| Outcome: | The proposed benchmark evaluates the alignment of LLMs with the values of five major nations: China, the United States, the UK, France, and Germany. |
More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Despite various proposed data construction methods, their practical utility in real-world pipelines remains underexplored. |
| Approach: | They conduct a comprehensive analysis of open-source datasets and data synthesis techniques for mathematical reasoning under a unified pipeline designed to mirror training and deployment scenarios. |
| Outcome: | The proposed pipelines mirror training and deployment scenarios and are suitable for industrial applications. |
FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation (2025.acl-long)
Copied to clipboard
Junyu Luo, Zhizhuo Kou, Liming Yang, Xiao Luo, Jinsheng Huang, Zhiping Xiao, Jingshu Peng, Chengzhong Liu, Jiaming Ji, Xuanzhe Liu, Sirui Han, Ming Zhang, Yike Guo
| Challenge: | Multimodal Large Language Models (MLLMs) have experienced rapid development in recent years, but there is a notable lack of effective and specialized multimodal evaluation datasets in the financial domain. |
| Approach: | They introduce FinMME, a multimodal large language model with 11,000 financial research samples and 20 annotators. |
| Outcome: | The proposed model performs better than state-of-the-art models, highlighting its challenging nature. |
Integrating Semantic Knowledge to Tackle Zero-shot Text Classification (N19-1)
Copied to clipboard
| Challenge: | Existing approaches to classify text documents of emerging classes are ineffective because of insufficient or even unavailable training data. |
| Approach: | They propose a two-phase framework with data augmentation and feature augmentation to deal with unseen classes effectively using four kinds of semantic knowledge. |
| Outcome: | The proposed framework achieves the best overall accuracy compared with baselines and recent approaches in classifying real-world texts under the zero-shot scenario. |
Graceful Forgetting in Generative Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies show that pre-trained models do not provide all knowledge needed for fine-tuning tasks. |
| Approach: | They propose a framework to achieve graceful forgetting in generative language models by pre-training a model on large-scale correlating datasets. |
| Outcome: | The proposed framework improves the learning plasticity of the target task by selectively discarding irrelevant knowledge. |