Papers by Rui Hou
Unlocking Decoding-time Controllability: Gradient-Free Multi-Objective Alignment with Contrastive Prompts (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for aligning large language models with human preferences are poor in extensibility and require significant retraining. |
| Approach: | They propose a multi-objective alignment approach that constructs an expert prompt and an adversarial prompt for each alignment objective to contrast at the decoding time. |
| Outcome: | The proposed approach is superior to existing methods in obtaining a well-distributed Pareto front among different alignment objectives. |
MART: Improving LLM Safety with Multi-round Automatic Red-Teaming (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing red-teaming methods for large language models often discover safety risks without addressing them. |
| Approach: | They propose a multi-round automatic red-teaming method that incorporates both adversarial prompt writing and safe response generation. |
| Outcome: | The proposed method significantly increases red-teaming scalability and the safety of the target LLM. |
SCE: Semantic Consistency Enhanced Reinforcement Learning for Multi-Hop Knowledge Graph Reasoning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to multihop reasoning fail to address the problem of spurious paths . existing approaches neglect the internal semantic consistency of the reward function . |
| Approach: | They propose a framework that incorporates semantic consistency into the reward function to guide multi-hop reasoning. |
| Outcome: | The proposed framework outperforms baseline methods and facilitates more interpretable reasoning paths. |
Residual Prompt Tuning: improving prompt tuning with residual reparameterization (2023.findings-acl)
Copied to clipboard
| Challenge: | Prompt tuning is one of the most parameter-efficient approaches for parameter-effective tuning of pre-trained language models. |
| Approach: | They propose to reparameterize soft prompt embeddings using a shallow network with a residual connection and use it to tune prompt embeds P. |
| Outcome: | The proposed method outperforms prompt tuning on SuperGLUE, T5-Base and BERT-Bass models and can reduce the prompt length by 10 times without hurting performance. |
Learning Easily Updated General Purpose Text Representations with Adaptable Task-Specific Prefix (2023.findings-emnlp)
Copied to clipboard
| Challenge: | a large pre-trained language model can cause computational burdens in inference time due to multiple forward passes. |
| Approach: | They propose a method to learn fixed text representations with source tasks . they learn a task-specific prefix for each source task independently and combine them . |
| Outcome: | The proposed method improves generalizability of representations with source tasks. |
AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis (2026.acl-demo)
Copied to clipboard
Massimiliano Pronesti, Angelo Miculescu, Mohsin Kapdi, Paul Flanagan, Oisín Redmond, Joao H Bettencourt-Silva, Gurdeep Singh Mannu, Spiros Denaxas, Rui Providencia, Anya Belz, Yufang Hou
| Challenge: | Existing systems that generate publication-ready forest plots from biomedical papers are fragmented and time-consuming. |
| Approach: | They propose a system that generates publication-ready forest plots directly from biomedical papers . autoforest automatically suggests ICO elements, extracts outcome data and performs statistical synthesis . authors demonstrate how the system can accelerate evidence synthesis and lower the barrier to conducting meta-analyses . |
| Outcome: | The proposed system accelerates evidence synthesis and lowers the barrier to meta-analyses. |
XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models (2023.emnlp-main)
Copied to clipboard
Davis Liang, Hila Gonen, Yuning Mao, Rui Hou, Naman Goyal, Marjan Ghazvininejad, Luke Zettlemoyer, Madian Khabsa
| Challenge: | Large multilingual models rely on a single vocabulary shared across 100+ languages . this vocabulary bottleneck limits the representational capabilities of multilingual model XLM-R . |
| Approach: | They propose a new approach for scaling to large multilingual vocabularies by de-emphasizing token sharing between languages with little lexical overlap and assigning vocabulary capacity to achieve sufficient coverage for each individual language. |
| Outcome: | The proposed model outperforms XLM-R on all language tasks and is particularly effective on low-resource tasks. |
A Study on Knowledge Distillation from Weak Teacher for Scaling Up Pre-trained Language Models (2023.findings-acl)
Copied to clipboard
| Challenge: | a study shows that DWT can be effective in the vision domain and natural language processing pre-training stages. |
| Approach: | They examine three key factors to optimize Distillation from Weak Teacher (DWT) DWT is a method of transferring knowledge from a weaker teacher model to a larger student model to improve its performance. |
| Outcome: | a new study examines three key factors to optimize DWT in NLP pre-training scenarios . the impact of teacher model quality and guidelines for adjusting the weighting value for DW T loss are examined . |
DrKGC: Dynamic Subgraph Retrieval-Augmented LLMs for Knowledge Graph Completion across General and Biomedical Domains (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Knowledge graph completion (KGC) aims to predict missing triples in knowledge graphs . current approaches encode graph context in textual form, which fails to exploit its potential . |
| Approach: | a new method is proposed to predict missing triples in knowledge graphs by leveraging existing triples and textual information. |
| Outcome: | The proposed model learns structural embeddings and logical rules within the KG and extracts a subgraph for each query guided by the learned rules. |
Multi-perspective Preference Alignment of LLMs for Programming-Community Question Answering (2025.coling-main)
Copied to clipboard
| Challenge: | Extensive experiments on a high-quality, real-world PCQA dataset validate its accuracy and preference. |
| Approach: | They propose a multi-perspective preference alignment for programming-community question answering to generate user-centric responses. |
| Outcome: | Experiments on a high-quality, real-world PCQA dataset validate the proposed model's accuracy and preference. |
Self-Generated Critiques Boost Reward Modeling for Language Models (2025.naacl-long)
Copied to clipboard
Yue Yu, Zhengxing Chen, Aston Zhang, Liang Tan, Chenguang Zhu, Richard Yuanzhe Pang, Yundi Qian, Xuewei Wang, Suchin Gururangan, Chao Zhang, Melanie Kambadur, Dhruv Mahajan, Rui Hou
| Challenge: | Existing reward models produce scalar scores and struggle to incorporate critiques in a natural language format. |
| Approach: | They propose a framework that predicts critiques and rewards using self-generated critiques without extra supervision. |
| Outcome: | The proposed framework improves reward modeling accuracy by 3.7%-7.3% compared to standard reward models and LLM judges. |
UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for parameter-efficient language model tuning (PELT) match the performance of fine-tuning with fewer trainable parameters. |
| Approach: | They propose a framework which integrates different PELT methods as submodules and learns to activate the ones that best suit the current data or task setup via gating mechanism. |
| Outcome: | The proposed framework outperforms fine-tuning methods on the GLUE benchmark and achieves 14% gains over the best individual PELT method. |
TreeRL: LLM Reinforcement Learning with On-Policy Tree Search (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for On-Policy LLM RL typically train a separate process reward model, which suffers from distribution mismatch and reward hacking. |
| Approach: | They propose a reinforcement learning framework that directly incorporates on-policy tree search for RL training. |
| Outcome: | Experiments on math and code reasoning benchmarks show that tree search achieves superior performance compared to traditional ChainRL. |
Effective Long-Context Scaling of Foundation Models (2024.naacl-long)
Copied to clipboard
Wenhan Xiong, Jingyu Liu, Igor Molybog, Hejia Zhang, Prajjwal Bhargava, Rui Hou, Louis Martin, Rashi Rungta, Karthik Abinav Sankararaman, Barlas Oguz, Madian Khabsa, Han Fang, Yashar Mehdad, Sharan Narang, Kshitiz Malik, Angela Fan, Shruti Bhosale, Sergey Edunov, Mike Lewis, Sinong Wang, Hao Ma
| Challenge: | Large language models (LLMs) are rapidly deployed and continue to evolve through scaling. |
| Approach: | They propose a method to train strong long-context LLMs that are capable of utilizing massive context windows of up to 32,000 tokens. |
| Outcome: | The proposed model can surpass gpt-3.5-turbo-16k's overall performance on long-context benchmarks with a cost-effective instruction tuning procedure that is free of expensive annotations. |
CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution (2026.acl-long)
Copied to clipboard
Xiangxi Zheng, Kuang He, Jiayi Hu, Ping Yu, Rui Yan, Yuan Yao, Peng Hou, Anxiang Zeng, Alex Jinpeng Wang
| Challenge: | Existing approaches to chart-to-code generation are constrained by data-centric limitations . authors present a new framework that redesigns both training and alignment data . |
| Approach: | They propose a data-centric framework that redesigns both training and alignment data for chart-to-code generation. |
| Outcome: | The proposed framework outperforms open-source baselines and is competitive with GPT-5. |
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. |
A Systematic Examination of Preference Learning through the Lens of Instruction-Following (2025.naacl-long)
Copied to clipboard
Joongwon Kim, Anirudh Goyal, Aston Zhang, Bo Xiong, Rui Hou, Melanie Kambadur, Dhruv Mahajan, Hannaneh Hajishirzi, Liang Tan
| Challenge: | a recent study has found that preference learning is a key tool for enhancing LLM training and alignment. |
| Approach: | They use a synthetic data generation pipeline to generate 48,000 unique instruction-following prompts with 23 verifiable constraints to obtain preference pairs. |
| Outcome: | The proposed pipeline generates 48,000 unique instruction-following prompts with 23 verifiable constraints that enable fine-grained and automated quality assessments of model responses. |
IDPG: An Instance-Dependent Prompt Generation Method (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing prompt tuning methods use a fixed prompt in each input instance during the model training stage. |
| Approach: | They propose a conditional prompt generation method to generate prompts for each input instance. |
| Outcome: | The proposed method outperforms other prompt tuning methods while tuning fewer parameters. |
RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training (2023.findings-emnlp)
Copied to clipboard
Jaehyung Kim, Yuning Mao, Rui Hou, Hanchao Yu, Davis Liang, Pascale Fung, Qifan Wang, Fuli Feng, Lifu Huang, Madian Khabsa
| Challenge: | Several perspectives of robustness for pre-trained language models have been studied independently, but lacking a unified consideration in multiple perspectives. |
| Approach: | They propose a technique to enhance the multi-perspective robustness of LMs by introducing adversarial perturbation while the model parameters are selectively updated upon their relative importance. |
| Outcome: | The proposed technique improves the robustness of LMs by incorporating four perspectives on model robustness. |
Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Study (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Audio-Language Models (LALMs) are increasingly being deployed in real-world applications, yet their robustness against malicious audio injection remains underexplored. |
| Approach: | They quantitatively assess their vulnerabilities and resilience using metrics: the Defense Success Rate, Context Robustness Score, and Judgment Robustic Index. |
| Outcome: | The proposed models demonstrate significant performance disparities across four attack scenarios. |
Co-training and Co-distillation for Quality Improvement and Compression of Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Knowledge Distillation (KD) compresses expensive pre-trained language models . however, most smaller models fail to surpass performance of larger model . |
| Approach: | They propose a framework that co-trains two models while mutually distilling knowledge to improve performance and inference speed together. |
| Outcome: | The proposed framework outperforms the original larger model by 1.66 on the GLUE benchmark. |