Papers by Xinyu Liu
CE-RM: A Pointwise Generative Reward Model Optimized via Two-Stage Rollout and Unified Criteria (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have shown that rule-based evaluation methods are ineffective for open-ended natural language generation. |
| Approach: | They propose a pointwise generative reward model with a dedicated two-stage rollout method and unified query-based criteria that can be trained with 5.7K high-quality data. |
| Outcome: | The proposed model achieves superior performance on diverse reward model benchmarks, especially in Best-of-N scenarios, and delivers more effective improvements in downstream RL practice. |
AFT-Tab: Adversarial Fine-Tuning for Tabular Data Synthesis with Long Text Columns (2026.acl-long)
Copied to clipboard
| Challenge: | Existing tabular data synthesis methods fail to account for cross-modal heterogeneity of real-world tables, where structured continuous and discrete attributes coexist with unstructured long-text columns. |
| Approach: | They propose a framework that synergistically trains an LLM-based text generator and a deep-learning-based non-textual generator to quantify cross-modal semantic alignment. |
| Outcome: | The proposed framework outperforms state-of-the-art frameworks in fidelity, diversity, and task utility. |
Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot (2025.findings-emnlp)
Copied to clipboard
| Challenge: | In-Context Learning (ICL) is an essential emergent ability of Large Language Models (LLMs). |
| Approach: | They introduce CoT to exemplars of ICL to enhance the reasoning capability . however, it remains unclear whether CoT exemplar is still beneficial for recent, stronger models in such tasks. |
| Outcome: | The enhanced exemplars fail to improve the model’s reasoning performance, despite being constructed using answers from advanced models such as Qwen2.5-Max and DeepSeek-R1. |
Reinforced Efficient Reasoning via Semantically Diverse Exploration (2026.acl-long)
Copied to clipboard
Ziqi Zhao, Zhaochun Ren, Jiahong Zou, Liu Yang, Zhiwei Xu, Xuri Ge, Zhumin Chen, Xinyu Ma, Daiting Shi, Shuaiqiang Wang, Dawei Yin, Xin Xin
| Challenge: | Existing methods for reinforcement learning with verifiable rewards suffer from limited exploration diversity and inefficient reasoning. |
| Approach: | They propose a method that rewards concise and correct reasoning while penalizing unnecessarily long reasoning chains. |
| Outcome: | Extensive experiments on Qwen and Llama models validate the effectiveness and efficiency of ROSE. |
CoRanking: Collaborative Ranking with Small and Large Ranking Agents (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Listwise ranking based on Large Language Models (LLMs) has achieved state-of-the-art performance in Information Retrieval (IR) however, their effectiveness often depends on LLMs with massive parameter scales and computationally expensive sliding window processing, leading to substantial efficiency bottlenecks. |
| Approach: | They propose a Collaborative Ranking framework (CoRanking) for LLM-based listwise ranking based on large language models with massive parameter scales and computationally expensive sliding window processing. |
| Outcome: | The proposed framework reduces ranking latency by approximately 70% while improving effectiveness compared to the standalone large reranker. |
Task Oriented In-Domain Data Augmentation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for large language models suffer from two major issues: in-domain data are scarce compared with general domain-agnostic data. |
| Approach: | They propose a task-oriented in-domain data augmentation framework that uses in- domain data selection and task-orientated synthetic passage generation to adapt LLMs to two domains: advertisement and math. |
| Outcome: | The proposed framework improves LLM performance by 8% in the advertisement domain and 7.5% in the math domain. |
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. |
Towards Efficient NLP: A Standard Evaluation and A Strong Baseline (2022.naacl-main)
Copied to clipboard
Xiangyang Liu, Tianxiang Sun, Junliang He, Jiawen Wu, Lingling Wu, Xinyu Zhang, Hao Jiang, Zhao Cao, Xuanjing Huang, Xipeng Qiu
| Challenge: | Rather than pursuing the reachless SOTA accuracy, researchers are focusing on model efficiency and usability. |
| Approach: | They propose an evaluation and a public leaderboard for efficient NLP models that depicts the Pareto Frontier for various language understanding tasks. |
| Outcome: | The proposed model outperforms or performs on par with SOTA compressed and early exiting models. |
OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks focus on Mathematical Programming and Combinatorial Optimization, hindering comprehensive evaluation. |
| Approach: | They propose a benchmarking tool that compares 1,000 curated optimization problems across three difficulty levels. |
| Outcome: | The proposed model improves performance on hard problems while maintaining 27% accuracy. |
NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in reinforcement learning, such as DeepSeek R1-Zero, highlight the effectiveness of incentive training, but these methods rely on external verifiers, which limits their applicability to domains like mathematics and coding, where such verifier is readily available. |
| Approach: | They propose a general reinforcement learning framework that requires only standard supervised fine-tuning data with no need for an external verifier. |
| Outcome: | The proposed framework outperforms the model of the same size distilled from large reasoning models such as DeepSeek R1 671B by 7.7%. |
KnowDis: Knowledge Enhanced Data Augmentation for Event Causality Detection via Distant Supervision (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods of event causality detection use hand-labeled training data. |
| Approach: | They propose a framework for event causality detection that augments training data via distant supervision. |
| Outcome: | The proposed framework outperforms existing methods on two benchmark datasets . it outperformed previous methods by a large margin assisted with automatically labeled training data. |
Reasoning Like Program Executors (2022.emnlp-main)
Copied to clipboard
Xinyu Pi, Qian Liu, Bei Chen, Morteza Ziyadi, Zeqi Lin, Qiang Fu, Yan Gao, Jian-Guang Lou, Weizhu Chen
| Challenge: | Existing language models are inadequate in reasoning, according to studies . a new reasoning pre-training paradigm is based on pretraining language models with programs . |
| Approach: | They propose a reasoning pre-training paradigm that empowers language models to harvest reasoning knowledge possessed by program executors. |
| Outcome: | The proposed reasoning pre-training paradigm can boost models' reasoning skills . it can be instantiated by different kinds of program executors and run on a single database . |
Reward Mixology: Crafting Hybrid Signals for Reinforcement Learning Driven In-Context Learning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for in-context learning (ICL) performance rely on quality and ordering of demonstrations. |
| Approach: | They propose a method that models iterative demonstration selection as a Markov Decision Process and craft hybrid reward signals. |
| Outcome: | The proposed method combines outcome-based accuracy signals with process-oriented signals like stepwise influence and label entropy improvement. |
PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning (2025.acl-long)
Copied to clipboard
Xinyu Zhang, Yuxuan Dong, Yanrui Wu, Jiaxing Huang, Chengyou Jia, Basura Fernando, Mike Zheng Shou, Lingling Zhang, Jun Liu
| Challenge: | Large language models demonstrate remarkable capabilities across various domains, including mathematics and logic reasoning. |
| Approach: | They propose a physics-based reasoning benchmark that includes physics theorems and constraints and a Physics Solution Auto Scoring Framework to evaluate physics based reasoning in large language models. |
| Outcome: | The proposed framework enables models to achieve less than 60% on answer-level evaluation, with performance dropping from knowledge questions (75.11%) to hard problems (31.99%). |
Memory-Guided Hard Data Augmentation for Multimodal Named Entity Recognition (2026.findings-acl)
Copied to clipboard
Xinyu Liu, Kai fu, Yinghan Shi, Quanyou Chu, Ming Du, Hongya Wang, Xiaojun Meng, Jiansheng Wei, Yanghua Xiao, Bo Xu
| Challenge: | Existing methods for Named Entity Recognition (NER) ignore the internal state of the target model. |
| Approach: | They propose a framework to repair model-specific errors by using a model-based approach . they employ cross-validation to identify model- specific Hard Data and a memory tree to induce macro-level error patterns from micro-level failures. |
| Outcome: | The proposed framework yields significant performance gains on Twitter and other platforms. |
ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability (2026.acl-long)
Copied to clipboard
| Challenge: | Existing rerankers perform poorly in complex ranking scenarios due to the scarcity of reasoning-intensive training data. |
| Approach: | They propose an automated reasoning-intensive training framework which generates high-quality training labels from training queries and passages. |
| Outcome: | The proposed model outperforms baselines significantly and achieves much lower latency than the pointwise reranker. |
HierGR: Hierarchical Semantic Representation Enhancement for Generative Retrieval in Food Delivery Search (2025.acl-industry)
Copied to clipboard
Fuwei Zhang, Xiaoyu Liu, Xinyu Jia, Yingfei Zhang, Zenghua Xia, Fei Jiang, Fuzhen Zhuang, Wei Lin, Zhao Zhang
| Challenge: | Generative retrieval (GR) is an emerging search paradigm for food delivery search. |
| Approach: | They propose a method that harnesses the advanced query understanding capabilities of large language models to enhance the retrieval of results for complex and long-tail queries in food delivery search scenarios. |
| Outcome: | The proposed method increases the number of online orders by 0.68% for complex search intents. |
AutoConv: Automatically Generating Information-seeking Conversations with Large Language Models (2023.acl-short)
Copied to clipboard
Siheng Li, Cheng Yang, Yichun Yin, Xinyu Zhu, Zesen Cheng, Lifeng Shang, Xin Jiang, Qun Liu, Yujiu Yang
| Challenge: | Existing research on information-seeking conversations is stymied by the lack of training data. |
| Approach: | They propose to use autoconv for synthetic conversation generation to capture the characteristics of the information-seeking process and fine tune an LLM with a few human conversations to generate synthetic conversations with high quality. |
| Outcome: | The proposed model improves on two commonly-used datasets and alleviates the dependence on human annotation. |
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. |
TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making (2025.emnlp-main)
Copied to clipboard
Kechen Jiao, Zhirui Fang, Jiahao Liu, Bei Li, Qifan Wang, Xinyu Liu, Junhao Ruan, Zhongjian Qiao, Yifan Zhu, Yaxin Xu, Jingang Wang, Xiu Li
| Challenge: | Existing post-SFT methods for embodied AI are constrained by sparse rewards and action-only optimization, resulting in low sample efficiency, poor consistency, and model degradation. |
| Approach: | They propose to integrate Thought-Centric Preference Optimization (TCPO) into embodied decision-making by transforming sparse reward signals into richer step sample pairs. |
| Outcome: | The proposed approach achieves an average success rate of 26.67% in the ALFWorld environment, and a 6% improvement over RL4VLM. |
Multi-Hop Knowledge Editing via Critic-Guided Multi-Agent Reasoning (2026.findings-acl)
Copied to clipboard
Xudong Li, Yuhang Tian, Dandan Song, Zhijing Wu, Shuhao Zhang, Jun Yang, Yongyu Huo, Changzhi Zhou, Xinyu Zhang, Chenhao Li, Huipeng Ma, Luan Zhang, Yan Xu, Qian Liu
| Challenge: | Existing knowledge editing methods rely on unidirectional, feed-forward pipelines . a minor retrieval error or logical mismatch at an early hop can become a silent failure . |
| Approach: | They propose a framework for closed-loop post-edit reasoning that uses a Critic agent to verify coherence and step-wise correctness. |
| Outcome: | Experiments on MQuAKE-2002 and MQuADE-hard show that CARE effectively mitigates error propagation . a minor retrieval error or logical mismatch at an early hop can become a silent failure . |
TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on large language models (LLMs) focus on basic plan validity, but neglect critical aspects such as route efficiency, POI appeal, and real-time adaptability. |
| Approach: | They propose a benchmark for retrieval-augmented, spatiotemporal-aware travel planning that integrates retrieved trajectories with LLMs’ intrinsic reasoning. |
| Outcome: | The proposed framework improves spatial efficiency and POI rationality while challenging universality and robustness due to conflicting references and noisy data. |
CDT: A Comprehensive Capability Framework for Large Language Models Across Cognition, Domain, and Task (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing benchmarks focus on isolated abilities, lacking a holistic framework for assessing LLM capabilities. |
| Approach: | They propose a Cognition-Domain-Task framework which measures a model’s capabilities across three dimensions. |
| Outcome: | The proposed framework improves performance on dataset evaluation and data selection, while achieving higher scores on general and specific benchmarks. |
PersLEARN: Research Training through the Lens of Perspective Cultivation (2023.acl-demo)
Copied to clipboard
Yu-Zhe Shi, Shiqian Li, Xinyi Niu, Qiao Xu, Jiawen Liu, Yifan Xu, Shiyu Gu, Bingru He, Xinyang Li, Xinyu Zhao, Zijian Zhao, Yidong Lyu, Zhen Li, Sijia Liu, Lin Qiu, Jinhao Ji, Lecheng Ruan, Yuxi Ma, Wenjuan Han, Yixin Zhu
| Challenge: | PersLEARN is a tool designed to facilitate the cultivation of scientific perspectives . junior researchers struggle to identify the perspectives reflected in the literature and struggle to develop their own viewpoints. |
| Approach: | They propose a tool to facilitate the cultivation of scientific perspectives by interacting with a prompt-based model and allowing students to develop their own perspectives explicitly. |
| Outcome: | The proposed tool outperforms baseline approaches across multiple domains of literature from different perspectives. |
Glyph: Scaling Context Windows via Visual-Text Compression (2026.acl-long)
Copied to clipboard
Jiale Cheng, Yusen Liu, Xinyu Zhang, Yulin Fei, Wenyi Hong, Ruiliang Lyu, Weihan Wang, Zhe Su, Xiaotao Gu, Xiao Liu, Yushi Bai, Jie Tang, Hongning Wang, Minlie Huang
| Challenge: | Large language models (LLMs) traditionally represent text as sequences of discrete tokens . a long-context scaling problem requires processing more tokens more efficiently . |
| Approach: | They propose a framework that renders long texts into compact visual pages and processes them with a vision-language model. |
| Outcome: | The proposed framework renders long texts into compact visual pages and processes them with a vision-language model. |
Diagram-Driven Course Questions Generation (2025.emnlp-main)
Copied to clipboard
Xinyu Zhang, Lingling Zhang, Yanrui Wu, Muye Huang, Wenjun Wu, Bo Li, Shaowei Wang, Basura Fernando, Jun Liu
| Challenge: | Visual Question Generation (VQG) research focuses on natural images while neglecting diagrams, a critical component of educational materials. |
| Approach: | They propose a diagram-driven course questions generation task to generate diagram-relevant questions for specific courses. |
| Outcome: | The proposed framework outperforms existing models on DiagramQG while maintaining strong generalizability across natural image datasets. |
Agentic-R: Learning to Retrieve for Agentic Search (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing retrievers for single-turn retrieval-augmented generation (RAG) rely on similarity-based retrievers, but similar passages are not always useful for final answer generation. |
| Approach: | They propose a retrieval-augmented-generation retriever that integrates reasoning with retrieval . they use local query-passage relevance and global answer correctness to measure passage utility . |
| Outcome: | The proposed retriever outperforms existing retrievers on QA benchmarks on seven single-hop and multi-hop searches. |
MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning (2026.acl-long)
Copied to clipboard
Weikang Shi, Aldrich Yu, Rongyao Fang, Houxing Ren, Ke Wang, Aojun Zhou, Changyao Tian, Xinyu Fu, Yuxuan Hu, Zimu Lu, Linjiang Huang, Si Liu, Rui Liu, Hongsheng Li
| Challenge: | Existing approaches to visual chain-of-thought are limited by external tools or fail to generate high-fidelity diagrams. |
| Approach: | They propose a framework to enable large multimodal models with VCoT capabilities . they pre-train a model on a 15.2M-pair corpus and teach it how to leverage visual aids . |
| Outcome: | The proposed framework unlocks complex, human-like visual reasoning in large language models . it pre-trains the model on a 15.2M-pair corpus and fine-tunes it on MathCanvas-Instruct . |
PhysPRM: A Generative Process Reward Model with Fine-grained Diagnosis for Physics Problem Solving (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing Large Language Models (LLMs) struggle with physics problem solving due to difficulties in decoding implicit constraints and maintaining physical consistency. |
| Approach: | They propose a Generative PRM that treats evaluation as a generative task . it produces fine-grained diagnoses comprising critiques, final judgments, and specific error types . |
| Outcome: | The proposed model improves performance across seven benchmarks in Best-of-N and critique refinement strategies. |
Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to compress context information ignore holistic contextual dependencies. |
| Approach: | They propose a method that adjusts position encodings to minimize the distance between context tokens and special tokens. |
| Outcome: | Enhanced Position Layout (EPL) improves compression of context information in large language models. |
MIRACL: A Multilingual Retrieval Dataset Covering 18 Diverse Languages (2023.tacl-1)
Copied to clipboard
Xinyu Zhang, Nandan Thakur, Odunayo Ogundepo, Ehsan Kamalloo, David Alfonso-Hermelo, Xiaoguang Li, Qun Liu, Mehdi Rezagholizadeh, Jimmy Lin
| Challenge: | MIRACL is a multilingual dataset for ad hoc retrieval across 18 languages that collectively encompass over three billion native speakers around the world. |
| Approach: | They have gathered over 726k high-quality relevance judgments for 78k queries over Wikipedia in these languages, where all annotations have been performed by native speakers hired by their team. |
| Outcome: | MIRACL covers languages that are typologically close as well as distant from 10 language families and 13 sub-families, associated with varying amounts of publicly available resources. |
OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and tool use, but their ability to continuously refine solutions in response to dynamic environmental feedback remains underexplored. |
| Approach: | They propose a benchmark to evaluate self-improvement capabilities in large-scale search spaces by combining 20 machine learning tasks with 10 classic NP-hard problems. |
| Outcome: | The proposed framework emulates human-like cognitive adaptation and operates via a general perception–memory–reasoning loop, iteratively refining solutions based on environmental feedback. |
EduBench: A Comprehensive Benchmarking Dataset for Evaluating Large Language Models in Diverse Educational Scenarios (2026.acl-long)
Copied to clipboard
Bin Xu, Yu Bai, Huashan Sun, Yiguan Lin, Siming Liu, Xinyue Liang, Yaolin Li, Zhuangzhi Dong, Jingren Zhang, Yufan Deng, Xinyu Zou, Yang Gao, Heyan Huang
| Challenge: | Existing benchmarks that focus on knowledge-intensive tasks do not reflect diverse educational scenarios. |
| Approach: | They propose a benchmark that incorporates 9 major scenarios and 4,000 educational contexts. |
| Outcome: | The proposed model performs comparable to state-of-the-art large models on the test set. |
MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks (2026.acl-long)
Copied to clipboard
Junhao Ruan, Abudukeyumu Abudula, Bei Li, Yongjing Yin, Xinyu Liu, Kechen Jiao, Xin Chen, Jingang Wang, Xunliang Cai, Tong Xiao, JingBo Zhu
| Challenge: | Existing conversational retrieval benchmarks suffer from costly, sparse human annotation or rigid, unnatural automated heuristics. |
| Approach: | They propose a framework for auditing, synthesizing, and benchmarking conversational retrieval. |
| Outcome: | The proposed framework is based on three LLM-based auditors and a multi-agent system . it mimics production-style challenges (hard topic switching, verbosity) and offers superior discriminative power. |
IIET: Efficient Numerical Transformer via Implicit Iterative Euler Method (2025.emnlp-main)
Copied to clipboard
Xinyu Liu, Bei Li, Jiahao Liu, Junhao Ruan, Kechen Jiao, Hongyin Tang, Jingang Wang, Tong Xiao, JingBo Zhu
| Challenge: | High-order numerical methods enhance performance in tasks like NLP but introduce a performance-efficiency trade-off due to increased computational overhead. |
| Approach: | They propose an iterative implicit Euler Transformer which simplifies high-order numerical methods by iterating implicit Eule. |
| Outcome: | The proposed method improves accuracy and reduces inference overhead by 55% while retaining 99.4% of the original task accuracy. |
Sliding Windows Are Not the End: Exploring Full Ranking with Long-Context Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for listwise passage ranking use sliding window approach, which is inefficient as it requires repetitive and serialized processing. |
| Approach: | They propose a listwise label construction approach and importance-aware learning objective for full ranking. |
| Outcome: | The proposed method outperforms existing methods in listwise ranking tasks. |
FaStFact: Faster, Stronger Long-Form Factuality Evaluations in LLMs (2025.findings-emnlp)
Copied to clipboard
Yingjia Wan, Haochen Tan, Xiao Zhu, Xinyu Zhou, Zhiwei Li, Qingsong Lv, Changxuan Sun, Jiaqi Zeng, Yi Xu, Jianqiao Lu, Yinhong Liu, Zhijiang Guo
| Challenge: | Prior evaluation pipelines fail to evaluate factuality of long-form LLMs due to inefficiency and costly human assessment. |
| Approach: | They propose a fast and strong evaluation pipeline that can evaluate factuality of long-form LLMs . they propose 'faStFact' to reduce cost of web searching and inference calling . |
| Outcome: | The proposed evaluation pipeline achieves highest alignment with human evaluation and efficiency among existing baselines. |
Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference (2025.findings-naacl)
Copied to clipboard
| Challenge: | Evaluating and ranking the capabilities of different LLMs is crucial for understanding their performance and alignment with human preferences. |
| Approach: | They propose a system-level evaluation framework that ranks LLMs based on their alignment with human preferences. |
| Outcome: | The proposed framework aims to rank LLMs based on their performance and alignment with human preferences. |
Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Processing (2022.emnlp-main)
Copied to clipboard
Abbas Ghaddar, Yimeng Wu, Sunyam Bagga, Ahmad Rashid, Khalil Bibi, Mehdi Rezagholizadeh, Chao Xing, Yasheng Wang, Xinyu Duan, Zhefeng Wang, Baoxing Huai, Xin Jiang, Qun Liu, Phillippe Langlais
| Challenge: | Existing pre-trained language models are not well-explored and are not reproducible in the literature. |
| Approach: | They propose to improve existing Arabic language pre-trained language models using a more methodical approach. |
| Outcome: | The proposed models outperform existing models on ALUE, a leaderboard-powered benchmark for Arabic NLU and NLG tasks. |
ESPVR: Entity Spans Position Visual Regions for Multimodal Named Entity Recognition (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for acquiring local visual information are limited . existing methods for named entity recognition are redundant or insufficient . |
| Approach: | They propose an Entity Spans Position Visual Regions module to obtain visual regions corresponding to entities in the text. |
| Outcome: | The proposed method achieves the SOTA on Twitter-2017 and competitive results on Twitter 2015 . previous efforts have yielded promising results, but they still fall short in selecting visual information. |
Dialogue is Better Than Monologue: Instructing Meidcal LLMs via Strategic Conversations (2026.findings-eacl)
Copied to clipboard
Zijie Liu, Xinyu Zhao, Jie Peng, Jinhao Duan, Zhuangdi Zhu, Qingyu Chen, Kaidi Xu, Xia Hu, Tianlong Chen
| Challenge: | Existing tuning methods for medical AI models are monologue-based . existing benchmarks are based on licensing exams or research articles . |
| Approach: | They propose a benchmark to expose limitations of monologue-based tuning for medical AI models . they use a large dialogue dataset to capture stepwise diagnostic reasoning . |
| Outcome: | The proposed model outperforms monologue-tuned models on a medical question answering task and improves accuracy on standard medical QA benchmarks. |
LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for event causality identification (ECI) rely on annotated training data. |
| Approach: | They propose a method to augment training data for event causality identification by iteratively generating new examples and classifying event causalities in a dual learning framework. |
| Outcome: | The proposed method outperforms existing methods on EventStoryLine and Causal-TimeBank. |
Reflection in the Dark: Exposing and Escaping the Black Box in Reflective Prompt Optimization (2026.acl-srw)
Copied to clipboard
| Challenge: | Automatic prompt optimization (APO) is a powerful paradigm for improving LLM performance without manual prompt engineering. |
| Approach: | They propose a framework that decouples hypothesis generation from prompt rewriting . they propose VISTA framework that recovers accuracy to 87.57% on same defective seed . |
| Outcome: | The proposed framework outperforms baselines on GSM8K and AIME2025 on a defective seed. |
Generalized Supervised Attention for Text Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing supervised attention methods that use human knowledge to learn better alignments are costly or infeasible. |
| Approach: | They propose a generalized supervised attention method based on quasi alignments that are easier to obtain than ideal alignments. |
| Outcome: | The proposed framework improves generation performance and is robust against errors in attention supervision. |
UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity Mixture-of-Experts (2026.acl-long)
Copied to clipboard
Zhenyu Liu, Yunxin li, Xuanyu Zhang, Qixun Teng, Shenyuan Jiang, Xinyu Chen, Haoyuan Shi, Haolan Chen, Fanbo Meng, Mingjun Zhao, Yu Xu, Yancheng He, Baotian Hu, Haizhou Li, Min Zhang
| Challenge: | Recent advances in unified multimodal models indicate a clear trend towards comprehensive content generation. |
| Approach: | They propose a unified speech and music generation model built upon a novel framework . they propose specialized MoE architectures and curated training strategies to tackle data imbalances . |
| Outcome: | The proposed model achieves state-of-the-art performance on major speech and music generation benchmarks. |
P3: Prompts Promote Prompting (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in prompt optimization have shown effectiveness of using multiple components to optimize models . however, such unilateral approaches often yield suboptimal results due to interdependent nature of these components. |
| Approach: | They propose a self-improvement framework that optimizes both system and user prompts . they use offline optimized prompts to promote online prompt optimization . |
| Outcome: | The proposed framework improves performance on general and reasoning tasks. |
Debiasing In-Context Learning by Instructing LLMs How to Follow Demonstrations (2024.findings-acl)
Copied to clipboard
Lvxue Li, Jiaqi Chen, Xinyu Lu, Yaojie Lu, Hongyu Lin, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun
| Challenge: | In-context learning (ICL) has gained considerable attention due to its data efficiency and task adaptability. |
| Approach: | They propose to de-biase demonstration bias in in-context learning by focusing on semantic ambiguity induced by demonstrations and reducing the semantic hazard. |
| Outcome: | The proposed methods significantly improve performance on six datasets. |
Forgetting Curve: A Reliable Method for Evaluating Memorization Capability for Long-Context Models (2024.emnlp-main)
Copied to clipboard
Xinyu Liu, Runsong Zhao, Pengcheng Huang, Chunyang Xiao, Bei Li, Jingang Wang, Tong Xiao, JingBo Zhu
| Challenge: | Existing methods, tasks and benchmarks to measure model’s effective memory length are limited. |
| Approach: | They propose a method called forgetting curve to measure the memorization capability of long-context models. |
| Outcome: | The proposed method is robust to the tested corpus and experimental settings, and can be applied to any model size. |
Coarse-to-Fine: Hierarchical Multi-task Learning for Natural Language Understanding (2022.coling-1)
Copied to clipboard
Zhaoye Fei, Yu Tian, Yongkang Wu, Xinyu Zhang, Yutao Zhu, Zheng Liu, Jiawen Wu, Dejiang Kong, Ruofei Lai, Zhao Cao, Zhicheng Dou, Xipeng Qiu
| Challenge: | Existing methods to learn downstream tasks by stitches skill block lack rationality and interpretation. |
| Approach: | They propose a hierarchical framework with a coarse-to-fine paradigm for generalized text representations from the large-scale corpus. |
| Outcome: | The proposed model learns basic language properties from all tasks and boosts performance on relevant tasks. |
Showing Your Work Doesn’t Always Work (2020.acl-main)
Copied to clipboard
| Challenge: | countless experimental papers lack empirical rigor, disregarding necessities such as statistical significance tests and computational environments. |
| Approach: | They propose to report the expected validation effectiveness of the best-tuned model with respect to the computational budget. |
| Outcome: | The proposed model favors negative errors and yields poor bootstrapped confidence intervals, the authors argue . they find that the proposed model is biased and uses error-prone assumptions . |
The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse (2024.findings-acl)
Copied to clipboard
| Challenge: | Even a single edit can trigger model collapse, manifesting as significant performance degradation in various benchmark tasks. |
| Approach: | They propose to use perplexity as a surrogate metric to determine whether an edited model's performance is affected by a single edit. |
| Outcome: | The proposed method shows that even a single edit can cause model collapse, manifesting as significant performance degradation in various benchmark tasks. |
Multi-level Relevance Document Identifier Learning for Generative Retrieval (2025.acl-long)
Copied to clipboard
Fuwei Zhang, Xiaoyu Liu, Xinyu Jia, Yingfei Zhang, Shuai Zhang, Xiang Li, Fuzhen Zhuang, Wei Lin, Zhao Zhang
| Challenge: | Existing methods generate DocIDs based on textual content, which may result in weak semantic connections for similar documents due to variations in expression. |
| Approach: | They propose a new retrieval paradigm that generates unique document identifiers . they propose to use queries as a bridge to connect documents with varying relevance levels . |
| Outcome: | The proposed approach outperforms existing methods on multilingual e-commerce search datasets. |
Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks focus on correctness, overlooking optimality . large language models excel at math, coding, logic and puzzles . |
| Approach: | They propose a framework for training and evaluating Large Language Models on NP-hard optimization problems through quality-aware RLVR. |
| Outcome: | The proposed framework outperforms existing benchmarks on math, coding, logic and puzzles. |
3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset (2024.lrec-main)
Copied to clipboard
Xinyu Ma, Xuebo Liu, Derek F. Wong, Jun Rao, Bei Li, Liang Ding, Lidia S. Chao, Dacheng Tao, Min Zhang
| Challenge: | Existing studies have shown that visual information in existing MMT datasets is insufficient, causing models to disregard it and overestimate their capabilities. |
| Approach: | They propose to use 3AM to create an ambiguity-aware multimodal machine translation dataset. |
| Outcome: | The proposed dataset includes more ambiguity and a greater variety of captions and images than other MMT datasets. |
BrowseComp-Plus: A Fair and Disentangled Evaluation Benchmark for Deep Search Agents (2026.acl-long)
Copied to clipboard
Zijian Chen, Xueguang Ma, Shengyao Zhuang, Ping Nie, Kai Zou, Sahel Sharifymoghaddam, Andrew Liu, Joshua Green, Kshama Patel, Ruoxi Meng, Mingyi Su, Yanxi Li, Haoran Hong, Xinyu Shi, Xuye Liu, Hosna Oyarhoseini, Nandan Thakur, Crystina Zhang, Luyu Gao, Wenhu Chen, Jimmy Lin
| Challenge: | Existing benchmarks for deep search agents rely on blackbox web search APIs . dynamic and opaque web APIs hinder reproducibility and fair comparisons - authors . |
| Approach: | They propose a benchmark that employs a fixed corpus for controlled retrieval for deep search agents. |
| Outcome: | The new benchmark shows that agents that combine large language models with retrieval tools excel at complex, reasoning-intensive queries. |
Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation (2025.findings-acl)
Copied to clipboard
Qiyue Gao, Xinyu Pi, Kevin Liu, Junrong Chen, Ruolan Yang, Xinqi Huang, Xinyu Fang, Lu Sun, Gautham Kishore, Bo Ai, Stone Tao, Mengyang Liu, Jiaxi Yang, Chao-Jung Lai, Chuanyang Jin, Jiannan Xiang, Benhao Huang, Zeming Chen, David Danks, Hao Su, Tianmin Shu, Ziqiao Ma, Lianhui Qin, Zhiting Hu
| Challenge: | Recent studies have evaluated and shown limitations in specific capabilities such as visual understanding, but a systematic evaluation of VLMs’ fundamental WM abilities remains absent. |
| Approach: | They propose a framework that assesses perception and prediction to provide an atomic evaluation of VLMs as WMs. |
| Outcome: | The proposed framework assesses perception and prediction abilities on 15 latest VLMs and compares them to human-level models. |
MGPO: Thinking with Images via Multi-Turn Grounding-Based Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | State-of-the-art large multimodal models face challenges when processing high-resolution images, as these inputs are converted into enormous visual tokens, many of which are irrelevant to the downstream task. |
| Approach: | They propose a multi-turn grounding-based policy optimization framework that enables LMMs to iteratively focus on key visual regions by automatically cropping sub-images based on model-predicted grounding coordinates within a multiple-turn conversation framework. |
| Outcome: | The proposed framework improves on Qwen2.5-VL-7B with 21K samples and surpasses OpenAI’s o1 and GPT-4o models on the out-of-distribution (OOD) V* Bench. |
MPBoCo: Multimodal Prompt-based Boundary-enhanced Continual Framework for Joint Entity and Relation Extraction (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods struggle to balance real-time adaptability and computational efficiency in continual learning scenarios. |
| Approach: | They propose a Continual Multimodal Entity and Relation Joint Extraction task and a Multimodal Prompt-based Boundary-enhanced Continuum framework that stores task-specific knowledge via learnable multimodal prompts. |
| Outcome: | The proposed framework outperforms baseline methods in real-world scenarios by 5.5% and 7.2%. |
DGoT: Dynamic Graph of Thoughts for Scientific Abstract Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for generating abstracts involve collecting domain data and training corresponding models to complete the task of text summarization. |
| Approach: | They propose a method to train language models based on domain datasets and a Dynamic Graph of Thought (DGoT) which inherits the advantages of existing GoT prompt approach while reducing model reasoning cost. |
| Outcome: | The proposed method saves the cost of model training and improves reliability due to the hallucination problem of LLMs. |
Aligning Generative Language Models with Human Values (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for learning human values do not consider contextual and abstract nature of human values. |
| Approach: | They propose a reinforcement learning based method that embeds human values judgements into each step of language generation. |
| Outcome: | The proposed method improves on human values judgements and shows higher alignment performance. |
Knowledge-Enriched Event Causality Identification via Latent Structure Induction Networks (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for identifying causal relations of events are limited . Existing approaches cannot handle well the problem, especially in the condition of lacking training data. |
| Approach: | They propose a Latent Structure Induction Network to integrate external structural knowledge into a causality reasoning task. |
| Outcome: | The proposed approach outperforms existing state-of-the-art methods on two widely used datasets. |
Redundancy Principles for MLLMs Benchmarks (2025.acl-long)
Copied to clipboard
Zicheng Zhang, Xiangyu Zhao, Xinyu Fang, Chunyi Li, Xiaohong Liu, Xiongkuo Min, Haodong Duan, Kai Chen, Guangtao Zhai
| Challenge: | Rapid growth of Multi-modality Large Language Models has led to significant redundancy among benchmarks. |
| Approach: | They propose a framework to improve MLLM benchmark design by identifying redundancy at three levels: dimension, instance, and cross-benchmark redundancies. |
| Outcome: | The proposed framework streamlines evaluations and enhances reliability. |
Clustering Pseudo Language Family in Multilingual Translation Models with Fisher Information Matrix (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to cluster languages based on ancestral families can yield suboptimal results due to variations in the datasets employed during the model’s training phase. |
| Approach: | They propose a method that leverages the fisher information matrix to cluster language families anchored on the multilingual translation model's characteristics. |
| Outcome: | The proposed method improves performance over conventional language families in adapting a multilingual translation model to unfamiliar language pairs. |
UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing approaches to improve the performance of natural language processing models are over-parameterized and overfitted. |
| Approach: | They propose an approach to integrate dropout techniques into the training of Transformer models. |
| Outcome: | The proposed approach can achieve 1.5 BLEU improvement on IWSLT14 translation tasks and better accuracy for the classification even using strong pre-trained RoBERTa as backbone. |
AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code (2026.findings-acl)
Copied to clipboard
ShangZhan Li, Xinyu Yin, Xuanyu Jin, Ye He, Yuxin Zhou, Yuxuan Li, Xu Han, Wanxiang Che, Qi Shi, Ting Liu, Maosong Sun
| Challenge: | Current development practices face a dichotomy between automation and performance. |
| Approach: | They propose a framework to empower LLMs with the capability of automated explicit vectorization. |
| Outcome: | The proposed framework achieves state-of-the-art performance on the SSE and AVX subsets of SimdBench. |
Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering (2025.acl-long)
Copied to clipboard
| Challenge: | Existing work finds that long CoT reasoning can be efficiently elicited by tuning on only a few examples and can easily transfer to other tasks. |
| Approach: | They propose a representation engineering method to unleash the general long CoT reasoning capabilities of LLMs. |
| Outcome: | The proposed method is effective in in-domain and cross-domain scenarios. |
Dual-Cluster Memory Agent: Resolving Multi-Paradigm Ambiguity in Optimization Problem Solving (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) struggle with structural ambiguity in optimization problems, where a single problem admits multiple related but conflicting modeling paradigms, hindering effective solution generation. |
| Approach: | They propose to use memory to leverage historical solutions in a training-free manner to enhance performance by leveraging generalizable guidance knowledge. |
| Outcome: | The proposed agent achieves an average performance improvement of 11%-21% over previous agents. |
Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for event causality identification (ECI) rely on labeled data, but the scale of annotated datasets is limited. |
| Approach: | They propose a self-supervised framework to learn context-specific causal patterns from external causal statements and adopt a contrastive transfer strategy to incorporate the learned context- specific causal patterns into the target ECI model. |
| Outcome: | The proposed method significantly outperforms existing methods on EventSto-ryLine and Causal-TimeBank (+2.0 and +3.4 points on F1 value respectively). |
Improving Context Fidelity via Native Retrieval-Augmented Reasoning (2025.emnlp-main)
Copied to clipboard
Suyuchen Wang, Jinlin Wang, Xinyu Wang, Shiqi Li, Xiangru Tang, Sirui Hong, Xiao-Wen Chang, Chenglin Wu, Bang Liu
| Challenge: | Existing approaches to fidelity to contexts rely on expensive supervised fine-tuning to generate evidence post-answer or train models to perform web searches without improving utilization of the given context. |
| Approach: | They propose a native retrieval-augmented reasoning framework that integrates in-context evidence with the model’s own retrieval capabilities. |
| Outcome: | The proposed approach outperforms supervised fine-tuning, retrieval-augmented generation methods, and external retrieval solutions on multiple real-world and counterfactual QA benchmarks. |
Polymorphic Universal Transformer (2026.acl-long)
Copied to clipboard
Yilong Chen, Zitian Gao, Yihao Xiao, Jason Klein Liu, Xinyu Yang, Yifan Luo, Haoming Luo, Zhengmao Ye, Tingwen Liu, Ran Tao, Bryan Dai
| Challenge: | Compute Distribution Skew is a pathological phenomenon in ultra-deep recurrent models . it causes over-smoothing, representation rank collapse, and degraded reasoning performance. |
| Approach: | They propose a dynamic architecture that redefines recursive computation by decoupling parameter count from depth. |
| Outcome: | The proposed model significantly improves representation rank and reasoning robustness while reducing computation by 64.7%. |
MAIR: A Massive Benchmark for Evaluating Instructed Retrieval (2024.emnlp-main)
Copied to clipboard
Weiwei Sun, Zhengliang Shi, Wu Long, Lingyong Yan, Xinyu Ma, Yiding Liu, Min Cao, Dawei Yin, Zhaochun Ren
| Challenge: | Existing IR benchmarks focus on a limited scope of tasks, making them insufficient for evaluating the latest IR models. |
| Approach: | They propose a multi-task instruction-tuned IR benchmark that includes 126 distinct IR tasks across 6 domains. |
| Outcome: | The proposed model performs better on instruction-tuned models than non-instruction-tunned models on MAIR. |
Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering (2022.acl-long)
Copied to clipboard
Jiawei Zhou, Xiaoguang Li, Lifeng Shang, Lan Luo, Ke Zhan, Enrui Hu, Xinyu Zhang, Hao Jiang, Zhao Cao, Fan Yu, Xin Jiang, Qun Liu, Lei Chen
| Challenge: | Existing methods to train dense passage retrieval have a large data gap between upstream and downstream relevance. |
| Approach: | They propose a method to pre-train the dense retriever with the text relevance induced by hyperlinks within Web documents. |
| Outcome: | The proposed method outperforms existing methods under different scenarios and in the open-domain question answering domain. |