Linyi Yang

TIST Journal 2026 Journal Article

Introduction to the Special Issue on Evaluations of Large Language Models Part 2

• Jindong Wang
• Linyi Yang
• Sunayana Sitaram
• Qiang Yang
• Bhiksha Raj

ICLR Conference 2025 Conference Paper

An Empirical Analysis of Uncertainty in Large Language Model Evaluations

• Qiujie Xie
• Qingqiu Li
• Zhuohao Yu 0001
• Yuejie Zhang
• Yue Zhang 0004
• Linyi Yang

As LLM-as-a-Judge emerges as a new paradigm for assessing large language models (LLMs), concerns have been raised regarding the alignment, bias, and stability of LLM evaluators. While substantial work has focused on alignment and bias, little research has concentrated on the stability of LLM evaluators. In this paper, we conduct extensive experiments involving 9 widely used LLM evaluators across 2 different evaluation settings to investigate the uncertainty in model-based LLM evaluations. We pinpoint that LLM evaluators exhibit varying uncertainty based on model families and sizes. With careful comparative analyses, we find that employing special prompting strategies, whether during inference or post-training, can alleviate evaluation uncertainty to some extent. By utilizing uncertainty to enhance LLM's reliability and detection capability in Out-Of-Distribution (OOD) data, we further fine-tune an uncertainty-aware LLM evaluator named ConfiLM using a human-annotated fine-tuning set and assess ConfiLM's OOD evaluation ability on a manually designed test set sourced from the 2024 Olympics. Experimental results demonstrate that incorporating uncertainty as additional information during the fine-tuning phase can largely improve the model's evaluation performance in OOD scenarios. The code and data are released at: https://github.com/hasakiXie123/LLM-Evaluator-Uncertainty.

NeurIPS Conference 2025 Conference Paper

Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning

• Xiangning Yu
• Zhuohan Wang
• Linyi Yang
• Haoxuan Li
• Anjie Liu
• Xiao Xue
• Jun Wang
• Mengyue Yang

Chain-of-Thought (CoT) prompting plays an indispensable role in endowing large language models (LLMs) with complex reasoning capabilities. However, CoT currently faces two fundamental challenges: (1) Sufficiency, which ensures that the generated intermediate inference steps comprehensively cover and substantiate the final conclusion; and (2) Necessity, which identifies the inference steps that are truly indispensable for the soundness of the resulting answer. We propose a causal framework that characterizes CoT reasoning through the dual lenses of sufficiency and necessity. Incorporating causal Probability of Sufficiency and Necessity allows us not only to determine which steps are logically sufficient or necessary to the prediction outcome, but also to quantify their actual influence on the final reasoning outcome under different intervention scenarios, thereby enabling the automated addition of missing steps and the pruning of redundant ones. Extensive experimental results on various mathematical and commonsense reasoning benchmarks confirm substantial improvements in reasoning efficiency and reduced token usage without sacrificing accuracy. Our work provides a promising direction for improving LLM reasoning performance and cost-effectiveness. The code will be publicly available upon acceptance at: https: //anonymous. 4open. science/r/causalmath-1CEF.

ICLR Conference 2025 Conference Paper

CofCA: A STEP-WISE Counterfactual Multi-hop QA benchmark

• Jian Wu 0037
• Linyi Yang
• Zhen Wang 0020
• Manabu Okumura
• Yue Zhang 0004

While Large Language Models (LLMs) excel in question-answering (QA) tasks, their real reasoning abilities on multiple evidence retrieval and integration on Multi-hop QA tasks remain less explored. Firstly, LLMs sometimes generate answers that rely on internal memory rather than retrieving evidence and reasoning in the given context, which brings concerns about the evaluation quality of real reasoning abilities. Although previous counterfactual QA benchmarks can separate the internal memory of LLMs, they focus solely on final QA performance, which is insufficient for reporting LLMs' real reasoning abilities. Because LLMs are expected to engage in intricate reasoning processes that involve evidence retrieval and answering a series of sub-questions from given passages. Moreover, current factual Multi-hop QA (MHQA) benchmarks are annotated on open-source corpora such as Wikipedia, although useful for multi-step reasoning evaluation, they show limitations due to the potential data contamination in LLMs' pre-training stage. To address these issues, we introduce the Step-wise and Counterfactual benchmark (CofCA), a novel evaluation benchmark consisting of factual data and counterfactual data that reveals LLMs' real reasoning abilities on multi-step reasoning and reasoning chain evaluation. Our experimental results reveal a significant performance gap of several LLMs between Wikipedia-based factual data and counterfactual data, deeming data contamination issues in existing benchmarks. Moreover, we observe that LLMs usually bypass the correct reasoning chain, showing an inflated multi-step reasoning performance. We believe that our CofCA benchmark will enhance and facilitate the evaluations of trustworthy LLMs.

ICML Conference 2025 Conference Paper

Constrain Alignment with Sparse Autoencoders

• Qingyu Yin
• Chak Tou Leong
• Hongbo Zhang
• Minjun Zhu
• Hanqi Yan
• Qiang Zhang 0026
• Yulan He 0001
• Wenjie Li 0002

The alignment of large language models (LLMs) with human preferences remains a key challenge. While post-training techniques like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) have achieved notable success, they often experience computational inefficiencies and training instability. In this paper, we propose F eature-level constrained P reference O ptimization (FPO), a novel method designed to simplify the alignment process while ensuring stability. FPO leverages pre-trained Sparse Autoencoders (SAEs) and introduces feature-level constraints, allowing for efficient, sparsity-enforced alignment. Our approach enjoys efficiency by using sparse features activated in a well-trained sparse autoencoder and the quality of sequential KL divergence by using the feature-level offline reference. Experimental results on benchmark datasets demonstrate that FPO achieves an above 5% absolute improvement in win rate with much lower computational cost compared to state-of-the-art baselines, making it a promising solution for efficient and controllable LLM alignments.

ICLR Conference 2025 Conference Paper

CycleResearcher: Improving Automated Research via Automated Review

• Yixuan Weng
• Minjun Zhu
• Guangsheng Bao
• Hongbo Zhang
• Jindong Wang 0001
• Yue Zhang 0004
• Linyi Yang

The automation of scientific discovery has been a long-standing goal within the research community, driven by the potential to accelerate knowledge creation. While significant progress has been made using commercial large language models (LLMs) as research assistants or idea generators, the possibility of automating the entire research process with open-source LLMs remains largely unexplored. This paper explores the feasibility of using open-source post-trained LLMs as autonomous agents capable of performing the full cycle of automated research and review, from literature review and manuscript preparation to peer review and paper refinement. Our iterative preference training framework consists of CycleResearcher, which conducts research tasks, and CycleReviewer, which simulates the peer review process, providing iterative feedback via reinforcement learning. To train these models, we develop two new datasets, Review-5k and Research-14k, reflecting real-world machine learning research and peer review dynamics. Our results demonstrate that CycleReviewer achieves promising performance with a 26.89\% reduction in mean absolute error (MAE) compared to individual human reviewers in predicting paper scores, indicating the potential of LLMs to effectively assist expert-level research evaluation. In research, the papers generated by the CycleResearcher model achieved a score of 5.36 in simulated peer reviews, showing some competitiveness in terms of simulated review scores compared to the preprint level of 5.24 from human experts, while still having room for improvement compared to the accepted paper level of 5.69. This work represents a significant step toward fully automated scientific inquiry, providing ethical safeguards and exploring AI-driven research capabilities. The code, dataset and model weight are released at https://wengsyx.github.io/Researcher.

ICLR Conference 2025 Conference Paper

Human Simulacra: Benchmarking the Personification of Large Language Models

• Qiujie Xie
• Qiming Feng
• Tianqi Zhang
• Qingqiu Li
• Linyi Yang
• Yuejie Zhang
• Rui Feng 0001
• Liang He

Large Language Models (LLMs) are recognized as systems that closely mimic aspects of human intelligence. This capability has attracted the attention of the social science community, who see the potential in leveraging LLMs to replace human participants in experiments, thereby reducing research costs and complexity. In this paper, we introduce a benchmark for LLMs personification, including a strategy for constructing virtual characters' life stories from the ground up, a Multi-Agent Cognitive Mechanism capable of simulating human cognitive processes, and a psychology-guided evaluation method to assess human simulations from both self and observational perspectives. Experimental results demonstrate that our constructed simulacra can produce personified responses that align with their target characters. We hope this work will serve as a benchmark in the field of human simulation, paving the way for future research.

TIST Journal 2025 Journal Article

Introduction to the Special Issue on Evaluations of Large Language Models: Part 1

• Jindong Wang
• Linyi Yang
• Sunayana Sitaram
• Qiang Yang
• Bhiksha Raj

ICLR Conference 2025 Conference Paper

MMQA: Evaluating LLMs with Multi-Table Multi-Hop Complex Questions

• Jian Wu 0037
• Linyi Yang
• Dongyuan Li
• Yuliang Ji
• Manabu Okumura
• Yue Zhang 0004

While large language models (LLMs) have made strides in understanding tabular data, current tabular evaluation benchmarks, such as WikiTableQuestions and WikiSQL, are focus on single-table scenarios, which cannot necessarily reflect the complexity of real-world applications. To bridge this gap, we present a \textbf{M}ulti-table and Multi-hop Question Answering (MMQA) dataset to assess LLMs' understanding and reasoning capabilities in handling multi-table tasks. The MMQA dataset demands that models perform multiple inferences by drawing evidence from various tables, which are designed to be connected with each other and require models to identify and utilize relationships such as foreign and primary keys. Then, we introduce a comprehensive evaluation framework that tailors to assess LLMs' capabilities in several aspects including Multi-Table Retrieval, Text-to-SQL Generation, Multi-Table QA, Primary Key Selection, and Foreign Key Selection. Finally, we propose a novel multi-table retrieval method that achieves state-of-the-art (SOTA) performance on the MMQA dataset compared to several strong baselines. Our experiment results reveal that, compared with human performance, both open-source and commercial LLMs leave significant performance room for improvements in multi-table understanding and reasoning tasks. We believe that the MMQA benchmark will enhance and facilitate LLMs' multi-table capabilities in real-world scenarios.

ICLR Conference 2025 Conference Paper

Personality Alignment of Large Language Models

• Minjun Zhu
• Yixuan Weng
• Linyi Yang
• Yue Zhang 0004

Aligning large language models (LLMs) typically aim to reflect general human values and behaviors, but they often fail to capture the unique characteristics and preferences of individual users. To address this gap, we introduce the concept of Personality Alignment. This approach tailors LLMs' responses and decisions to match the specific preferences of individual users or closely related groups. Inspired by psychometrics, we created the Personality Alignment with Personality Inventories (PAPI) dataset, which includes data from over 320,000 real subjects across multiple personality assessments - including both the Big Five Personality Factors and Dark Triad traits. This comprehensive dataset enables quantitative evaluation of LLMs' alignment capabilities across both positive and potentially problematic personality dimensions. Recognizing the challenges of personality alignments—such as limited personal data, diverse preferences, and scalability requirements—we developed an activation intervention optimization method. This method enhances LLMs' ability to efficiently align with individual behavioral preferences using minimal data and computational resources. Remarkably, our method, PAS, achieves superior performance while requiring only 1/5 of the optimization time compared to DPO, offering practical value for personality alignment. Our work paves the way for future AI systems to make decisions and reason in truly personality ways, enhancing the relevance and meaning of AI interactions for each user and advancing human-centered artificial intelligence. The dataset and code are released at https://github.com/zhu-minjun/PAlign.

NeurIPS Conference 2025 Conference Paper

ReMA: Learning to Meta-Think for LLMs with Multi-agent Reinforcement Learning

• Ziyu Wan
• Yunxiang Li
• Xiaoyu Wen
• Yan Song
• Hanjing Wang
• Linyi Yang
• Mark Schmidt
• Jun Wang

Recent research on Reasoning of Large Language Models (LLMs) has sought to further enhance their performance by integrating meta-thinking—enabling models to monitor, evaluate, and control their reasoning processes for more adaptive and effective problem-solving. However, current single-agent work lacks a specialized design for acquiring meta-thinking, resulting in low efficacy. To address this challenge, we introduce Reinforced Meta-thinking Agents (ReMA), a novel framework that leverages Multi-Agent Reinforcement Learning (MARL) to elicit meta-thinking behaviors, encouraging LLMs to think about thinking. ReMA decouples the reasoning process into two hierarchical agents: a high-level meta-thinking agent responsible for generating strategic oversight and plans, and a low-level reasoning agent for detailed executions. Through iterative reinforcement learning with aligned objectives, these agents explore and learn collaboration, leading to improved generalization and robustness. Empirical results from single-turn experiments demonstrate that ReMA outperforms single-agent RL baselines on complex reasoning tasks, including competitive-level mathematical benchmarks and LLM-as-a-Judge benchmarks. Additionally, we further extend ReMA to multi-turn interaction settings, leveraging turn-level ratio and parameter sharing to improve efficiency. Comprehensive ablation studies further illustrate the evolving dynamics of each distinct agent, providing valuable insights into how the meta-thinking reasoning process enhances the reasoning capabilities of LLMs.

NeurIPS Conference 2025 Conference Paper

ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning

• Shulin Huang
• Linyi Yang
• Yan Song
• Shawn Chen
• Leyang Cui
• Ziyu Wan
• Qingcheng Zeng
• Ying Wen

Evaluating large language models (LLMs) poses significant challenges, particularly due to issues of data contamination and the leakage of correct answers. To address these challenges, we introduce ThinkBench, a novel evaluation framework designed to robustly evaluate the reasoning capability of LLMs. ThinkBench proposes a dynamic data generation method for constructing out-of-distribution (OOD) datasets and offers an OOD dataset that contains 2, 912 samples drawn from reasoning tasks. ThinkBench unifies the evaluation of reasoning models and non-reasoning models. We evaluate 16 LLMs and 4 PRMs under identical experimental conditions and show that most of the LLMs' performance are far from robust and they face a certain level of data leakage. By dynamically generating OOD datasets, ThinkBench effectively provides a reliable evaluation of LLMs and reduces data contamination impact. Our data and codes are available at https: //github. com/huangshulin123/ThinkBench.

TIST Journal 2024 Journal Article

A Survey on Evaluation of Large Language Models

• Yupeng Chang
• Xu Wang
• Jindong Wang
• Yuan Wu
• Linyi Yang
• Kaijie Zhu
• Hao Chen
• Xiaoyuan Yi

Large language models (LLMs) are gaining increasing popularity in both academia and industry, owing to their unprecedented performance in various applications. As LLMs continue to play a vital role in both research and daily use, their evaluation becomes increasingly critical, not only at the task level, but also at the society level for better understanding of their potential risks. Over the past years, significant efforts have been made to examine LLMs from various perspectives. This paper presents a comprehensive review of these evaluation methods for LLMs, focusing on three key dimensions: what to evaluate, where to evaluate, and how to evaluate. Firstly, we provide an overview from the perspective of evaluation tasks, encompassing general natural language processing tasks, reasoning, medical usage, ethics, education, natural and social sciences, agent applications, and other areas. Secondly, we answer the ‘where’ and ‘how’ questions by diving into the evaluation methods and benchmarks, which serve as crucial components in assessing the performance of LLMs. Then, we summarize the success and failure cases of LLMs in different tasks. Finally, we shed light on several future challenges that lie ahead in LLMs evaluation. Our aim is to offer invaluable insights to researchers in the realm of LLMs evaluation, thereby aiding the development of more proficient LLMs. Our key point is that evaluation should be treated as an essential discipline to better assist the development of LLMs. We consistently maintain the related open-source materials at: https://github.com/MLGroupJLU/LLM-eval-survey

NeurIPS Conference 2024 Conference Paper

CulturePark: Boosting Cross-cultural Understanding in Large Language Models

• Cheng Li
• Damien Teney
• Linyi Yang
• Qingsong Wen
• Xing Xie
• Jindong Wang

Cultural bias is pervasive in many large language models (LLMs), largely due to the deficiency of data representative of different cultures. Typically, cultural datasets and benchmarks are constructed either by extracting subsets of existing datasets or by aggregating from platforms such as Wikipedia and social media. However, these approaches are highly dependent on real-world data and human annotations, making them costly and difficult to scale. Inspired by cognitive theories on social communication, this paper introduces CulturePark, an LLM-powered multi-agent communication framework for cultural data collection. CulturePark simulates cross-cultural human communication with LLM-based agents playing roles in different cultures. It generates high-quality cross-cultural dialogues encapsulating human beliefs, norms, and customs. Using CulturePark, we generated 41, 000 cultural samples to fine-tune eight culture-specific LLMs. We evaluated these models across three downstream tasks: content moderation, cultural alignment, and cultural education. Results show that for content moderation, our GPT-3. 5-based models either match or outperform GPT-4 on $41$ datasets. Regarding cultural alignment, our models surpass GPT-4 on Hofstede's VSM 13 framework. Furthermore, for cultural education of human participants, our models demonstrate superior outcomes in both learning efficacy and user experience compared to GPT-4. CulturePark proves an important step in addressing cultural bias and advancing the democratization of AI, highlighting the critical role of culturally inclusive data in model training. Code is released at https: //github. com/Scarelette/CulturePark.

ICLR Conference 2024 Conference Paper

Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature

• Guangsheng Bao
• Yanbin Zhao
• Zhiyang Teng
• Linyi Yang
• Yue Zhang 0004

Large language models (LLMs) have shown the ability to produce fluent and cogent content, presenting both productivity opportunities and societal risks. To build trustworthy AI systems, it is imperative to distinguish between machine-generated and human-authored content. The leading zero-shot detector, DetectGPT, showcases commendable performance but is marred by its intensive computational costs. In this paper, we introduce the concept of **conditional probability curvature** to elucidate discrepancies in word choices between LLMs and humans within a given context. Utilizing this curvature as a foundational metric, we present **Fast-DetectGPT**, an optimized zero-shot detector, which substitutes DetectGPT's perturbation step with a more efficient sampling step. Our evaluations on various datasets, source models, and test conditions indicate that Fast-DetectGPT not only surpasses DetectGPT by a relative around 75\% in both the white-box and black-box settings but also accelerates the detection process by a factor of 340, as detailed in Table 1.

ICLR Conference 2024 Conference Paper

PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization

• Yidong Wang 0003
• Zhuohao Yu 0001
• Wenjin Yao
• Zhengran Zeng
• Linyi Yang
• Cunxiang Wang
• Hao Chen 0102
• Chaoya Jiang

Instruction tuning large language models (LLMs) remains a challenging task, owing to the complexity of hyperparameter selection and the difficulty involved in evaluating the tuned models. To determine the optimal hyperparameters, an automatic, robust, and reliable evaluation benchmark is essential. However, establishing such a benchmark is not a trivial task due to the challenges associated with evaluation accuracy and privacy protection. In response to these challenges, we introduce a judge large language model, named PandaLM, which is trained to distinguish the superior model given several LLMs. PandaLM's focus extends beyond just the objective correctness of responses, which is the main focus of traditional evaluation datasets. It addresses vital subjective factors such as relative conciseness, clarity, adherence to instructions, comprehensiveness, and formality. To ensure the reliability of PandaLM, we collect a diverse human-annotated test dataset, where all contexts are generated by humans and labels are aligned with human preferences. Our findings reveal that PandaLM-7B offers a performance comparable to both GPT-3.5 and GPT-4. Impressively, PandaLM-70B surpasses their performance. PandaLM enables the evaluation of LLM to be fairer but with less cost, evidenced by significant improvements achieved by models tuned through PandaLM compared to their counterparts trained with default Alpaca's hyperparameters. In addition, PandaLM does not depend on API-based evaluations, thus avoiding potential data leakage.

ICLR Conference 2024 Conference Paper

Supervised Knowledge Makes Large Language Models Better In-context Learners

• Linyi Yang
• Shuibai Zhang
• Zhuohao Yu 0001
• Guangsheng Bao
• Yidong Wang 0003
• Jindong Wang 0001
• Ruochen Xu
• Wei Ye 0004

Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The recent progress in large-scale generative models has further expanded their use in real-world language applications. However, the critical challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored. While previous in-context learning research has focused on enhancing models to adhere to users' specific instructions and quality expectations, and to avoid undesired outputs, little to no work has explored the use of task-specific fine-tuned Language Models (SLMs) to improve LLMs' in-context learning during the inference stage. Our primary contribution is the establishment of a simple yet effective framework that enhances the reliability of LLMs as it: 1) generalizes out-of-distribution data, 2) elucidates how LLMs benefit from discriminative models, and 3) minimizes hallucinations in generative tasks. Using our proposed plug-in method, enhanced versions of Llama 2 and ChatGPT surpass their original versions regarding generalizability and factuality. We offer a comprehensive suite of resources, including 16 curated datasets, prompts, model checkpoints, and LLM outputs across 9 distinct tasks. Our empirical analysis sheds light on the advantages of incorporating discriminative models into LLMs and highlights the potential of our methodology in fostering more reliable LLMs.

AAAI Conference 2022 Conference Paper

NumHTML: Numeric-Oriented Hierarchical Transformer Model for Multi-Task Financial Forecasting

• Linyi Yang
• Jiazheng Li
• Ruihai Dong
• Yue Zhang
• Barry Smyth

Financial forecasting has been an important and active area of machine learning research because of the challenges it presents and the potential rewards that even minor improvements in prediction accuracy or forecasting may entail. Traditionally, financial forecasting has heavily relied on quantitative indicators and metrics derived from structured financial statements. Earnings conference call data, including text and audio, is an important source of unstructured data that has been used for various prediction tasks using deep earning and related approaches. However, current deep learningbased methods are limited in the way that they deal with numeric data; numbers are typically treated as plain-text tokens without taking advantage of their underlying numeric structure. This paper describes a numeric-oriented hierarchical transformer model (NumHTML) to predict stock returns, and financial risk using multi-modal aligned earnings calls data by taking advantage of the different categories of numbers (monetary, temporal, percentages etc.) and their magnitude. We present the results of a comprehensive evaluation of NumHTML against several state-of-the-art baselines using a real-world publicly available dataset. The results indicate that NumHTML significantly outperforms the current stateof-the-art across a variety of evaluation metrics and that it has the potential to offer significant financial gains in a practical trading context.

NeurIPS Conference 2022 Conference Paper

USB: A Unified Semi-supervised Learning Benchmark for Classification

• Yidong Wang
• Hao Chen
• Yue Fan
• Wang Sun
• Ran Tao
• Wenxin Hou
• Renjie Wang
• Linyi Yang

Semi-supervised learning (SSL) improves model generalization by leveraging massive unlabeled data to augment limited labeled samples. However, currently, popular SSL evaluation protocols are often constrained to computer vision (CV) tasks. In addition, previous work typically trains deep neural networks from scratch, which is time-consuming and environmentally unfriendly. To address the above issues, we construct a Unified SSL Benchmark (USB) for classification by selecting 15 diverse, challenging, and comprehensive tasks from CV, natural language processing (NLP), and audio processing (Audio), on which we systematically evaluate the dominant SSL methods, and also open-source a modular and extensible codebase for fair evaluation of these SSL methods. We further provide the pre-trained versions of the state-of-the-art neural models for CV tasks to make the cost affordable for further tuning. USB enables the evaluation of a single SSL algorithm on more tasks from multiple domains but with less cost. Specifically, on a single NVIDIA V100, only 39 GPU days are required to evaluate FixMatch on 15 tasks in USB while 335 GPU days (279 GPU days on 4 CV datasets except for ImageNet) are needed on 5 CV tasks with TorchSSL.