Large language models (LLMs) have demonstrated remarkable performances in various tasks. However, the performances of LLMs heavily depend on the input prompt. This has given rise to a number of recent works on prompt optimization. However, the previous works often require the availability of a numeric score to assess the quality of every prompt. Unfortunately, when a human user interacts with a black-box LLM, it is often infeasible and unreliable to attain such a score. Instead, it is usually significantly easier and more reliable to obtain preference feedback from a human user, i.e., showing the user the responses generated from a pair of prompts and asking the user which one is preferred. Therefore, in this paper, we study the problem of prompt optimization with human feedback (POHF), in which we aim to optimize the prompt for a black-box LLM using only human preference feedback. By drawing inspirations from dueling bandits, we design a theoretically principled strategy to select a pair of prompts to query for preference feedback in every iteration, and hence introduce our algorithm named automated POHF (APOHF). We apply our APOHF algorithm to a variety of tasks, including optimizing user instructions, prompt optimization for text-to-image generative models, and response optimization with human feedback (i.e., further refining the response using a variant of our APOHF). The results demonstrate that our APOHF can efficiently find a good prompt using a small number of preference feedback instances.

Recently, several multi-turn dialogue benchmarks have been proposed to evaluate the conversational abilities of large language models (LLMs). As LLMs are increasingly recognized as key technology for advancing intelligent education, owing to their ability to deeply understand instructional contexts and provide personalized guidance, constructing dedicated teacher-student dialogue benchmarks has become particularly important. To this end, we present EduDial, a comprehensive multi-turn teacher-student dialogue dataset. EduDial covers 345 core knowledge points and consists of 34,250 dialogue sessions from interactions between teacher and student agents. Its design is guided by Bloom’s taxonomy of educational objectives and incorporates ten questioning strategies—including situational questioning, zone of proximal development (ZPD) questioning, and metacognitive questioning—better capturing authentic classroom interactions. Furthermore, we design differentiated teaching strategies for students at different cognitive levels, providing more targeted guidance. Building on EduDial, we develop EduDial-LLM 32B via training and propose an 11-dimensional evaluation framework that systematically measures the teaching abilities of LLMs, encompassing overall teaching quality and content quality. Experiments on 17 mainstream LLMs reveal that most models struggle in student-centered teaching scenarios, whereas EduDial-LLM achieves significant gains, consistently outperforming all baselines across all metrics. Code is available at https://github.com/ECNU-RAIL/EduDial-EMNLP2026.

Large language models (LLMs) are shifting from answer providers to intelligent tutors in educational settings. However, current supervised fine-tuning methods only learn surface-level teaching patterns without dynamic adaptation. Recent reinforcement learning approaches address this, yet two key challenges remain. First, they evaluate teaching effectiveness solely based on whether students produce correct outputs, unable to distinguish whether students genuinely understand or echo teacher-provided answers. Second, they cannot perceive students’ evolving cognitive states through dialogue, failing to adapt teaching strategies accordingly. We propose Unidirectional Cognitive Optimization (UCO) to address these challenges. UCO employs a multi-turn interactive reinforcement learning paradigm with two synergistic reward functions: the Progress Reward captures cognitive advancement, evaluating students’ transition from confusion to comprehension, and the Scaffold Reward dynamically identifies each student’s Zone of Proximal Development (ZPD), encouraging the teacher to conduct productive teaching within this zone. We evaluate UCO against 11 baseline models on BigMath and MathTutorBench. Results demonstrate that UCO outperforms all equivalent-scale models and achieves performance comparable to leading closed-source models. Code is available at https://github.com/ECNU-RAIL/UCO-EMNLP2026.

Large language models (LLMs) have recently been employed as agents to solve sequential decision-making tasks such as Bayesian optimization and multi-armed bandits. These works usually adopt an LLM for sequential action selection by providing it with a fixed, manually designed meta-prompt. However, numerous previous works have found that the prompt has a significant impact on the performance of the LLM, which calls for a method to automatically optimize the meta-prompt for LLM-based agents. Unfortunately, the non-stationarity in the reward observations during LLM-based sequential decision making makes meta-prompt optimization highly challenging. To address this challenge, we draw inspirations from adversarial bandit algorithms, which are inherently capable of handling non-stationary reward observations. Building on this foundation, we propose our EXPonential-weight algorithm for prompt Optimization (EXPO) to automatically optimize the task description and meta-instruction in the meta-prompt for LLM-based agents. We also extend EXPO to additionally optimize the exemplars (i.e., history of interactions) in the meta-prompt to further enhance the performance, hence introducing our EXPO-ES algorithm. We use extensive experiments to show that our algorithms significantly improve the performance of LLM-based sequential decision making.

Large language models (LLMs) have advanced the development of personalized learning in education. However, their inherent generation mechanisms often produce homogeneous responses to identical prompts. This “one-size-fits-all” mechanism overlooks the substantial heterogeneity in students’ cognitive and psychological characteristics, thereby posing potential safety risks to vulnerable groups. Existing safety evaluations primarily rely on context-independent metrics such as factual accuracy, bias, or toxicity, which fail to capture the divergent harms that the same response might cause across different student attributes. To address this gap, we propose the concept of “Student-Tailored Personalized Safety” and construct CASTLE based on educational theories. This benchmark covers 15 educational safety risks and 14 student attributes, comprising 92,908 bilingual scenarios. We further design three evaluation metrics: Risk Sensitivity, measuring the model’s ability to detect risks; Emotional Empathy, evaluating the model’s capacity to recognize student states; and Student Alignment, assessing the match between model responses and student attributes. Experiments on 18 LLMs demonstrate that CASTLE poses a significant challenge: all models scored below an average safety score of 2.5 out of 5, indicating substantial deficiencies in personalized safety assurance. The code is available at https://github.com/ECNU-RAIL/CASTLE-EMNLP2026.

Large language models (LLMs) increasingly solve complex reasoning tasks via long chain-of-thought, but their forward-only autoregressive generation process is fragile; early token errors can cascade, which creates a clear need for self-reflection mechanisms. However, existing self-reflection either performs revisions over full drafts or learns self-correction via expensive training, both fundamentally reactive and inefficient. To address this, we propose Self-Reflective Generation at Test Time (SRGen), a lightweight test-time framework that reflects before generating at uncertain points. During token generation, SRGen utilizes dynamic entropy thresholding to identify high-uncertainty tokens. For each identified token, it trains a specific corrective vector, which fully exploits the already generated context for a self-reflective generation to correct the token probability distribution. By retrospectively analyzing the partial output, this self-reflection enables more trustworthy decisions, thereby significantly reducing the probability of errors at highly uncertain points. Evaluated on challenging mathematical reasoning benchmarks and a diverse set of LLMs, SRGen can significantly strengthen model reasoning. Moreover, our findings position SRGen as a plug-and-play method that integrates reflection into the generation process for reliable LLM reasoning, achieving consistent gains with bounded overhead and can be combined with other training-time (e.g., RLHF) and test-time (e.g., SLOT) techniques.

Large language models (LLMs) have been applied to sequential decision-making tasks like multi-armed bandits (MAB), where an LLM is tasked with selecting arms in each iteration. However, this direct arm selection approach is often suboptimal. We propose an alternative method combining classical MAB algorithms with LLMs. Specifically, we use a classical MAB framework and leverage the in-context learning capability of LLMs for reward prediction. First, we integrate the LLM-based predictor into Thompson sampling (TS) with a decaying temperature schedule to balance exploration and exploitation. We also incorporate the predictor into a regression oracle-based MAB algorithm with explicit exploration. Additionally, we extend our TS-based algorithm to dueling bandits, where only preference feedback between arm pairs is available, requiring significant algorithmic modifications. Our empirical evaluations on synthetic MAB tasks show that our algorithms outperform LLM-based direct arm selection. In experiments on real-world text datasets, we demonstrate that, in tasks where arms lack exploitable semantic meaning, our approach delivers significantly better performance than direct arm selection.

The impressive performances of Large Language Models (LLMs) and their immense potential for commercialization have given rise to serious concerns over the Intellectual Property (IP) of their training data. In particular, the synthetic texts generated by LLMs may infringe the IP of the data being used to train the LLMs. To this end, it is imperative to be able to perform source attribution by identifying the data provider who contributed to the generation of a synthetic text by an LLM. In this paper, we show that this problem can be tackled by watermarking, i.e., by enabling an LLM to generate synthetic texts with embedded watermarks that contain information about their source(s). We identify the key properties of such watermarking frameworks (e.g., source attribution accuracy, robustness against adversaries), and propose a source attribution framework that satisfies these key properties due to our algorithmic designs. Our framework enables an LLM to learn an accurate mapping from the generated texts to data providers, which sets the foundation for effective source attribution. Extensive empirical evaluations show that our framework achieves effective source attribution.

This position paper proposes a data-centric viewpoint of AI research, focusing on large language models (LLMs). We start by making a key observation that data is instrumental in the developmental (e.g., pretraining and fine-tuning) and inferential stages (e.g., in-context learning) of LLMs, and advocate that data-centric research should receive more attention from the community. We identify four specific scenarios centered around data, covering data-centric benchmarks and data curation, data attribution, knowledge transfer, and inference contextualization. In each scenario, we underscore the importance of data, highlight promising research directions, and articulate the potential impacts on the research community and, where applicable, the society as a whole. For instance, we advocate for a suite of data-centric benchmarks tailored to the scale and complexity of data for LLMs. These benchmarks can be used to develop new data curation methods and document research efforts and results, which can help promote openness and transparency in AI and LLM research.