Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time

Large Language Models (LLMs) often struggle with complex reasoning scenarios. While preference optimization methods enhance reasoning performance through training, they often lack transparency in why one reasoning outcome is preferred over another. Verbal reflection techniques improve explainability but are limited in LLMs' critique and refinement capacity. To address these challenges, we introduce a contrastive reflection synthesis pipeline that enhances the accuracy and depth of LLM-generated reflections. We further propose a dual-model reasoning framework within a verbal reinforcement learning paradigm, decoupling inference-time self-reflection into specialized, trained models for reasoning critique and refinement. Extensive experiments show that our framework outperforms traditional preference optimization methods across all evaluation metrics. Our findings also show that "two heads are better than one", demonstrating that a collaborative Reasoner-Critic model achieves superior reasoning performance and transparency, compared to single-model approaches.

Scalable Model Merging with Progressive Layer-wise Distillation

Model merging offers an effective way to integrate the capabilities of multiple fine-tuned models. However, the performance degradation of the merged model remains a challenge, particularly when none or few data are available. This paper first highlights the necessity of domain-specific data for model merging by proving that data-agnostic algorithms can have arbitrarily bad worst-case performance. Building on this theoretical insight, we explore the relationship between model merging and distillation, introducing a novel few-shot merging algorithm, ProDistill (Progressive Layer-wise Distillation). Unlike common belief that layer wise training hurts performance, we show that layer-wise teacher-student distillation not only enhances the scalability but also improves model merging performance. We conduct extensive experiments to show that compared to existing few-shot merging methods, ProDistill achieves state-of-the-art performance, with up to 6.14% and 6.61% improvements in vision and NLU tasks. Furthermore, we extend the experiments to models with over 10B parameters, showcasing the exceptional scalability of ProDistill.

RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following

Role-playing is important for Large Language Models (LLMs) to follow diverse instructions while maintaining role identity and the role's pre-defined ability limits. Existing role-playing datasets mostly contribute to controlling role style and knowledge boundaries, but overlook role-playing in instruction-following scenarios. We introduce a fine-grained role-playing and instruction-following composite benchmark, named RoleMRC, including: (1) Multi-turn dialogues between ideal roles and humans, including free chats or discussions upon given passages; (2) Role-playing machine reading comprehension, involving response, refusal, and attempts according to passage answerability and role ability; (3) More complex scenarios with nested, multi-turn and prioritized instructions. The final RoleMRC features a 10.2k role profile meta-pool, 37.9k well-synthesized role-playing instructions, and 1.4k testing samples. We develop a pipeline to quantitatively evaluate the fine-grained role-playing and instruction-following capabilities of several mainstream LLMs, as well as models that are fine-tuned on our data. Moreover, cross-evaluation on external role-playing datasets confirms that models fine-tuned on RoleMRC enhances instruction-following without compromising general role-playing and reasoning capabilities. We also probe the neural-level activation maps of different capabilities over post-tuned LLMs. Access to our RoleMRC, RoleMRC-mix and Codes: https://github.com/LuJunru/RoleMRC.

An Automated Explainable Educational Assessment System Built on LLMs

In this demo, we present AERA Chat, an automated and explainable educational assessment system designed for interactive and visual evaluations of student responses. This system leverages large language models (LLMs) to generate automated marking and rationale explanations, addressing the challenge of limited explainability in automated educational assessment and the high costs associated with annotation. Our system allows users to input questions and student answers, providing educators and researchers with insights into assessment accuracy and the quality of LLM-assessed rationales. Additionally, it offers advanced visualization and robust evaluation tools, enhancing the usability for educational assessment and facilitating efficient rationale verification. Our demo video can be found at https://youtu.be/qUSjz-sxlBc.

Instance-Aware Graph Prompt Learning

Graph neural networks stand as the predominant technique for graph representation learning owing to their strong expressive power, yet the performance highly depends on the availability of high-quality labels in an end-to-end manner. Thus the pretraining and fine-tuning paradigm has been proposed to mitigate the label cost issue. Subsequently, the gap between the pretext tasks and downstream tasks has spurred the development of graph prompt learning which inserts a set of graph prompts into the original graph data with minimal parameters while preserving competitive performance. However, the current exploratory works are still limited since they all concentrate on learning fixed task-specific prompts which may not generalize well across the diverse instances that the task comprises. To tackle this challenge, we introduce Instance-Aware Graph Prompt Learning (IA-GPL) in this paper, aiming to generate distinct prompts tailored to different input instances. The process involves generating intermediate prompts for each instance using a lightweight architecture, quantizing these prompts through trainable codebook vectors, and employing the exponential moving average technique to ensure stable training. Extensive experiments conducted on multiple datasets and settings showcase the superior performance of IA-GPL compared to state-of-the-art baselines.

AERA Chat: An Interactive Platform for Automated Explainable Student Answer Assessment

Generating rationales that justify scoring decisions has emerged as a promising approach to enhance explainability in the development of automated scoring systems. However, the scarcity of publicly available rationale data and the high cost of annotation have resulted in existing methods typically relying on noisy rationales generated by large language models (LLMs). To address these challenges, we have developed AERA Chat, an interactive platform, to provide visually explained assessment of student answers and streamline the verification of rationales. Users can input questions and student answers to obtain automated, explainable assessment results from LLMs. The platform's innovative visualization features and robust evaluation tools make it useful for educators to assist their marking process, and for researchers to evaluate assessment performance and quality of rationales generated by different LLMs, or as a tool for efficient annotation. We evaluated three rationale generation approaches on our platform to demonstrate its capability.

ExDDI: Explaining Drug-Drug Interaction Predictions with Natural Language

Predicting unknown drug-drug interactions (DDIs) is crucial for improving medication safety. Previous efforts in DDI prediction have typically focused on binary classification or predicting DDI categories, with the absence of explanatory insights that could enhance trust in these predictions. In this work, we propose to generate natural language explanations for DDI predictions, enabling the model to reveal the underlying pharmacodynamics and pharmacokinetics mechanisms simultaneously as making the prediction. To do this, we have collected DDI explanations from DDInter and DrugBank and developed various models for extensive experiments and analysis. Our models can provide accurate explanations for unknown DDIs between known drugs. This paper contributes new tools to the field of DDI prediction and lays a solid foundation for further research on generating explanations for DDI predictions.

PropSAM: A Propagation-Based Model for Segmenting Any 3D Objects in Multi-Modal Medical Images

Volumetric segmentation is crucial for medical imaging but is often constrained by labor-intensive manual annotations and the need for scenario-specific model training. Furthermore, existing general segmentation models are inefficient due to their design and inferential approaches. Addressing this clinical demand, we introduce PropSAM, a propagation-based segmentation model that optimizes the use of 3D medical structure information. PropSAM integrates a CNN-based UNet for intra-slice processing with a Transformer-based module for inter-slice propagation, focusing on structural and semantic continuities to enhance segmentation across various modalities. Distinctively, PropSAM operates on a one-view prompt, such as a 2D bounding box or sketch mask, unlike conventional models that require two-view prompts. It has demonstrated superior performance, significantly improving the Dice Similarity Coefficient (DSC) across 44 medical datasets and various imaging modalities, outperforming models like MedSAM and SegVol with an average DSC improvement of 18.1%. PropSAM also maintains stable predictions despite prompt deviations and varying propagation configurations, confirmed by one-way ANOVA tests with P>0.5985 and P>0.6131, respectively. Moreover, PropSAM's efficient architecture enables faster inference speeds (Wilcoxon rank-sum test, P<0.001) and reduces user interaction time by 37.8% compared to two-view prompt models. Its ability to handle irregular and complex objects with robust performance further demonstrates its potential in clinical settings, facilitating more automated and reliable medical imaging analyses with minimal retraining.

Calibrating LLMs with Preference Optimization on Thought Trees for Generating Rationale in Science Question Scoring

Generating rationales that justify scoring decisions has been a promising way to facilitate explainability in automated scoring systems. However, existing methods do not match the accuracy of classifier-based methods. Plus, the generated rationales often contain hallucinated information. To address these issues, we propose a novel framework capable of generating more faithful rationales and, more importantly, matching performance with classifier-based black-box scoring systems. We first mimic the human assessment process by querying Large Language Models (LLMs) to generate a thought tree. We then summarise intermediate assessment decisions from each thought tree path for creating synthetic rationale data and rationale preference data. Finally, we utilise the generated synthetic data to calibrate LLMs through a two-step training process: supervised fine-tuning and preference optimization. Extensive experimental results demonstrate that our framework achieves a 38% assessment performance improvement in the QWK score compared to prior work while producing higher-quality rationales, as recognised by human evaluators and LLMs. Our work sheds light on the effectiveness of performing preference optimization using synthetic preference data obtained from thought tree paths.

Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence

Direct Preference Optimization (DPO) has emerged as a prominent algorithm for the direct and robust alignment of Large Language Models (LLMs) with human preferences, offering a more straightforward alternative to the complex Reinforcement Learning from Human Feedback (RLHF). Despite its promising efficacy, DPO faces a notable drawback: "verbosity", a common over-optimization phenomenon also observed in RLHF. While previous studies mainly attributed verbosity to biased labels within the data, we propose that the issue also stems from an inherent algorithmic length reliance in DPO. Specifically, we suggest that the discrepancy between sequence-level Kullback-Leibler (KL) divergences between chosen and rejected sequences, used in DPO, results in overestimated or underestimated rewards due to varying token lengths. Empirically, we utilize datasets with different label lengths to demonstrate the presence of biased rewards. We then introduce an effective downsampling approach, named SamPO, to eliminate potential length reliance. Our experimental evaluations, conducted across three LLMs of varying scales and a diverse array of conditional and open-ended benchmarks, highlight the efficacy of SamPO in mitigating verbosity, achieving improvements of 5% to 12% over DPO through debaised rewards. Our codes can be accessed at: https://github.com/LuJunru/SamPO/.