Many real-world multi-agent or multi-task evaluation scenarios can be naturally modelled as normal-form games due to inherent strategic (adversarial, cooperative, and mixed motive) interactions. These strategic interactions may be agentic (e.g. In such a formulation, it is the strategies (actions, policies, agents, models, tasks, prompts, etc.) that are rated. However, the rating problem is complicated by redundancy and complexity of N-player strategic interactions. Repeated or similar strategies can distort ratings for those that counter or complement them. Previous work proposed "clone invariant" ratings to handle such redundancies, but this was limited to two-player zero-sum (i.e. This work introduces the first N-player generalsum clone invariant rating, called deviation ratings, based on coarse correlated equilibria. The rating is explored on several domains including LLMs evaluation. Data often captures relationships within a set (e.g., chess match outcomes) or between sets (e.g., film ratings by demographics). These sets can represent anything including human players, machine learning models, tasks, or features. The interaction data, often scalar (win rates, scores, or other metrics), may be symmetric, asymmetric or arbitrary. These interactions can be strategic, either in an agentic sense (e.g., players aiming to win) or due to inherent trade-offs (e.g., cost vs quality). This can lead to a game-theoretic interpretation: sets as players, elements as strategies, and interaction statistics as payoffs. This framing is common in analyzing strategic interactions between entities like Premier League teams, chess players (Sanjaya et al., 2022), reinforcement learning agents and tasks (Balduzzi et al., 2018), or even language models (Chiang et al., 2024). More generally, the idea of formulating real-world interactions as normal-form games, empirical game-theoretic analysis (Wellman, 2006), is well explored.

Transformer-based foundation models have achieved unprecedented success with a gigantic amount of parameters and computational resources. Yet, the core building blocks of these models, the Transformer layers, and how they are arranged and configured are primarily engineered from the bottom up and driven by heuristics. For advancing next-generation architectures, it demands exploring a prototypical model that is amenable to high interpretability and of practical competence. To this end, we take a step from the top-down view and design neural networks from an energy minimization perspective. Specifically, to promote isotropic token distribution on the sphere, we formulate a modified Hopfield energy function on the subspace-embedded hypersphere, based on which Transformer layers with symmetric structures are designed as the iterative optimization for the energy function. By integrating layers with the same parameters, we propose \textit{Hyper-Spherical Energy Transformer} (Hyper-SET), an alternative to the vanilla Transformer with recurrent depth. This design inherently provides greater interpretability and allows for scaling to deeper layers without a significant increase in the number of parameters. We also empirically demonstrate that Hyper-SET achieves comparable or even superior performance on both synthetic and real-world tasks, such as solving Sudoku and masked image modeling, while utilizing fewer parameters.

Large Language Models (LLMs) are widely applied in decision making, but their deployment is threatened by jailbreak attacks, where adversarial users manipulate model behavior to bypass safety measures. Existing defense mechanisms, such as safety fine-tuning and model editing, either require extensive parameter modifications or lack precision, leading to performance degradation on general tasks, which is unsuitable to post-deployment safety alignment. To address these challenges, we propose DELMAN (Dynamic Editing for LLMs JAilbreak DefeNse), a novel approach leveraging direct model editing for precise, dynamic protection against jailbreak attacks. DELMAN directly updates a minimal set of relevant parameters to neutralize harmful behaviors while preserving the model's utility. To avoid triggering a safe response in benign context, we incorporate KL-divergence regularization to ensure the updated model remains consistent with the original model when processing benign queries. Experimental results demonstrate that DELMAN outperforms baseline methods in mitigating jailbreak attacks while preserving the model's utility, and adapts seamlessly to new attack instances, providing a practical and efficient solution for post-deployment model protection.

We introduce a novel non-cooperative game to analyse opinion formation and resistance, incorporating principles from social psychology such as confirmation bias, resource constraints, and influence penalties. Our simulation features Large Language Model (LLM) agents competing to influence a population, with penalties imposed for generating messages that propagate or counter misinformation. This framework integrates resource optimisation into the agents' decision-making process. Our findings demonstrate that while higher confirmation bias strengthens opinion alignment within groups, it also exacerbates overall polarisation. Conversely, lower confirmation bias leads to fragmented opinions and limited shifts in individual beliefs. Investing heavily in a high-resource debunking strategy can initially align the population with the debunking agent, but risks rapid resource depletion and diminished long-term influence.

Large vision-language models (LVLMs) have shown great promise in medical applications, particularly in visual question answering (MedVQA) and diagnosis from medical images. However, existing datasets and models often fail to consider critical aspects of medical diagnostics, such as the integration of historical records and the analysis of disease progression over time. In this paper, we introduce MMXU (Multimodal and MultiX-ray Understanding), a novel dataset for MedVQA that focuses on identifying changes in specific regions between two patient visits. Unlike previous datasets that primarily address single-image questions, MMXU enables multi-image questions, incorporating both current and historical patient data. We demonstrate the limitations of current LVLMs in identifying disease progression on MMXU-\textit{test}, even those that perform well on traditional benchmarks. To address this, we propose a MedRecord-Augmented Generation (MAG) approach, incorporating both global and regional historical records. Our experiments show that integrating historical records significantly enhances diagnostic accuracy by at least 20\%, bridging the gap between current LVLMs and human expert performance. Additionally, we fine-tune models with MAG on MMXU-\textit{dev}, which demonstrates notable improvements. We hope this work could illuminate the avenue of advancing the use of LVLMs in medical diagnostics by emphasizing the importance of historical context in interpreting medical images. Our dataset is released at \href{https://github.com/linjiemu/MMXU}{https://github.com/linjiemu/MMXU}.

Rotary Position Embedding (RoPE) has shown strong performance in text-based Large Language Models (LLMs), but extending it to video remains a challenge due to the intricate spatiotemporal structure of video frames. Existing adaptations, such as RoPE-3D, attempt to encode spatial and temporal dimensions separately but suffer from two major limitations: positional bias in attention distribution and disruptions in video-text transitions. To overcome these issues, we propose Video Rotary Position Embedding (VRoPE), a novel positional encoding method tailored for Video-LLMs. Our approach restructures positional indices to preserve spatial coherence and ensure a smooth transition between video and text tokens. Additionally, we introduce a more balanced encoding strategy that mitigates attention biases, ensuring a more uniform distribution of spatial focus. Extensive experiments on Vicuna and Qwen2 across different model scales demonstrate that VRoPE consistently outperforms previous RoPE variants, achieving significant improvements in video understanding, temporal reasoning, and retrieval tasks. Code will be available at https://github.com/johncaged/VRoPE

Data augmentation is an essential technique in natural language processing (NLP) for enriching training datasets by generating diverse samples. This process is crucial for improving the robustness and generalization capabilities of NLP models. However, a significant challenge remains: \textit{Insufficient Attention to Sample Distribution Diversity}. Most existing methods focus on increasing the sample numbers while neglecting the sample distribution diversity, which can lead to model overfitting. In response, we explore data augmentation's impact on dataset diversity and propose a \textbf{\underline{D}}iversity-\textbf{\underline{o}}riented data \textbf{\underline{Aug}}mentation framework (\textbf{DoAug}). % \(\mathscr{DoAug}\) Specifically, we utilize a diversity-oriented fine-tuning approach to train an LLM as a diverse paraphraser, which is capable of augmenting textual datasets by generating diversified paraphrases. Then, we apply the LLM paraphraser to a selected coreset of highly informative samples and integrate the paraphrases with the original data to create a more diverse augmented dataset. Finally, we conduct extensive experiments on 12 real-world textual datasets. The results show that our fine-tuned LLM augmenter improves diversity while preserving label consistency, thereby enhancing the robustness and performance of downstream tasks. Specifically, it achieves an average performance gain of \(10.52\%\), surpassing the runner-up baseline with more than three percentage points.

Large language models (LLMs) exhibit impressive performance across diverse tasks but often struggle to accurately gauge their knowledge boundaries, leading to confident yet incorrect responses. This paper explores leveraging LLMs' internal states to enhance their perception of knowledge boundaries from efficiency and risk perspectives. We investigate whether LLMs can estimate their confidence using internal states before response generation, potentially saving computational resources. Our experiments on datasets like Natural Questions, HotpotQA, and MMLU reveal that LLMs demonstrate significant pre-generation perception, which is further refined post-generation, with perception gaps remaining stable across varying conditions. To mitigate risks in critical domains, we introduce Consistency-based Confidence Calibration ($C^3$), which assesses confidence consistency through question reformulation. $C^3$ significantly improves LLMs' ability to recognize their knowledge gaps, enhancing the unknown perception rate by 5.6\% on NQ and 4.9\% on HotpotQA. Our findings suggest that pre-generation confidence estimation can optimize efficiency, while $C^3$ effectively controls output risks, advancing the reliability of LLMs in practical applications.

Metacognitive education plays a crucial role in cultivating students' self-regulation and reflective thinking, providing essential support for those with learning difficulties through academic advising. Simulating students with insufficient learning capabilities using large language models offers a promising approach to refining pedagogical methods without ethical concerns. However, existing simulations often fail to authentically represent students' learning struggles and face challenges in evaluation due to the lack of reliable metrics and ethical constraints in data collection. To address these issues, we propose a pipeline for automatically generating and filtering high-quality simulated student agents. Our approach leverages a two-round automated scoring system validated by human experts and employs a score propagation module to obtain more consistent scores across the student graph. Experimental results demonstrate that our pipeline efficiently identifies high-quality student agents, and we discuss the traits that influence the simulation's effectiveness. By simulating students with varying degrees of learning difficulties, our work paves the way for broader applications in personalized learning and educational assessment.

Alignment tuning is crucial for ensuring large language models (LLMs) behave ethically and helpfully. Current alignment approaches require high-quality annotations and significant training resources. This paper proposes a low-cost, tuning-free method using in-context learning (ICL) to enhance LLM alignment. Through an analysis of high-quality ICL demos, we identified style as a key factor influencing LLM alignment capabilities and explicitly restyled ICL exemplars based on this stylistic framework. Additionally, we combined the restyled demos to achieve a balance between the two conflicting aspects of LLM alignment--factuality and safety. We packaged the restyled examples as prompts to trigger few-shot learning, improving LLM alignment. Compared to the best baseline approach, with an average score of 5.00 as the maximum, our method achieves a maximum 0.10 increase on the Alpaca task (from 4.50 to 4.60), a 0.22 enhancement on the Just-eval benchmark (from 4.34 to 4.56), and a maximum improvement of 0.32 (from 3.53 to 3.85) on the MT-Bench dataset. We release the code and data at https://github.com/AnonymousCode-ComputerScience/RIDE.