Moral alignment has emerged as a widely adopted approach for regulating the behavior of pretrained language models (PLMs), typically through fine-tuning on curated datasets. Gender stereotype mitigation is a representational task within the broader application of moral alignment. However, this process often comes at the cost of degraded downstream task performance. Prior studies commonly aim to achieve a performance trade-off by encouraging PLMs to selectively forget only stereotypical knowledge through carefully designed fairness objective, while preserving their language modeling capability (overall forgetting). In this short paper, we investigate whether the performance trade-off can be achieved through the lens of forgetting and the fairness objective. Our analysis shows that the large datasets needed for satisfactory fairness highlight the limitations of current fairness objectives in achieving an effective trade-off: (1) downstream task performance is strongly correlated with overall forgetting; (2) selective forgetting reduces stereotypes, but overall forgetting increases. and (3) general solutions for alleviating forgetting are ineffective at reducing the overall forgetting and fail to improve downstream task performance.

A key feature differentiating artificial general intelligence (AGI) from traditional AI is that AGI can perform composite tasks that require a wide range of capabilities. Although embodied agents powered by multimodal large language models (MLLMs) offer rich perceptual and interactive capabilities, it remains largely unexplored whether they can solve composite tasks. In the current work, we designed a set of composite tasks inspired by common daily activities observed in early childhood development. Within a dynamic and simulated home environment, these tasks span three core domains: object understanding, spatial intelligence, and social activity. We evaluated 17 leading proprietary and open-source MLLMs on these tasks. The results consistently showed poor performance across all three domains, indicating a substantial gap between current capabilities and general intelligence requirements. Together, our tasks offer a preliminary framework for evaluating the general capabilities of embodied agents, marking an early but significant step toward the development of embodied MLLMs and their real-world deployment.

Imagine a world where clinical trials need far fewer patients to achieve the same statistical power, thanks to the knowledge encoded in large language models (LLMs). We present a novel framework for hierarchical Bayesian modeling of adverse events in multi-center clinical trials, leveraging LLM-informed prior distributions. Unlike data augmentation approaches that generate synthetic data points, our methodology directly obtains parametric priors from the model. Our approach systematically elicits informative priors for hyperparameters in hierarchical Bayesian models using a pre-trained LLM, enabling the incorporation of external clinical expertise directly into Bayesian safety modeling. Through comprehensive temperature sensitivity analysis and rigorous cross-validation on real-world clinical trial data, we demonstrate that LLM-derived priors consistently improve predictive performance compared to traditional meta-analytical approaches. This methodology paves the way for more efficient and expert-informed clinical trial design, enabling substantial reductions in the number of patients required to achieve robust safety assessment and with the potential to transform drug safety monitoring and regulatory decision making.

Quantization offers a practical solution to deploy LLMs in resource-constraint environments. However, its impact on internal representations remains understudied, raising questions about the reliability of quantized models. In this study, we employ a range of interpretability techniques to investigate how quantization affects model and neuron behavior. We analyze multiple LLMs under 4-bit and 8-bit quantization. Our findings reveal that the impact of quantization on model calibration is generally minor. Analysis of neuron activations indicates that the number of dead neurons, i.e., those with activation values close to 0 across the dataset, remains consistent regardless of quantization. In terms of neuron contribution to predictions, we observe that smaller full precision models exhibit fewer salient neurons, whereas larger models tend to have more, with the exception of Llama-2-7B. The effect of quantization on neuron redundancy varies across models. Overall, our findings suggest that effect of quantization may vary by model and tasks, however, we did not observe any drastic change which may discourage the use of quantization as a reliable model compression technique.

Ensuring the robustness of factual knowledge in LLMs is critical for reliable applications in tasks such as question answering and reasoning. However, existing evaluation methods predominantly focus on performance-based metrics, often investigating from the perspective of prompt perturbations, which captures only the externally triggered side of knowledge robustness. To bridge this gap, we introduce a principled approach to measure factual robustness from the perspective of the generation process by analyzing token distribution entropy in combination with temperature scaling sensitivity. These two factors build the Factual Robustness Score (FRS), a novel metric which quantifies the stability of a fact against perturbations in decoding conditions, given its initial uncertainty. To validate our approach, we conduct extensive experiments on 5 LLMs across 3 closed-book QA datasets (SQuAD, TriviaQA, and HotpotQA). We show that factual robustness varies significantly -- smaller models report an FRS of $0.76$, larger ones $0.93$ -- with accuracy degrading by ~$60\%$ under increased uncertainty. These insights demonstrate how entropy and temperature scaling impact factual accuracy, and lay a foundation for developing more robust knowledge retention and retrieval in future models.

Designing therapeutic peptides with tailored properties is hindered by the vastness of sequence space, limited experimental data, and poor interpretability of current generative models. To address these challenges, we introduce PepThink-R1, a generative framework that integrates large language models (LLMs) with chain-of-thought (CoT) supervised fine-tuning and reinforcement learning (RL). Unlike prior approaches, PepThink-R1 explicitly reasons about monomer-level modifications during sequence generation, enabling interpretable design choices while optimizing for multiple pharmacological properties. Guided by a tailored reward function balancing chemical validity and property improvements, the model autonomously explores diverse sequence variants. We demonstrate that PepThink-R1 generates cyclic peptides with significantly enhanced lipophilicity, stability, and exposure, outperforming existing general LLMs (e.g., GPT-5) and domain-specific baseline in both optimization success and interpretability. To our knowledge, this is the first LLM-based peptide design framework that combines explicit reasoning with RL-driven property control, marking a step toward reliable and transparent peptide optimization for therapeutic discovery.

As large language models (LLMs) are increasingly deployed in real-world applications, the need to selectively remove unwanted knowledge while preserving model utility has become paramount. Recent work has explored sparse autoencoders (SAEs) to perform precise interventions on monosemantic features. However, most SAE-based methods operate at inference time, which does not create persistent changes in the model's parameters. Such interventions can be bypassed or reversed by malicious actors with parameter access. We introduce CRISP, a parameter-efficient method for persistent concept unlearning using SAEs. CRISP automatically identifies salient SAE features across multiple layers and suppresses their activations. We experiment with two LLMs and show that our method outperforms prior approaches on safety-critical unlearning tasks from the WMDP benchmark, successfully removing harmful knowledge while preserving general and in-domain capabilities. Feature-level analysis reveals that CRISP achieves semantically coherent separation between target and benign concepts, allowing precise suppression of the target features.

Recent advances in large language models (LLMs) offer new opportunities for scalable, interactive mental health assessment, but excessive querying by LLMs burdens users and is inefficient for real-world screening across transdiagnostic symptom profiles. We introduce MAQuA, an adaptive question-asking framework for simultaneous, multidimensional mental health screening. Combining multi-outcome modeling on language responses with item response theory (IRT) and factor analysis, MAQuA selects the questions with most informative responses across multiple dimensions at each turn to optimize diagnostic information, improving accuracy and potentially reducing response burden. Empirical results on a novel dataset reveal that MAQuA reduces the number of assessment questions required for score stabilization by 50-87% compared to random ordering (e.g., achieving stable depression scores with 71% fewer questions and eating disorder scores with 85% fewer questions). MAQuA demonstrates robust performance across both internalizing (depression, anxiety) and externalizing (substance use, eating disorder) domains, with early stopping strategies further reducing patient time and burden. These findings position MAQuA as a powerful and efficient tool for scalable, nuanced, and interactive mental health screening, advancing the integration of LLM-based agents into real-world clinical workflows.

E-commerce sellers are advised to bid on keyphrases to boost their advertising campaigns. These keyphrases must be relevant to prevent irrelevant items from cluttering search systems and to maintain positive seller perception. It is vital that keyphrase suggestions align with seller, search and buyer judgments. Given the challenges in collecting negative feedback in these systems, LLMs have been used as a scalable proxy to human judgments. This paper presents an empirical study on a major ecommerce platform of a distillation framework involving an LLM teacher, a cross-encoder assistant and a bi-encoder Embedding Based Retrieval (EBR) student model, aimed at mitigating click-induced biases in keyphrase recommendations.

Argument summarization aims to generate concise, structured representations of complex, multi-perspective debates. While recent work has advanced the identification and clustering of argumentative components, the generation stage remains underexplored. Existing approaches typically rely on single-pass generation, offering limited support for factual correction or structural refinement. To address this gap, we introduce Arg-LLaDA, a novel large language diffusion framework that iteratively improves summaries via sufficiency-guided remasking and regeneration. Our method combines a flexible masking controller with a sufficiency-checking module to identify and revise unsupported, redundant, or incomplete spans, yielding more faithful, concise, and coherent outputs. Empirical results on two benchmark datasets demonstrate that Arg-LLaDA surpasses state-of-the-art baselines in 7 out of 10 automatic evaluation metrics. In addition, human evaluations reveal substantial improvements across core dimensions, coverage, faithfulness, and conciseness, validating the effectiveness of our iterative, sufficiency-aware generation strategy.