Long-form question answering (LFQA) presents unique challenges for large language models, requiring the synthesis of coherent, paragraph-length answers. While retrieval-augmented generation (RAG) systems have emerged as a promising solution, existing research struggles with key limitations: the scarcity of high-quality training data for long-form generation, the compounding risk of hallucination in extended outputs, and the absence of reliable evaluation metrics for factual completeness. In this paper, we propose RioRAG, a novel reinforcement learning (RL) framework that advances long-form RAG through reinforced informativeness optimization. Our approach introduces two fundamental innovations to address the core challenges. First, we develop an RL training paradigm of reinforced informativeness optimization that directly optimizes informativeness and effectively addresses the slow-thinking deficit in conventional RAG systems, bypassing the need for expensive supervised data. Second, we propose a nugget-centric hierarchical reward modeling approach that enables precise assessment of long-form answers through a three-stage process: extracting the nugget from every source webpage, constructing a nugget claim checklist, and computing rewards based on factual alignment. Extensive experiments on two LFQA benchmarks LongFact and RAGChecker demonstrate the effectiveness of the proposed method. Our codes are available at https://github.com/RUCAIBox/RioRAG.

As large language models (LLMs) are increasingly deployed in healthcare, ensuring their safety, particularly within collaborative multi-agent configurations, is paramount. In this paper we introduce MedSentry, a benchmark comprising 5 000 adversarial medical prompts spanning 25 threat categories with 100 subthemes. Coupled with this dataset, we develop an end-to-end attack-defense evaluation pipeline to systematically analyze how four representative multi-agent topologies (Layers, SharedPool, Centralized, and Decentralized) withstand attacks from 'dark-personality' agents. Our findings reveal critical differences in how these architectures handle information contamination and maintain robust decision-making, exposing their underlying vulnerability mechanisms. For instance, SharedPool's open information sharing makes it highly susceptible, whereas Decentralized architectures exhibit greater resilience thanks to inherent redundancy and isolation. To mitigate these risks, we propose a personality-scale detection and correction mechanism that identifies and rehabilitates malicious agents, restoring system safety to near-baseline levels. MedSentry thus furnishes both a rigorous evaluation framework and practical defense strategies that guide the design of safer LLM-based multi-agent systems in medical domains.

Mental manipulation is a subtle yet pervasive form of abuse in interpersonal communication, making its detection critical for safeguarding potential victims. However, due to manipulation's nuanced and context-specific nature, identifying manipulative language in complex, multi-turn, and multi-person conversations remains a significant challenge for large language models (LLMs). To address this gap, we introduce the MultiManip dataset, comprising 220 multi-turn, multi-person dialogues balanced between manipulative and non-manipulative interactions, all drawn from reality shows that mimic real-world scenarios. For manipulative interactions, it includes 11 distinct manipulations depicting real-life scenarios. We conduct extensive evaluations of state-of-the-art LLMs, such as GPT-4o and Llama-3.1-8B, employing various prompting strategies. Despite their capabilities, these models often struggle to detect manipulation effectively. To overcome this limitation, we propose SELF-PERCEPT, a novel, two-stage prompting framework inspired by Self-Perception Theory, demonstrating strong performance in detecting multi-person, multi-turn mental manipulation. Our code and data are publicly available at https://github.com/danushkhanna/self-percept .

The performance of large language models (LLMs) across diverse downstream applications is fundamentally governed by the quality and composition of their pretraining corpora. Existing domain reweighting algorithms primarily optimize data mixtures for a single target task, thereby resulting in models that overfit to specialized objectives while exhibiting substantial performance degradation on other benchmarks. This paper introduces Group Robust Multi-target Adaptive PrEtraining (GRAPE), a novel multi-source-multi-target domain reweighting framework designed to calibrate pretraining data mixtures for robust performance across multiple target tasks simultaneously. GRAPE dynamically adjusts sampling weights across source domains (domain weights) while concurrently modulating task weights that quantify the relative importance of each individual target task. This adaptive process prioritizes tasks based on their learning difficulty throughout training. We formulate this interleaved reweighting mechanism as a minimax optimization problem: The inner maximization adjusts task weights leveraging group distributed-robust-optimization (DRO), where those tasks demonstrating the least improvement under the current data mixture are prioritized with higher weights; The outer minimization then optimizes domain weights to maximize loss reduction on the prioritized tasks. Experiments on ClimbLab and SlimPajama datasets demonstrate that GRAPE consistently outperforms baseline methods in terms of reasoning performance across 6 benchmarks. Furthermore, when applied to multilingual targets, GRAPE effectively identifies optimal training mixtures from mainstream languages, achieving superior language modeling capabilities across 8 low-resource target languages.

The rapid advancement of vision-language models (VLMs) has brought a lot of attention to their safety alignment. However, existing methods have primarily focused on model undersafety, where the model responds to hazardous queries, while neglecting oversafety, where the model refuses to answer safe queries. In this paper, we introduce the concept of $\textit{safety calibration}$, which systematically addresses both undersafety and oversafety. Specifically, we present $\textbf{VSCBench}$, a novel dataset of 3,600 image-text pairs that are visually or textually similar but differ in terms of safety, which is designed to evaluate safety calibration across image-centric and text-centric scenarios. Based on our benchmark, we evaluate safety calibration across eleven widely used VLMs. Our extensive experiments revealed major issues with both undersafety and oversafety. We further investigated four approaches to improve the model's safety calibration. We found that even though some methods effectively calibrated the models' safety problems, these methods also lead to the degradation of models' utility. This trade-off underscores the urgent need for advanced calibration methods, and our benchmark provides a valuable tool for evaluating future approaches. Our code and data are available at https://github.com/jiahuigeng/VSCBench.git.

We investigate the existence and persistence of a specific type of gender bias in some of the popular LLMs and contribute a new benchmark dataset, RealWorldQuestioning (released on HuggingFace ), developed from real-world questions across four key domains in business and health contexts: education, jobs, personal financial management, and general health. We define and study entropy bias, which we define as a discrepancy in the amount of information generated by an LLM in response to real questions users have asked. We tested this using four different LLMs and evaluated the generated responses both qualitatively and quantitatively by using ChatGPT-4o (as "LLM-as-judge"). Our analyses (metric-based comparisons and "LLM-as-judge" evaluation) suggest that there is no significant bias in LLM responses for men and women at a category level. However, at a finer granularity (the individual question level), there are substantial differences in LLM responses for men and women in the majority of cases, which "cancel" each other out often due to some responses being better for males and vice versa. This is still a concern since typical users of these tools often ask a specific question (only) as opposed to several varied ones in each of these common yet important areas of life. We suggest a simple debiasing approach that iteratively merges the responses for the two genders to produce a final result. Our approach demonstrates that a simple, prompt-based debiasing strategy can effectively debias LLM outputs, thus producing responses with higher information content than both gendered variants in 78% of the cases, and consistently achieving a balanced integration in the remaining cases.

As the quality of code generated by Large Language Models (LLMs) improves, their adoption in the software industry for automated code generation continues to grow. Researchers primarily focus on enhancing the functional correctness of the generated code while commonly overlooking its energy efficiency and environmental impact. This paper investigates the energy efficiency of the code generated by 20 popular LLMs for 878 programming problems of varying difficulty levels and diverse algorithmic categories selected from the LeetCode platform by comparing them against canonical human-written solutions. Although LLMs can produce functionally correct results in most cases, our findings show that the performance and energy efficiency of LLM-produced solutions are often far below those of human-written solutions. Among the studied LLMs, DeepSeek-v3 and GPT-4o generate the most energy-efficient code, whereas Grok-2 and Gemini-1.5-Pro are among the least energy-efficient models. On average, human-generated canonical solutions are approximately 1.17 times more energy efficient than DeepSeek-v3, 1.21 times more energy efficient than GPT-4o, and over 2 times more energy efficient than Grok-2 and Gemini-1.5-Pro. For specific algorithmic groups such as dynamic programming, backtracking, and bit manipulation, LLM-generated code can consume up to 450 times more energy than human-generated canonical solutions.

Knowledge representation and reasoning in neural networks have been a long-standing endeavor which has attracted much attention recently. The principled integration of reasoning and learning in neural networks is a main objective of the area of neurosymbolic Artificial Intelligence (AI). In this chapter, a simple energy-based neurosymbolic AI system is described that can represent and reason formally about any propositional logic formula. This creates a powerful combination of learning from data and knowledge and logical reasoning. We start by positioning neurosymbolic AI in the context of the current AI landscape that is unsurprisingly dominated by Large Language Models (LLMs). We identify important challenges of data efficiency, fairness and safety of LLMs that might be addressed by neurosymbolic reasoning systems with formal reasoning capabilities. We then discuss the representation of logic by the specific energy-based system, including illustrative examples and empirical evaluation of the correspondence between logical reasoning and energy minimization using Restricted Boltzmann Machines (RBM). Learning from data and knowledge is also evaluated empirically and compared with a symbolic, neural and a neurosymbolic system. Results reported in this chapter in an accessible way are expected to reignite the research on the use of neural networks as massively-parallel models for logical reasoning and promote the principled integration of reasoning and learning in deep networks. We conclude the chapter with a discussion of the importance of positioning neurosymbolic AI within a broader framework of formal reasoning and accountability in AI, discussing the challenges for neurosynbolic AI to tackle the various known problems of reliability of deep learning.

Future of Code with Generative AI: Transparency and Safety in the Era of AI-Generated Software By David Hanson Ph.D. Abstract As artificial intelligence (AI) becomes increasingly integrated into software development processes, the prevalence and sophistication of AI-generated code continue to expand rapidly. This study addresses the critical need for transparency and safety in AI-generated code by examining the current landscape, identifying potential risks, and exploring future implications. We analyze market opportunities for detecting AI-generated code, discuss the challenges associated with managing increasing complexity, and propose solutions to enhance transparency and functionality analysis. Furthermore, this study investigates the long-term implications of AI-generated code, including its potential role in the development of artificial general intelligence and its impact on human-AI interaction. In conclusion, we emphasize the importance of proactive measures for ensuring the responsible development and deployment of AI in software engineering. Introduction The integration of artificial intelligence (AI) into software development processes marks a pivotal development in the evolution of computer programming. As AI-generated code becomes increasingly prevalent and sophisticated, it introduces both significant opportunities and complex challenges for software engineering.

This study examines the behavior of Large Language Models (LLMs) when evaluating professional candidates based on their resumes or curricula vitae (CVs). In an experiment involving 22 leading LLMs, each model was systematically given one job description along with a pair of profession-matched CVs, one bearing a male first name, the other a female first name, and asked to select the more suitable candidate for the job. Each CV pair was presented twice, with names swapped to ensure that any observed preferences in candidate selection stemmed from gendered names cues. Despite identical professional qualifications across genders, all LLMs consistently favored female-named candidates across 70 different professions. Adding an explicit gender field (male/female) to the CVs further increased the preference for female applicants. When gendered names were replaced with gender-neutral identifiers "Candidate A" and "Candidate B", several models displayed a preference to select "Candidate A". Counterbalancing gender assignment between these gender-neutral identifiers resulted in gender parity in candidate selection. When asked to rate CVs in isolation rather than compare pairs, LLMs assigned slightly higher average scores to female CVs overall, but the effect size was negligible. Including preferred pronouns (he/him or she/her) next to a candidate's name slightly increased the odds of the candidate being selected regardless of gender. Finally, most models exhibited a substantial positional bias to select the candidate listed first in the prompt. These findings underscore the need for caution when deploying LLMs in high-stakes autonomous decision-making contexts and raise doubts about whether LLMs consistently apply principled reasoning.