The paper presents our system developed for table question answering (TQA). TQA tasks face challenges due to the characteristics of real-world tabular data, such as large size, incomplete column semantics, and entity ambiguity. To address these issues, we propose a large language model (LLM)-powered and programming-based table reasoning framework, named TableReasoner. It models a table using the schema that combines structural and semantic representations, enabling holistic understanding and efficient processing of large tables. We design a multi-step schema linking plan to derive a focused table schema that retains only query-relevant information, eliminating ambiguity and alleviating hallucinations. This focused table schema provides precise and sufficient table details for query refinement and programming. Furthermore, we integrate the reasoning workflow into an iterative thinking architecture, allowing incremental cycles of thinking, reasoning and reflection. Our system achieves first place in both subtasks of SemEval-2025 Task 8.

The advancements in the domain of LLMs in recent years have surprised many, showcasing their remarkable capabilities and diverse applications. Their potential applications in various real-world scenarios have led to significant research on their reliability and effectiveness. On the other hand, multimodal LLMs and Text-to-Image models have only recently gained prominence, especially when compared to text-only LLMs. Their reliability remains constrained due to insufficient research on assessing their performance and robustness. This paper aims to establish a comprehensive evaluation framework for Text-to-Image models, concentrating particularly on their adherence to prompts. We created a novel dataset that aimed to assess the robustness of these models in generating images that conform to the specified factors of variation in the input text prompts. Our evaluation studies present findings on three variants of Stable Diffusion models: Stable Diffusion 3 Medium, Stable Diffusion 3.5 Large, and Stable Diffusion 3.5 Large Turbo, and two variants of Janus models: Janus Pro 1B and Janus Pro 7B. We introduce a pipeline that leverages text descriptions generated by the gpt-4o model for our ground-truth images, which are then used to generate artificial images by passing these descriptions to the Text-to-Image models. We then pass these generated images again through gpt-4o using the same system prompt and compare the variation between the two descriptions. Our results reveal that these models struggle to create simple binary images with only two factors of variation: a simple geometric shape and its location. We also show, using pre-trained VAEs on our dataset, that they fail to generate images that follow our input dataset distribution.

Autonomous agents built on language models (LMs) are showing increasing popularity in many fields, including scientific research. AI co-scientists aim to support or automate parts of the research process using these agents. A key component of empirical AI research is the design of ablation experiments. To this end, we introduce AblationBench, a benchmark suite for evaluating agents on ablation planning tasks in empirical AI research. It includes two tasks: AuthorAblation, which helps authors propose ablation experiments based on a method section and contains 83 instances, and ReviewerAblation, which helps reviewers find missing ablations in a full paper and contains 350 instances. For both tasks, we develop LM-based judges that serve as an automatic evaluation framework. Our experiments with frontier LMs show that these tasks remain challenging, with the best-performing LM system identifying only 29% of the original ablations on average. Lastly, we analyze the limitations of current LMs on these tasks, and find that chain-of-thought prompting outperforms the currently existing agent-based approach.

Recent advancements in large language models (LLMs) underscore the need for stronger reasoning capabilities to solve complex problems effectively. While Chain-of-Thought (CoT) reasoning has been a step forward, it remains insufficient for many domains. A promising alternative is explicit high-level plan generation, but existing approaches largely assume that LLMs can produce effective plans through few-shot prompting alone, without additional training. In this work, we challenge this assumption and introduce CRISP (Complex Reasoning with Interpretable Step-based Plans), a multi-domain dataset of high-level plans for mathematical reasoning and code generation. The plans in CRISP are automatically generated and rigorously validated--both intrinsically, using an LLM as a judge, and extrinsically, by evaluating their impact on downstream task performance. We demonstrate that fine-tuning a small model on CRISP enables it to generate higher-quality plans than much larger models using few-shot prompting, while significantly outperforming Chain-of-Thought reasoning. Furthermore, our out-of-domain evaluation reveals that fine-tuning on one domain improves plan generation in the other, highlighting the generalizability of learned planning capabilities.

This paper deals with improving querying large language models (LLMs). It is well-known that without relevant contextual information, LLMs can provide poor quality responses or tend to hallucinate. Several initiatives have proposed integrating LLMs with external tools to provide them with up-to-date data to improve accuracy. In this paper, we propose a framework to integrate external tools to enhance the capabilities of LLMs in answering queries in educational settings. Precisely, we develop a framework that allows accessing external APIs to request additional relevant information. Integrated tools can also provide computational capabilities such as calculators or calendars. The proposed framework has been evaluated using datasets from the Multi-Modal Language Understanding (MMLU) collection. The data consists of questions on mathematical and scientific reasoning. Results compared to state-of-the-art language models show that the proposed approach significantly improves performance. Our Athena framework achieves 83% accuracy in mathematical reasoning and 88% in scientific reasoning, substantially outperforming all tested models including GPT-4o, LLaMA-Large, Mistral-Large, Phi-Large, and GPT-3.5, with the best baseline model (LLaMA-Large) achieving only 67% and 79% respectively. These promising results open the way to creating complex computing ecosystems around LLMs to make their use more natural to support various tasks and activities.

Generative AI models, including large language models (LLMs) and vision-language models (VLMs), are increasingly used to interpret medical images and answer clinical questions. Their responses often include inaccuracies; therefore, safety measures like medical disclaimers are critical to remind users that AI outputs are not professionally vetted or a substitute for medical advice. This study evaluated the presence of disclaimers in LLM and VLM outputs across model generations from 2022 to 2025. Using 500 mammograms, 500 chest X-rays, 500 dermatology images, and 500 medical questions, outputs were screened for disclaimer phrases. Medical disclaimer presence in LLM and VLM outputs dropped from 26.3% in 2022 to 0.97% in 2025, and from 19.6% in 2023 to 1.05% in 2025, respectively. By 2025, the majority of models displayed no disclaimers. As public models become more capable and authoritative, disclaimers must be implemented as a safeguard adapting to the clinical context of each output.

Artificial intelligence (AI) is increasingly used in recruitment, yet empirical evidence quantifying its impact on hiring efficiency and candidate selection remains limited. We randomly assign 37,000 applicants for a junior-developer position to either a traditional recruitment process (resume screening followed by human selection) or an AI-assisted recruitment pipeline incorporating an initial AI-driven structured video interview before human evaluation. Candidates advancing from either track faced the same final-stage human interview, with interviewers blind to the earlier selection method. In the AI-assisted pipeline, 54% of candidates passed the final interview compared with 34% from the traditional pipeline, yielding an average treatment effect of 20 percentage points (SE 12 pp.). Five months later, we collected LinkedIn profiles of top applicants from both groups and found that 18% (SE 1.1%) of applicants from the traditional track found new jobs compared with 23% (SE 2.3%) from the AI group, resulting in a 5.9 pp. (SE 2.6 pp.) difference in the probability of finding new employment between groups. The AI system tended to select younger applicants with less experience and fewer advanced credentials. We analyze AI-generated interview transcripts to examine the selection criteria and conversational dynamics. Our findings contribute to understanding how AI technologies affect decision making in recruitment and talent acquisition while highlighting some of their potential implications.

"Amazing, They All Lean Left" - Analyzing the Political Temperaments of Current LLMs Abstract Recent studies have revealed a consistent liberal orientation in the ethical and political responses generated by most commercial large language models (LLMs), yet the underlying causes and resulting implications remain unclear. This paper systematically i nvestigates the political temperament of seven prominent LLMs -- OpenAI's GPT - 4o, Anthropic's Claude Sonnet 4, Perplexity (Sonar Large), Google's Gemini 2.5 Flash, Meta AI's L l a ma 4, Mistral 7b Le Chat, and High - Flyer ' s DeepSeek R1 -- using a multi - pronged approach that incl udes Moral Foundations Theory, a dozen established political ideology scales, and a new index of current political controversies. We find strong and consistent prioritization of liberal - leaning values, particularly care and fairness, across most models. Fur ther analysis attributes this trend to four overlapping factors: liberal - leaning training corpora, reinforcement learning from human feedback (RLHF), the dominance of liberal frameworks in academic ethical discourse, and safety - driven fine - tuning practices . We also distinguish between political "bias" and legitimate epistemic differences, cautioning against conflating the two. A comparison of base and fine - tuned model pairs reveals that fine - tuning generally increases liberal lean, an effect confirmed throu gh both self - report and empirical testing. We argue that this "liberal tilt" is not a programming error or the personal preferences of programmers but an emergent property of training on democratic, rights - focused discourse. Finally, we propose that LLMs may indirectly echo John Rawls' famous veil - of - igno rance philosophical aspiration, reflecting a moral stance unanchored to personal identity or interest. Rather than undermining democratic discourse, this pattern may offer a new lens through which to examine collective ethical reasoning. In the course of our research on the ethical logics of currently prominent large language models (Neuman et al. 2025a, b; Coleman et al. 2025), we encountered an interesting finding. The responses to various ethical dilemmas and the explanations of the underlying logics used by these models appear to resonate with the liberal side of the political spectrum. One research analytic we utilize draws on Moral Foundation Theory's five - element typology of foundational moral principles (Graham et al. 2009; Haidt 2012). The five foundations emp hasizing in turn, Care, Fairness, Loyalty, Authority and Purity, are traditionally divided into two clusters. The first two, Care and Fairness, are associated with a liberal political perspective, while conservatives who fully acknowledge the first two more often emphasize the latter three -- Loyalty, Authority and Purity in support of traditional norms.

Large Language Models (LLMs) have achieved remarkable success across domains such as healthcare, education, and cybersecurity. However, this openness also introduces significant security risks, particularly through embedding space poisoning, which is a subtle attack vector where adversaries manipulate the internal semantic representations of input data to bypass safety alignment mechanisms. While previous research has investigated universal perturbation methods, the dynamics of LLM safety alignment at the embedding level remain insufficiently understood. Consequently, more targeted and accurate adversarial perturbation techniques, which pose significant threats, have not been adequately studied. In this work, we propose ETTA (Embedding Transformation Toxicity Attenuation), a novel framework that identifies and attenuates toxicity-sensitive dimensions in embedding space via linear transformations. ETTA bypasses model refusal behaviors while preserving linguistic coherence, without requiring model fine-tuning or access to training data. Evaluated on five representative open-source LLMs using the AdvBench benchmark, ETTA achieves a high average attack success rate of 88.61%, outperforming the best baseline by 11.34%, and generalizes to safety-enhanced models (e.g., 77.39% ASR on instruction-tuned defenses). These results highlight a critical vulnerability in current alignment strategies and underscore the need for embedding-aware defenses.

This study investigates whether large language models (LLMs) exhibit consistent behavior (signal) or random variation (noise) when screening resumes against job descriptions, and how their performance compares to human experts. Using controlled datasets, we tested three LLMs (Claude, GPT, and Gemini) across contexts (No Company, Firm1 [MNC], Firm2 [Startup], Reduced Context) with identical and randomized resumes, benchmarked against three human recruitment experts. Analysis of variance revealed significant mean differences in four of eight LLM-only conditions and consistently significant differences between LLM and human evaluations (p < 0.01). Paired t-tests showed GPT adapts strongly to company context (p < 0.001), Gemini partially (p = 0.038 for Firm1), and Claude minimally (p > 0.1), while all LLMs differed significantly from human experts across contexts. Meta-cognition analysis highlighted adaptive weighting patterns that differ markedly from human evaluation approaches. Findings suggest LLMs offer interpretable patterns with detailed prompts but diverge substantially from human judgment, informing their deployment in automated hiring systems.