Molecular dynamics (MD) simulations are essential for understanding biomolecular systems but remain challenging to automate. Recent advances in large language models (LLM) have demonstrated success in automating complex scientific tasks using LLM-based agents. In this paper, we introduce MDCrow, an agentic LLM assistant capable of automating MD workflows. MDCrow uses chain-of-thought over 40 expert-designed tools for handling and processing files, setting up simulations, analyzing the simulation outputs, and retrieving relevant information from literature and databases. We assess MDCrow's performance across 25 tasks of varying required subtasks and difficulty, and we evaluate the agent's robustness to both difficulty and prompt style. \texttt{gpt-4o} is able to complete complex tasks with low variance, followed closely by \texttt{llama3-405b}, a compelling open-source model. While prompt style does not influence the best models' performance, it has significant effects on smaller models.

Multi-modal large language models (MLLMs) have shown remarkable abilities in various visual understanding tasks. However, MLLMs still struggle with fine-grained visual recognition (FGVR), which aims to identify subordinate-level categories from images. This can negatively impact more advanced capabilities of MLLMs, such as object-centric visual question answering and reasoning. In our study, we revisit three quintessential capabilities of MLLMs for FGVR, including object information extraction, category knowledge reserve, object-category alignment, and position of the root cause as a misalignment problem. To address this issue, we present Finedefics, an MLLM that enhances the model's FGVR capability by incorporating informative attribute descriptions of objects into the training phase. We employ contrastive learning on object-attribute pairs and attribute-category pairs simultaneously and use examples from similar but incorrect categories as hard negatives, naturally bringing representations of visual objects and category names closer. Extensive evaluations across multiple popular FGVR datasets demonstrate that Finedefics outperforms existing MLLMs of comparable parameter sizes, showcasing its remarkable efficacy. The code is available at https://github.com/PKU-ICST-MIPL/Finedefics_ICLR2025.

Slot-filling and intent detection are well-established tasks in Conversational AI. However, current large-scale benchmarks for these tasks often exclude evaluations of low-resource languages and rely on translations from English benchmarks, thereby predominantly reflecting Western-centric concepts. In this paper, we introduce Injongo -- a multicultural, open-source benchmark dataset for 16 African languages with utterances generated by native speakers across diverse domains, including banking, travel, home, and dining. Through extensive experiments, we benchmark the fine-tuning multilingual transformer models and the prompting large language models (LLMs), and show the advantage of leveraging African-cultural utterances over Western-centric utterances for improving cross-lingual transfer from the English language. Experimental results reveal that current LLMs struggle with the slot-filling task, with GPT-4o achieving an average performance of 26 F1-score. In contrast, intent detection performance is notably better, with an average accuracy of 70.6%, though it still falls behind the fine-tuning baselines. Compared to the English language, GPT-4o and fine-tuning baselines perform similarly on intent detection, achieving an accuracy of approximately 81%. Our findings suggest that the performance of LLMs is still behind for many low-resource African languages, and more work is needed to further improve their downstream performance.

Large Language Models (LLMs) have demonstrated remarkable success across various NLP benchmarks. However, excelling in complex tasks that require nuanced reasoning and precise decision-making demands more than raw language proficiency--LLMs must reason, i.e., think logically, draw from past experiences, and synthesize information to reach conclusions and take action. To enhance reasoning abilities, approaches such as prompting and fine-tuning have been widely explored. While these methods have led to clear improvements in reasoning, their impact on LLM safety remains less understood. In this work, we investigate the interplay between reasoning and safety in LLMs. We highlight the latent safety risks that arise as reasoning capabilities improve, shedding light on previously overlooked vulnerabilities. At the same time, we explore how reasoning itself can be leveraged to enhance safety, uncovering potential mitigation strategies. By examining both the risks and opportunities in reasoning-driven LLM safety, our study provides valuable insights for developing models that are not only more capable but also more trustworthy in real-world deployments.

Answering questions with Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs), yet its impact on Large Multimodal Models (LMMs) still lacks a systematic assessment and in-depth investigation. In this paper, we introduce MME-CoT, a specialized benchmark evaluating the CoT reasoning performance of LMMs, spanning six domains: math, science, OCR, logic, space-time, and general scenes. As the first comprehensive study in this area, we propose a thorough evaluation suite incorporating three novel metrics that assess the reasoning quality, robustness, and efficiency at a fine-grained level. Leveraging curated high-quality data and a unique evaluation strategy, we conduct an in-depth analysis of state-of-the-art LMMs, uncovering several key insights: 1) Models with reflection mechanism demonstrate a superior CoT quality, with Kimi k1.5 outperforming GPT-4o and demonstrating the highest quality results; 2) CoT prompting often degrades LMM performance on perception-heavy tasks, suggesting a potentially harmful overthinking behavior; and 3) Although the CoT quality is high, LMMs with reflection exhibit significant inefficiency in both normal response and self-correction phases. We hope MME-CoT serves as a foundation for advancing multimodal reasoning in LMMs. Project Page: https://mmecot.github.io/

We propose E-MD3C ($\underline{E}$fficient $\underline{M}$asked $\underline{D}$iffusion Transformer with Disentangled $\underline{C}$onditions and $\underline{C}$ompact $\underline{C}$ollector), a highly efficient framework for zero-shot object image customization. Unlike prior works reliant on resource-intensive Unet architectures, our approach employs lightweight masked diffusion transformers operating on latent patches, offering significantly improved computational efficiency. The framework integrates three core components: (1) an efficient masked diffusion transformer for processing autoencoder latents, (2) a disentangled condition design that ensures compactness while preserving background alignment and fine details, and (3) a learnable Conditions Collector that consolidates multiple inputs into a compact representation for efficient denoising and learning. E-MD3C outperforms the existing approach on the VITON-HD dataset across metrics such as PSNR, FID, SSIM, and LPIPS, demonstrating clear advantages in parameters, memory efficiency, and inference speed. With only $\frac{1}{4}$ of the parameters, our Transformer-based 468M model delivers $2.5\times$ faster inference and uses $\frac{2}{3}$ of the GPU memory compared to an 1720M Unet-based latent diffusion model.

Recent attention to anthropomorphism -- the attribution of human-like qualities to non-human objects or entities -- of language technologies like LLMs has sparked renewed discussions about potential negative impacts of anthropomorphism. To productively discuss the impacts of this anthropomorphism and in what contexts it is appropriate, we need a shared vocabulary for the vast variety of ways that language can be anthropomorphic. In this work, we draw on existing literature and analyze empirical cases of user interactions with language technologies to develop a taxonomy of textual expressions that can contribute to anthropomorphism. We highlight challenges and tensions involved in understanding linguistic anthropomorphism, such as how all language is fundamentally human and how efforts to characterize and shift perceptions of humanness in machines can also dehumanize certain humans. We discuss ways that our taxonomy supports more precise and effective discussions of and decisions about anthropomorphism of language technologies.

Modern Large Language Models (LLMs) have shown human-like abilities in many language tasks, sparking interest in comparing LLMs' and humans' language processing. In this paper, we conduct a detailed comparison of the two on a sentence comprehension task using garden-path constructions, which are notoriously challenging for humans. Based on psycholinguistic research, we formulate hypotheses on why garden-path sentences are hard, and test these hypotheses on human participants and a large suite of LLMs using comprehension questions. Our findings reveal that both LLMs and humans struggle with specific syntactic complexities, with some models showing high correlation with human comprehension. To complement our findings, we test LLM comprehension of garden-path constructions with paraphrasing and text-to-image generation tasks, and find that the results mirror the sentence comprehension question results, further validating our findings on LLM understanding of these constructions.

From crowdsourced storymapping projects sharing stories of love, loss, and a sense of belonging [1] to safe, anonymous spaces to seek resources [2] and dating platforms [3] - the internet and modern technologies play a positive role in health and well-being of the LGBTQ+ community in various ways. However, cyberbullying [4], exposure to dehumanization through news media [5], and more recently, worrisome homophobic biases in large language models [6] - are some of the modern technology perils the community grapples with. How do mainstream US cable news outlets cover the LGBTQ+ community and how do users interact with such news content? Via a substantial corpus of more than 130 million YouTube comments on more than 300K YouTube news videos uploaded on three major US cable news outlets, this paper investigates how LGBTQ+ discussions are situated in mainstream US political discourse. While prior literature has analyzed LGBTQ+ discourse in print media through the lens of a dehumanization framework [5], such analyses consulted a single source of news (The New York Times) and did not consider reader responses to LGBTQ+ news. In this work, we consider three major US cable news networks representing diverse political views (Fox News, CNN, and MSNBC) with a key goal to understand how users interact and engage with LGBTQ+ news content. In doing so, we not only focus on identifying negative discussions about the LGBTQ+ community, one of our key contributions is operationalizing the detection of positive, hope speech championing the disadvantaged minority in the broader spirit of counter-speech literature [7, 8, 9, 10, 11].

Evaluating the open-ended text generation of large language models (LLMs) is challenging because of the lack of a clear ground truth and the high cost of human or LLM-based assessments. We propose a novel benchmark that evaluates LLMs using n-gram statistics and rules, without relying on human judgement or LLM-as-a-judge approaches. Using 50 question and reference answer sets, we introduce three new metrics based on n-grams and rules: Fluency, Truthfulness, and Helpfulness. Our benchmark strongly correlates with GPT-4o-based evaluations while requiring significantly fewer computational resources, demonstrating its effectiveness as a scalable alternative for assessing LLMs' open-ended generation capabilities.