Gestures are an integral part of non-verbal communication, with meanings that vary across cultures, and misinterpretations that can have serious social and diplomatic consequences. As AI systems become more integrated into global applications, ensuring they do not inadvertently perpetuate cultural offenses is critical. To this end, we introduce Multi-Cultural Set of Inappropriate Gestures and Nonverbal Signs (MC-SIGNS), a dataset of 288 gesture-country pairs annotated for offensiveness, cultural significance, and contextual factors across 25 gestures and 85 countries. Through systematic evaluation using MC-SIGNS, we uncover critical limitations: text-to-image (T2I) systems exhibit strong US-centric biases, performing better at detecting offensive gestures in US contexts than in non-US ones; large language models (LLMs) tend to over-flag gestures as offensive; and vision-language models (VLMs) default to US-based interpretations when responding to universal concepts like wishing someone luck, frequently suggesting culturally inappropriate gestures. These findings highlight the urgent need for culturally-aware AI safety mechanisms to ensure equitable global deployment of AI technologies.

Large language models (LLMs) have been widely adopted in various downstream task domains. However, their ability to directly recall and apply factual medical knowledge remains under-explored. Most existing medical QA benchmarks assess complex reasoning or multi-hop inference, making it difficult to isolate LLMs' inherent medical knowledge from their reasoning capabilities. Given the high-stakes nature of medical applications, where incorrect information can have critical consequences, it is essential to evaluate how well LLMs encode, retain, and recall fundamental medical facts. To bridge this gap, we introduce the Medical Knowledge Judgment, a dataset specifically designed to measure LLMs' one-hop factual medical knowledge. MKJ is constructed from the Unified Medical Language System (UMLS), a large-scale repository of standardized biomedical vocabularies and knowledge graphs. We frame knowledge assessment as a binary judgment task, requiring LLMs to verify the correctness of medical statements extracted from reliable and structured knowledge sources. Our experiments reveal that LLMs struggle with factual medical knowledge retention, exhibiting significant performance variance across different semantic categories, particularly for rare medical conditions. Furthermore, LLMs show poor calibration, often being overconfident in incorrect answers. To mitigate these issues, we explore retrieval-augmented generation, demonstrating its effectiveness in improving factual accuracy and reducing uncertainty in medical decision-making.

Large Language Models (LLMs) have demonstrated strong generalization capabilities across a wide range of natural language processing (NLP) tasks. However, they exhibit notable weaknesses in character-level string manipulation, struggling with fundamental operations such as character deletion, insertion, and substitution. These challenges stem primarily from tokenization constraints, despite the critical role of such operations in data preprocessing and code generation. Through systematic analysis, we derive two key insights: (1) LLMs face significant difficulties in leveraging intrinsic token knowledge for character-level reasoning, and (2) atomized word structures can substantially enhance LLMs' ability to process token-level structural information. Building on these insights, we propose Character-Level Manipulation via Divide and Conquer, a novel approach designed to bridge the gap between token-level processing and character-level manipulation. Our method decomposes complex operations into explicit character-level subtasks coupled with controlled token reconstruction phases, leading to significant improvements in accuracy. Without additional training, our method significantly improves accuracies on the $\texttt{Deletion}$, $\texttt{Insertion}$, and $\texttt{Substitution}$ tasks. To support further research, we open-source our implementation and benchmarks.

Pre-trained Large Language Models (LLMs) require post-training methods such as supervised fine-tuning (SFT) on instruction-response pairs to enable instruction following. However, this process can potentially harm existing capabilities learned during pre-training. In this paper, we investigate the loss of context awareness after SFT, where context awareness is defined as the ability to extract and understand information from user-provided context and respond accordingly. We are the first to identify and show that the loss of context awareness, as reflected by the performance drop in the Needle-in-a-Haystack test, occurs in instruction fine-tuned LLMs when the chat template is applied to input prompts. We identify that the performance decline is partially caused by an attention bias toward different roles learned during conversational instruction fine-tuning. We validate our hypothesis by visualizing changes in attention allocation after the chat template is applied and manually steering the attention heads. Based on these observations, we propose a metric to select context-dependent examples from general instruction fine-tuning datasets. We then apply conditional instruction fine-tuning with a context-dependency indicator, enabling the model to learn context awareness from these selected examples. Empirical experiments on four context-dependent downstream tasks and three pre-trained LLMs of different sizes show that our method effectively mitigates the loss of context awareness without compromising general instruction-following capabilities. Given our findings, we strongly advocate for careful benchmarking of context awareness after instruction fine-tuning.

In the rapidly evolving field of Large Language Models (LLMs), ensuring safety is a crucial and widely discussed topic. However, existing works often overlook the geo-diversity of cultural and legal standards across the world. To demonstrate the challenges posed by geo-diverse safety standards, we introduce SafeWorld, a novel benchmark specifically designed to evaluate LLMs' ability to generate responses that are not only helpful but also culturally sensitive and legally compliant across diverse global contexts. SafeWorld encompasses 2,342 test user queries, each grounded in high-quality, human-verified cultural norms and legal policies from 50 countries and 493 regions/races. On top of it, we propose a multi-dimensional automatic safety evaluation framework that assesses the contextual appropriateness, accuracy, and comprehensiveness of responses. Our evaluations reveal that current LLMs struggle to meet these criteria. To enhance LLMs' alignment with geo-diverse safety standards, we synthesize helpful preference pairs for Direct Preference Optimization (DPO) alignment training. The preference pair construction aims to encourage LLMs to behave appropriately and provide precise references to relevant cultural norms and policies when necessary. Our trained SafeWorldLM outperforms all competing models, including GPT-4o on all three evaluation dimensions by a large margin. Global human evaluators also note a nearly 20% higher winning rate in helpfulness and harmfulness evaluation. Our code and data can be found here: https://github.com/PlusLabNLP/SafeWorld.

Question answering represents a core capability of large language models (LLMs). However, when individuals encounter unfamiliar knowledge in texts, they often formulate questions that the text itself cannot answer due to insufficient understanding of the underlying information. Recent studies reveal that while LLMs can detect unanswerable questions, they struggle to assist users in reformulating these questions. Even advanced models like GPT-3.5 demonstrate limited effectiveness in this regard. To address this limitation, we propose DRS: Deep Question Reformulation with Structured Output, a novel zero-shot method aimed at enhancing LLMs ability to assist users in reformulating questions to extract relevant information from new documents. DRS combines the strengths of LLMs with a DFS-based algorithm to iteratively explore potential entity combinations and constrain outputs using predefined entities. This structured approach significantly enhances the reformulation capabilities of LLMs. Comprehensive experimental evaluations demonstrate that DRS improves the reformulation accuracy of GPT-3.5 from 23.03% to 70.42%, while also enhancing the performance of open-source models, such as Gemma2-9B, from 26.35% to 56.75%.

The ability of large vision-language models (LVLMs) to critique and correct their reasoning is an essential building block towards their self-improvement. However, a systematic analysis of such capabilities in LVLMs is still lacking. We propose VISCO, the first benchmark to extensively analyze the fine-grained critique and correction capabilities of LVLMs. Compared to existing work that uses a single scalar value to critique the entire reasoning [4], VISCO features dense and fine-grained critique, requiring LVLMs to evaluate the correctness of each step in the chain-of-thought and provide natural language explanations to support their judgments. Extensive evaluation of 24 LVLMs demonstrates that human-written critiques significantly enhance the performance after correction, showcasing the potential of the self-improvement strategy. However, the model-generated critiques are less helpful and sometimes detrimental to the performance, suggesting that critique is the crucial bottleneck. We identified three common patterns in critique failures: failure to critique visual perception, reluctance to "say no", and exaggerated assumption of error propagation. To address these issues, we propose an effective LookBack strategy that revisits the image to verify each piece of information in the initial reasoning. LookBack significantly improves critique and correction performance by up to 13.5%.

Humans recognize objects after observing only a few examples, a remarkable capability enabled by their inherent language understanding of the real-world environment. Developing verbalized and interpretable representation can significantly improve model generalization in low-data settings. In this work, we propose Verbalized Representation Learning (VRL), a novel approach for automatically extracting human-interpretable features for object recognition using few-shot data. Our method uniquely captures inter-class differences and intra-class commonalities in the form of natural language by employing a Vision-Language Model (VLM) to identify key discriminative features between different classes and shared characteristics within the same class. These verbalized features are then mapped to numeric vectors through the VLM. The resulting feature vectors can be further utilized to train and infer with downstream classifiers. Experimental results show that, at the same model scale, VRL achieves a 24% absolute improvement over prior state-of-the-art methods while using 95% less data and a smaller mode. Furthermore, compared to human-labeled attributes, the features learned by VRL exhibit a 20% absolute gain when used for downstream classification tasks. Code is available at: https://github.com/joeyy5588/VRL/tree/main.

Human writers plan, then write. For large language models (LLMs) to play a role in longer-form article generation, we must understand the planning steps humans make before writing. We explore one kind of planning, source-selection in news, as a case-study for evaluating plans in long-form generation. We ask: why do specific stories call for specific kinds of sources? We imagine a generative process for story writing where a source-selection schema is first selected by a journalist, and then sources are chosen based on categories in that schema. Learning the article's plan means predicting the schema initially chosen by the journalist. Working with professional journalists, we adapt five existing schemata and introduce three new ones to describe journalistic plans for the inclusion of sources in documents. Then, inspired by Bayesian latent-variable modeling, we develop metrics to select the most likely plan, or schema, underlying a story, which we use to compare schemata. We find that two schemata: stance and social affiliation best explain source plans in most documents. However, other schemata like textual entailment explain source plans in factually rich topics like "Science". Finally, we find we can predict the most suitable schema given just the article's headline with reasonable accuracy. We see this as an important case-study for human planning, and provides a framework and approach for evaluating other kinds of plans. We release a corpora, NewsSources, with annotations for 4M articles.

Contrastive decoding (CD) (Li et al., 2023) improves the next-token distribution of a large expert language model (LM) using a small amateur LM. Although CD is applied to various LMs and domains to enhance open-ended text generation, it is still unclear why CD often works well, when it could fail, and how we can make it better. To deepen our understanding of CD, we first theoretically prove that CD could be viewed as linearly extrapolating the next-token logits from a huge and hypothetical LM. We also highlight that the linear extrapolation could make CD unable to output the most obvious answers that have already been assigned high probabilities by the amateur LM. To overcome CD's limitation, we propose a new unsupervised decoding method called $\mathbf{A}$symptotic $\mathbf{P}$robability $\mathbf{D}$ecoding (APD). APD explicitly extrapolates the probability curves from the LMs of different sizes to infer the asymptotic probabilities from an infinitely large LM without inducing more inference costs than CD. In FactualityPrompts, an open-ended text generation benchmark, sampling using APD significantly boosts factuality in comparison to the CD sampling and its variants, and achieves state-of-the-art results for Pythia 6.9B and OPT 6.7B. Furthermore, in five commonsense QA datasets, APD is often significantly better than CD and achieves a similar effect of using a larger LLM. For example, the perplexity of APD on top of Pythia 6.9B is even lower than the perplexity of Pythia 12B in CommonsenseQA and LAMBADA.