This study investigates the potential of Large Language Models (LLMs) to simulate human group dynamics, particularly within politically charged contexts. We replicate the Wisdom of Partisan Crowds phenomenon using LLMs to role-play as Democrat and Republican personas, engaging in a structured interaction akin to human group study. Our approach evaluates how agents' responses evolve through social influence. Our key findings indicate that LLM agents role-playing detailed personas and without Chain-of-Thought (CoT) reasoning closely align with human behaviors, while having CoT reasoning hurts the alignment. However, incorporating explicit biases into agent prompts does not necessarily enhance the wisdom of partisan crowds. Moreover, fine-tuning LLMs with human data shows promise in achieving human-like behavior but poses a risk of overfitting certain behaviors. These findings show the potential and limitations of using LLM agents in modeling human group phenomena.
Adapting pre-trained language models (PLMs) for time-series text classification amidst evolving domain shifts (EDS) is critical for maintaining accuracy in applications like stance detection. This study benchmarks the effectiveness of evolving domain adaptation (EDA) strategies, notably self-training, domain-adversarial training, and domain-adaptive pretraining, with a focus on an incremental self-training method. Our analysis across various datasets reveals that this incremental method excels at adapting PLMs to EDS, outperforming traditional domain adaptation techniques. These findings highlight the importance of continually updating PLMs to ensure their effectiveness in real-world applications, paving the way for future research into PLM robustness against the natural temporal evolution of language.
Accurately simulating human opinion dynamics is crucial for understanding a variety of societal phenomena, including polarization and the spread of misinformation. However, the agent-based models (ABMs) commonly used for such simulations lack fidelity to human behavior. We propose a new approach to simulating opinion dynamics based on populations of Large Language Models (LLMs). Our findings reveal a strong inherent bias in LLM agents towards accurate information, leading to consensus in line with scientific reality. However, this bias limits the simulation of individuals with resistant views on issues like climate change. After inducing confirmation bias through prompt engineering, we observed opinion fragmentation in line with existing agent-based research. These insights highlight the promise and limitations of LLM agents in this domain and suggest a path forward: refining LLMs with real-world discourse to better simulate the evolution of human beliefs.
Large language models (LLMs) have demonstrated great potential in the financial domain. Thus, it becomes important to assess the performance of LLMs in the financial tasks. In this work, we introduce CFBenchmark, to evaluate the performance of LLMs for Chinese financial assistant. The basic version of CFBenchmark is designed to evaluate the basic ability in Chinese financial text processing from three aspects~(\emph{i.e.} recognition, classification, and generation) including eight tasks, and includes financial texts ranging in length from 50 to over 1,800 characters. We conduct experiments on several LLMs available in the literature with CFBenchmark-Basic, and the experimental results indicate that while some LLMs show outstanding performance in specific tasks, overall, there is still significant room for improvement in basic tasks of financial text processing with existing models. In the future, we plan to explore the advanced version of CFBenchmark, aiming to further explore the extensive capabilities of language models in more profound dimensions as a financial assistant in Chinese. Our codes are released at https://github.com/TongjiFinLab/CFBenchmark.
Purpose: To determine if fine-tuned large language models (LLMs) can generate accurate, personalized impressions for whole-body PET reports. Materials and Methods: Twelve language models were trained on a corpus of PET reports using the teacher-forcing algorithm, with the report findings as input and the clinical impressions as reference. An extra input token encodes the reading physician's identity, allowing models to learn physician-specific reporting styles. Our corpus comprised 37,370 retrospective PET reports collected from our institution between 2010 and 2022. To identify the best LLM, 30 evaluation metrics were benchmarked against quality scores from two nuclear medicine (NM) physicians, with the most aligned metrics selecting the model for expert evaluation. In a subset of data, model-generated impressions and original clinical impressions were assessed by three NM physicians according to 6 quality dimensions and an overall utility score (5-point scale). Each physician reviewed 12 of their own reports and 12 reports from other physicians. Bootstrap resampling was used for statistical analysis. Results: Of all evaluation metrics, domain-adapted BARTScore and PEGASUSScore showed the highest Spearman's rho correlations (0.568 and 0.563) with physician preferences. Based on these metrics, the fine-tuned PEGASUS model was selected as the top LLM. When physicians reviewed PEGASUS-generated impressions in their own style, 89% were considered clinically acceptable, with a mean utility score of 4.08/5. Physicians rated these personalized impressions as comparable in overall utility to the impressions dictated by other physicians (4.03, P=0.41). Conclusion: Personalized impressions generated by PEGASUS were clinically useful, highlighting its potential to expedite PET reporting.
Recent generative approaches for multi-hop question answering (QA) utilize the fusion-in-decoder method~\cite{izacard-grave-2021-leveraging} to generate a single sequence output which includes both a final answer and a reasoning path taken to arrive at that answer, such as passage titles and key facts from those passages. While such models can lead to better interpretability and high quantitative scores, they often have difficulty accurately identifying the passages corresponding to key entities in the context, resulting in incorrect passage hops and a lack of faithfulness in the reasoning path. To address this, we propose a single-sequence prediction method over a local reasoning graph (\model)\footnote{Code/Models will be released at \url{https://github.com/gowtham1997/SeqGraph}} that integrates a graph structure connecting key entities in each context passage to relevant subsequent passages for each question. We use a graph neural network to encode this graph structure and fuse the resulting representations into the entity representations of the model. Our experiments show significant improvements in answer exact-match/F1 scores and faithfulness of grounding in the reasoning path on the HotpotQA dataset and achieve state-of-the-art numbers on the Musique dataset with only up to a 4\% increase in model parameters.
Recent years have witnessed impressive results of pre-trained vision-language models on knowledge-intensive tasks such as visual question answering (VQA). Despite the recent advances in VQA, existing methods mainly adopt a discriminative formulation that predicts answers within a pre-defined label set, leading to easy overfitting on low-resource domains with limited labeled data (e.g., medicine) and poor generalization under domain shift to another dataset. To tackle this limitation, we propose a novel generative model enhanced by multimodal prompt retrieval (MPR) that integrates retrieved prompts and multimodal features to generate answers in free text. Our generative model enables rapid zero-shot dataset adaptation to unseen data distributions and open-set answer labels across datasets. Our experiments on medical VQA tasks show that MPR outperforms its non-retrieval counterpart by up to 30% accuracy points in a few-shot domain adaptation setting.
Traditional neural machine translation (NMT) systems often fail to translate sentences that contain culturally specific information. Most previous NMT methods have incorporated external cultural knowledge during training, which requires fine-tuning on low-frequency items specific to the culture. Recent in-context learning utilizes lightweight prompts to guide large language models (LLMs) to perform machine translation, however, whether such an approach works in terms of injecting culture awareness into machine translation remains unclear. To this end, we introduce a new data curation pipeline to construct a culturally relevant parallel corpus, enriched with annotations of cultural-specific entities. Additionally, we design simple but effective prompting strategies to assist this LLM-based translation. Extensive experiments show that our approaches can largely help incorporate cultural knowledge into LLM-based machine translation, outperforming traditional NMT systems in translating cultural-specific sentences.
Out-of-distribution (OOD) detection is a critical task for reliable predictions over text. Fine-tuning with pre-trained language models has been a de facto procedure to derive OOD detectors with respect to in-distribution (ID) data. Despite its common use, the understanding of the role of fine-tuning and its necessity for OOD detection is largely unexplored. In this paper, we raise the question: is fine-tuning necessary for OOD detection? We present a study investigating the efficacy of directly leveraging pre-trained language models for OOD detection, without any model fine-tuning on the ID data. We compare the approach with several competitive fine-tuning objectives, and offer new insights under various types of distributional shifts. Extensive evaluations on 8 diverse ID-OOD dataset pairs demonstrate near-perfect OOD detection performance (with 0% FPR95 in many cases), strongly outperforming its fine-tuned counterparts. We show that using distance-based detection methods, pre-trained language models are near-perfect OOD detectors when the distribution shift involves a domain change. Furthermore, we study the effect of fine-tuning on OOD detection and identify how to balance ID accuracy with OOD detection performance. Our code is publically available at https://github.com/Uppaal/lm-ood.
Recently, RGB-Thermal based perception has shown significant advances. Thermal information provides useful clues when visual cameras suffer from poor lighting conditions, such as low light and fog. However, how to effectively fuse RGB images and thermal data remains an open challenge. Previous works involve naive fusion strategies such as merging them at the input, concatenating multi-modality features inside models, or applying attention to each data modality. These fusion strategies are straightforward yet insufficient. In this paper, we propose a novel fusion method named Explicit Attention-Enhanced Fusion (EAEF) that fully takes advantage of each type of data. Specifically, we consider the following cases: i) both RGB data and thermal data, ii) only one of the types of data, and iii) none of them generate discriminative features. EAEF uses one branch to enhance feature extraction for i) and iii) and the other branch to remedy insufficient representations for ii). The outputs of two branches are fused to form complementary features. As a result, the proposed fusion method outperforms state-of-the-art by 1.6\% in mIoU on semantic segmentation, 3.1\% in MAE on salient object detection, 2.3\% in mAP on object detection, and 8.1\% in MAE on crowd counting. The code is available at https://github.com/FreeformRobotics/EAEFNet.