Xinpeng Wang

Xinpeng Wang, William Cao, Andrew Gordon Wilson et al.

Recent studies on hallucination detection have shown that hallucination-related signals are more strongly encoded in intermediate layers than in the final layer of large language models (LLMs). Although a growing body of work has sought to exploit this property for hallucination detection, how to automate the selection of high-performing layers remains underexplored, and principled methods for this purpose are still lacking. To address this gap, we first propose several hypotheses for why such signals emerge in intermediate layers and evaluate corresponding criteria for automatic layer selection across diverse LLM architectures, scales, and tasks, covering both question answering and summarization hallucination detection benchmarks. However, we find that none of these criteria consistently delivers satisfactory performance. We therefore propose a new selection criterion, First Effective Peak of Intrinsic Dimension (FEPoID), which consistently identify optimal or near-optimal layers and outperforms both the aforementioned criteria and existing hallucination detection baselines. FEPoID is training-free and incurs negligible computational overhead. In addition, we study the generation behaviors of LLMs and introduce a simple yet effective truncation strategy, which further amplifies hallucination-related signals and substantially improves overall detection performance. Code is publicly available at https://github.com/DesoloYw/Automatic-Layer-Selection-for-Hallucination-Detection.git

Songtao Wang, Quang Hieu Pham, Fangcong Yin et al.

Reinforcement learning with verifiable rewards (RLVR) typically optimizes for outcome rewards without imposing constraints on intermediate reasoning. This leaves training susceptible to reward hacking, where models exploit loopholes (e.g., spurious patterns in training data) in the reward function to achieve high scores without solving the intended task. These reward-hacking behaviors are often implicit, as the intermediate chain-of-thought (CoT) may appear plausible on the surface, limiting the effectiveness of purely text-based monitoring. We propose Gradient Fingerprint (GRIFT), a method for detecting reward hacking using models' internal computations. Given a prompt and a model-generated CoT, GRIFT computes gradients of the CoT conditioned on the prompt and compresses them into a compact representation, which is then used to assess whether the CoT reflects reward hacking behavior. Across verifiable reasoning benchmarks spanning math, code, and logical reasoning, GRIFT substantially outperforms strong baselines, including CoT Monitor and TRACE, achieving over 25% relative improvement in detecting reward hacking behavior. Moreover, integrating GRIFT into the rejection fine-tuning pipeline for reasoning tasks reduces reward hacking and improves performance on the true task objective. Our results highlight a promising direction of leveraging gradient level representations for assessing the quality of CoT reasoning traces. Our code is available at: https://github.com/songtao-x/reward_hack.

Xinpeng Wang, Han Jiang, Zhihua Wei et al.

Story generation has emerged as an interesting yet challenging NLP task in recent years. Some existing studies aim at generating fluent and coherent stories from keywords and outlines; while others attempt to control the global features of the story, such as emotion, style and topic. However, these works focus on coarse-grained control on the story, neglecting control on the details of the story, which is also crucial for the task. To fill the gap, this paper proposes a model for fine-grained control on the story, which allows the generation of customized stories with characters, corresponding actions and emotions arbitrarily assigned. Extensive experimental results on both automatic and human manual evaluations show the superiority of our method. It has strong controllability to generate stories according to the fine-grained personalized guidance, unveiling the effectiveness of our methodology. Our code is available at https://github.com/victorup/CHAE.

Feifei Xu, Shanlin Zhou, Xinpeng Wang et al.

Open-domain multi-turn conversations normally face the challenges of how to enrich and expand the content of the conversation. Recently, many approaches based on external knowledge are proposed to generate rich semantic and information conversation. Two types of knowledge have been studied for knowledge-aware open-domain dialogue generation: structured triples from knowledge graphs and unstructured texts from documents. To take both advantages of abundant unstructured latent knowledge in the documents and the information expansion capabilities of the structured knowledge graph, this paper presents a new dialogue generation model, Dynamic Multi-form Knowledge Fusion based Open-domain Chatt-ing Machine (DMKCM).In particular, DMKCM applies an indexed text (a virtual Knowledge Base) to locate relevant documents as 1st hop and then expands the content of the dialogue and its 1st hop using a commonsense knowledge graph to get apposite triples as 2nd hop. To merge these two forms of knowledge into the dialogue effectively, we design a dynamic virtual knowledge selector and a controller that help to enrich and expand knowledge space. Moreover, DMKCM adopts a novel dynamic knowledge memory module that effectively uses historical reasoning knowledge to generate better responses. Experimental results indicate the effectiveness of our method in terms of dialogue coherence and informativeness.

Xinpeng Wang, Barbara Plank

Label aggregation such as majority voting is commonly used to resolve annotator disagreement in dataset creation. However, this may disregard minority values and opinions. Recent studies indicate that learning from individual annotations outperforms learning from aggregated labels, though they require a considerable amount of annotation. Active learning, as an annotation cost-saving strategy, has not been fully explored in the context of learning from disagreement. We show that in the active learning setting, a multi-head model performs significantly better than a single-head model in terms of uncertainty estimation. By designing and evaluating acquisition functions with annotator-specific heads on two datasets, we show that group-level entropy works generally well on both datasets. Importantly, it achieves performance in terms of both prediction and uncertainty estimation comparable to full-scale training from disagreement, while saving up to 70% of the annotation budget.

Han Jiang, Rui Wang, Zhihua Wei et al.

Opinion summarization is expected to digest larger review sets and provide summaries from different perspectives. However, most existing solutions are deficient in epitomizing extensive reviews and offering opinion summaries from various angles due to the lack of designs for information selection. To this end, we propose SUBSUMM, a supervised summarization framework for large-scale multi-perspective opinion summarization. SUBSUMM consists of a review sampling strategy set and a two-stage training scheme. The sampling strategies take sentiment orientation and contrastive information value into consideration, with which the review subsets from different perspectives and quality levels can be selected. Subsequently, the summarizer is encouraged to learn from the sub-optimal and optimal subsets successively in order to capitalize on the massive input. Experimental results on AmaSum and Rotten Tomatoes datasets demonstrate that SUBSUMM is adept at generating pros, cons, and verdict summaries from hundreds of input reviews. Furthermore, our in-depth analysis verifies that the advanced selection of review subsets and the two-stage training scheme are vital to boosting the summarization performance.

Xinpeng Wang, Yongxin Guo, Xiaoying Tang

Domain Generalization (DG) aims to train models that can effectively generalize to unseen domains. However, in the context of Federated Learning (FL), where clients collaboratively train a model without directly sharing their data, most existing DG algorithms are not directly applicable to the FL setting due to privacy constraints, as well as the limited data quantity and domain diversity at each client. To tackle these challenges, we propose FedCCRL, a lightweight federated domain generalization method that significantly improves the model's generalization ability while preserving privacy and ensuring computational and communication efficiency. Specifically, FedCCRL comprises two principal modules: the first is a cross-client feature extension module, which increases local domain diversity via cross-client domain transfer and domain-invariant feature perturbation; the second is a representation and prediction dual-stage alignment module, which enables the model to effectively capture domain-invariant features. Extensive experimental results demonstrate that FedCCRL achieves the state-of-the-art performance on the PACS, OfficeHome and miniDomainNet datasets across FL settings of varying numbers of clients. Code is available at https://github.com/sanphouwang/fedccrl

Jian Lan, Zhicheng Liu, Xinpeng Wang et al.

The ability to derive precise spatial and physical insights is a cornerstone of vision-language models (VLMs), yet their poor performances in related spatial intelligence tasks such as physical reasoning remain a fundamental barrier. The community critically lacks a scientific analysis revealing whether VLMs faithfully reach answers or plausibly make guesses. This work aims to provide a fundamental understanding of how VLMs perceive the physical world, and utilize physical laws, while assessing the reliability of model confidence. We propose NICE and FACT, a dual-diagnostic paradigm that explicitly decomposes quantitative reasoning for kinematic physics: FACT diagnoses visual fidelity, physical law comprehension, and temporal grounding. NICE studies our novel neighborhood-informed calibration method and novel metrics to evaluate and calibrate confidence reliability. Evaluated across 6 latest state-of-the-art VLMs, we uncover that models fail to identify visual preconditions or utilize necessary physical laws to reach answers. This work highlights and establishes a standardized diagnostic paradigm to guide the development of faithful, physically-grounded VLMs.

Xinpeng Wang, Bolei Ma, Chengzhi Hu et al.

The open-ended nature of language generation makes the evaluation of autoregressive large language models (LLMs) challenging. One common evaluation approach uses multiple-choice questions (MCQ) to limit the response space. The model is then evaluated by ranking the candidate answers by the log probability of the first token prediction. However, first-tokens may not consistently reflect the final response output, due to model's diverse response styles such as starting with "Sure" or refusing to answer. Consequently, MCQ evaluation is not indicative of model behaviour when interacting with users. But by how much? We evaluate how aligned first-token evaluation is with the text output along several dimensions, namely final option choice, refusal rate, choice distribution and robustness under prompt perturbation. Our results show that the two approaches are severely misaligned on all dimensions, reaching mismatch rates over 60%. Models heavily fine-tuned on conversational or safety data are especially impacted. Crucially, models remain misaligned even when we increasingly constrain prompts, i.e., force them to start with an option letter or example template. Our findings i) underscore the importance of inspecting the text output as well and ii) caution against relying solely on first-token evaluation.

Xinpeng Wang, Xiaoyuan Yi, Han Jiang et al.

Warning: this paper includes model outputs showing offensive content. Recent large-scale Visual-Language Generative Models (VLGMs) have achieved unprecedented improvement in multimodal image/text generation. However, these models might also generate toxic content, e.g., offensive text and pornography images, raising significant ethical risks. Despite exhaustive studies on toxic degeneration of language models, this problem remains largely unexplored within the context of visual-language generation. This work delves into the propensity for toxicity generation and susceptibility to toxic data across various VLGMs. For this purpose, we built ToViLaG, a dataset comprising 32K co-toxic/mono-toxic text-image pairs and 1K innocuous but evocative text that tends to stimulate toxicity. Furthermore, we propose WInToRe, a novel toxicity metric tailored to visual-language generation, which theoretically reflects different aspects of toxicity considering both input and output. On such a basis, we benchmarked the toxicity of a diverse spectrum of VLGMs and discovered that some models do more evil than expected while some are more vulnerable to infection, underscoring the necessity of VLGMs detoxification. Therefore, we develop an innovative bottleneck-based detoxification method. Our method could reduce toxicity while maintaining comparable generation quality, providing a promising initial solution to this line of research.

Xinpeng Wang, Shitong Duan, Xiaoyuan Yi et al.

Big models have achieved revolutionary breakthroughs in the field of AI, but they might also pose potential concerns. Addressing such concerns, alignment technologies were introduced to make these models conform to human preferences and values. Despite considerable advancements in the past year, various challenges lie in establishing the optimal alignment strategy, such as data cost and scalable oversight, and how to align remains an open question. In this survey paper, we comprehensively investigate value alignment approaches. We first unpack the historical context of alignment tracing back to the 1920s (where it comes from), then delve into the mathematical essence of alignment (what it is), shedding light on the inherent challenges. Following this foundation, we provide a detailed examination of existing alignment methods, which fall into three categories: Reinforcement Learning, Supervised Fine-Tuning, and In-context Learning, and demonstrate their intrinsic connections, strengths, and limitations, helping readers better understand this research area. In addition, two emerging topics, personal alignment, and multimodal alignment, are also discussed as novel frontiers in this field. Looking forward, we discuss potential alignment paradigms and how they could handle remaining challenges, prospecting where future alignment will go.

Xinpeng Wang, Chengzhi Hu, Bolei Ma et al.

Multiple choice questions (MCQs) are commonly used to evaluate the capabilities of large language models (LLMs). One common way to evaluate the model response is to rank the candidate answers based on the log probability of the first token prediction. An alternative way is to examine the text output. Prior work has shown that first token probabilities lack robustness to changes in MCQ phrasing, and that first token probabilities do not match text answers for instruction-tuned models. Therefore, in this paper, we investigate the robustness of text answers. We show that the text answers are more robust to question perturbations than the first token probabilities, when the first token answers mismatch the text answers. The difference in robustness increases as the mismatch rate becomes greater. As the mismatch reaches over 50\%, the text answer is more robust to option order changes than the debiased first token probabilities using state-of-the-art debiasing methods such as PriDe. Our findings provide further evidence for the benefits of text answer evaluation over first token probability evaluation.

Bolei Ma, Berk Yoztyurk, Anna-Carolina Haensch et al.

In recent research, large language models (LLMs) have been increasingly used to investigate public opinions. This study investigates the algorithmic fidelity of LLMs, i.e., the ability to replicate the socio-cultural context and nuanced opinions of human participants. Using open-ended survey data from the German Longitudinal Election Studies (GLES), we prompt different LLMs to generate synthetic public opinions reflective of German subpopulations by incorporating demographic features into the persona prompts. Our results show that Llama performs better than other LLMs at representing subpopulations, particularly when there is lower opinion diversity within those groups. Our findings further reveal that the LLM performs better for supporters of left-leaning parties like The Greens and The Left compared to other parties, and matches the least with the right-party AfD. Additionally, the inclusion or exclusion of specific variables in the prompts can significantly impact the models' predictions. These findings underscore the importance of aligning LLMs to more effectively model diverse public opinions while minimizing political biases and enhancing robustness in representativeness.

Shengyun Si, Xinpeng Wang, Guangyao Zhai et al.

Recent advancements in large language models (LLMs) have demonstrated that fine-tuning and human alignment can render LLMs harmless. In practice, such "harmlessness" behavior is mainly achieved by training models to reject harmful requests, such as "Explain how to burn down my neighbor's house", where the model appropriately declines to respond. However, this approach can inadvertently result in false refusal, where models reject benign queries as well, such as "Tell me how to kill a Python process". In this work, we demonstrate that prompting safety reflection before generating a response can mitigate false refusal behavior. Building on this finding, we introduce the Think-Before-Refusal (TBR) schema and conduct safety-aware instruction fine-tuning incorporating safety reflection. In an ablation study across 15 pre-trained models, we show that models fine-tuned with safety reflection significantly reduce false refusal behavior while maintaining safety and overall performance compared to those fine-tuned without safety reflection.

Xinpeng Wang, Rong Zhou, Han Xie et al.

Multimodal Federated Learning (MFL) has emerged as a promising approach for collaboratively training multimodal models across distributed clients, particularly in healthcare domains. In the context of brain imaging analysis, modality incompleteness presents a significant challenge, where some institutions may lack specific imaging modalities (e.g., PET, MRI, or CT) due to privacy concerns, device limitations, or data availability issues. While existing work typically assumes modality completeness or oversimplifies missing-modality scenarios, we simulate a more realistic setting by considering both client-level and instance-level modality incompleteness in this study. Building on this realistic simulation, we propose ClusMFL, a novel MFL framework that leverages feature clustering for cross-institutional brain imaging analysis under modality incompleteness. Specifically, ClusMFL utilizes the FINCH algorithm to construct a pool of cluster centers for the feature embeddings of each modality-label pair, effectively capturing fine-grained data distributions. These cluster centers are then used for feature alignment within each modality through supervised contrastive learning, while also acting as proxies for missing modalities, allowing cross-modal knowledge transfer. Furthermore, ClusMFL employs a modality-aware aggregation strategy, further enhancing the model's performance in scenarios with severe modality incompleteness. We evaluate the proposed framework on the ADNI dataset, utilizing structural MRI and PET scans. Extensive experimental results demonstrate that ClusMFL achieves state-of-the-art performance compared to various baseline methods across varying levels of modality incompleteness, providing a scalable solution for cross-institutional brain imaging analysis.

Xinpeng Wang, Mingyang Wang, Yihong Liu et al.

Refusal mechanisms in large language models (LLMs) are essential for ensuring safety. Recent research has revealed that refusal behavior can be mediated by a single direction in activation space, enabling targeted interventions to bypass refusals. While this is primarily demonstrated in an English-centric context, appropriate refusal behavior is important for any language, but poorly understood. In this paper, we investigate the refusal behavior in LLMs across 14 languages using PolyRefuse, a multilingual safety dataset created by translating malicious and benign English prompts into these languages. We uncover the surprising cross-lingual universality of the refusal direction: a vector extracted from English can bypass refusals in other languages with near-perfect effectiveness, without any additional fine-tuning. Even more remarkably, refusal directions derived from any safety-aligned language transfer seamlessly to others. We attribute this transferability to the parallelism of refusal vectors across languages in the embedding space and identify the underlying mechanism behind cross-lingual jailbreaks. These findings provide actionable insights for building more robust multilingual safety defenses and pave the way for a deeper mechanistic understanding of cross-lingual vulnerabilities in LLMs.

Qiqi Chen, Xinpeng Wang, Philipp Mondorf et al.

Tree of Thoughts (ToT) is a reasoning strategy for Large Language Models (LLMs) that employs a generator to suggest reasoning steps and a discriminator to decide which steps to implement. ToT demonstrates strong performance on reasoning tasks, often surpassing simple methods such as Input-Output (IO) prompting and Chain-of-Thought (CoT) reasoning. However, ToT does not consistently outperform such simpler methods across all models, leaving large knowledge gaps on the conditions under which ToT is most beneficial. In this paper, we analyze the roles of the generator and discriminator separately to better understand the conditions when ToT is beneficial. We find that the generator plays a more critical role than the discriminator in driving the success of ToT. Scaling the generator leads to notable improvements in ToT performance, even when using a smaller model as the discriminator, whereas scaling the discriminator with a fixed generator yields only marginal gains. Our results show that models across different scales exhibit comparable discrimination capabilities, yet differ significantly in their generative performance for ToT.

Shanlin Zhou, Xinpeng Wang, Jianxun Lian et al.

Trained on diverse human-authored texts, Large Language Models (LLMs) unlocked the potential for Creative Natural Language Generation (CNLG), benefiting various applications like advertising and storytelling. Nevertheless, CNLG still remains difficult due to two main challenges. (1) Multi-objective flexibility: user requirements are often personalized, fine-grained, and pluralistic, which LLMs struggle to satisfy simultaneously; (2) Interpretive complexity: beyond generation, creativity also involves understanding and interpreting implicit meaning to enhance users' perception. These challenges significantly limit current methods, especially in short-form text generation, in generating creative and insightful content. To address this, we focus on Chinese baby naming, a representative short-form CNLG task requiring adherence to explicit user constraints (e.g., length, semantics, anthroponymy) while offering meaningful aesthetic explanations. We propose NAMeGEn, a novel multi-agent optimization framework that iteratively alternates between objective extraction, name generation, and evaluation to meet diverse requirements and generate accurate explanations. To support this task, we further construct a classical Chinese poetry corpus with 17k+ poems to enhance aesthetics, and introduce CBNames, a new benchmark with tailored metrics. Extensive experiments demonstrate that NAMeGEn effectively generates creative names that meet diverse, personalized requirements while providing meaningful explanations, outperforming six baseline methods spanning various LLM backbones without any training.

Xinpeng Wang, Nitish Joshi, Barbara Plank et al.

Reward hacking, where a reasoning model exploits loopholes in a reward function to achieve high rewards without solving the intended task, poses a significant threat. This behavior may be explicit, i.e. verbalized in the model's chain-of-thought (CoT), or implicit, where the CoT appears benign thus bypasses CoT monitors. To detect implicit reward hacking, we propose TRACE (Truncated Reasoning AUC Evaluation). Our key observation is that hacking occurs when exploiting the loophole is easier than solving the actual task. This means that the model is using less 'effort' than required to achieve high reward. TRACE quantifies effort by measuring how early a model's reasoning becomes sufficient to obtain the reward. We progressively truncate a model's CoT at various lengths, force the model to answer, and estimate the expected reward at each cutoff. A hacking model, which takes a shortcut, will achieve a high expected reward with only a small fraction of its CoT, yielding a large area under the accuracy-vs-length curve. TRACE achieves over 65% gains over our strongest 72B CoT monitor in math reasoning, and over 30% gains over a 32B monitor in coding. We further show that TRACE can discover unknown loopholes during training. Overall, TRACE offers a scalable unsupervised approach for oversight where current monitoring methods prove ineffective.

Beiduo Chen, Xinpeng Wang, Siyao Peng et al.

Human label variation (HLV) is a valuable source of information that arises when multiple human annotators provide different labels for valid reasons. In Natural Language Inference (NLI) earlier approaches to capturing HLV involve either collecting annotations from many crowd workers to represent human judgment distribution (HJD) or use expert linguists to provide detailed explanations for their chosen labels. While the former method provides denser HJD information, obtaining it is resource-intensive. In contrast, the latter offers richer textual information but it is challenging to scale up to many human judges. Besides, large language models (LLMs) are increasingly used as evaluators ("LLM judges") but with mixed results, and few works aim to study HJDs. This study proposes to exploit LLMs to approximate HJDs using a small number of expert labels and explanations. Our experiments show that a few explanations significantly improve LLMs' ability to approximate HJDs with and without explicit labels, thereby providing a solution to scale up annotations for HJD. However, fine-tuning smaller soft-label aware models with the LLM-generated model judgment distributions (MJDs) presents partially inconsistent results: while similar in distance, their resulting fine-tuned models and visualized distributions differ substantially. We show the importance of complementing instance-level distance measures with a global-level shape metric and visualization to more effectively evaluate MJDs against human judgment distributions.

Bolei Ma, Xinpeng Wang, Tiancheng Hu et al.

Recent advances in Large Language Models (LLMs) have sparked wide interest in validating and comprehending the human-like cognitive-behavioral traits LLMs may capture and convey. These cognitive-behavioral traits include typically Attitudes, Opinions, Values (AOVs). However, measuring AOVs embedded within LLMs remains opaque, and different evaluation methods may yield different results. This has led to a lack of clarity on how different studies are related to each other and how they can be interpreted. This paper aims to bridge this gap by providing a comprehensive overview of recent works on the evaluation of AOVs in LLMs. Moreover, we survey related approaches in different stages of the evaluation pipeline in these works. By doing so, we address the potential and challenges with respect to understanding the model, human-AI alignment, and downstream application in social sciences. Finally, we provide practical insights into evaluation methods, model enhancement, and interdisciplinary collaboration, thereby contributing to the evolving landscape of evaluating AOVs in LLMs.

Xinpeng Wang, Leonie Weissweiler, Hinrich Schütze et al.

Recently, various intermediate layer distillation (ILD) objectives have been shown to improve compression of BERT models via Knowledge Distillation (KD). However, a comprehensive evaluation of the objectives in both task-specific and task-agnostic settings is lacking. To the best of our knowledge, this is the first work comprehensively evaluating distillation objectives in both settings. We show that attention transfer gives the best performance overall. We also study the impact of layer choice when initializing the student from the teacher layers, finding a significant impact on the performance in task-specific distillation. For vanilla KD and hidden states transfer, initialisation with lower layers of the teacher gives a considerable improvement over higher layers, especially on the task of QNLI (up to an absolute percentage change of 17.8 in accuracy). Attention transfer behaves consistently under different initialisation settings. We release our code as an efficient transformer-based model distillation framework for further studies.

Xinpeng Wang, Songan Zhang, Kuan-Hui Lee et al.

It is important to build a rigorous verification and validation (V&V) process to evaluate the safety of highly automated vehicles (HAVs) before their wide deployment on public roads. In this paper, we propose an interaction-aware framework for HAV safety evaluation which is suitable for some highly-interactive driving scenarios including highway merging, roundabout entering, etc. Contrary to existing approaches where the primary other vehicle (POV) takes predetermined maneuvers, we model the POV as a game-theoretic agent. To capture a wide variety of interactions between the POV and the vehicle under test (VUT), we characterize the interactive behavior using level-k game theory and social value orientation and train a diverse set of POVs using reinforcement learning. Moreover, we propose an adaptive test case sampling scheme based on the Gaussian process regression technique to generate customized and diverse challenging cases. The highway merging is used as the example scenario. We found the proposed method is able to capture a wide range of POV behaviors and achieve better coverage of the failure modes of the VUT compared with other evaluation approaches.

Xinpeng Wang, Chandan Yeshwanth, Matthias Nießner

We address the task of indoor scene generation by generating a sequence of objects, along with their locations and orientations conditioned on a room layout. Large-scale indoor scene datasets allow us to extract patterns from user-designed indoor scenes, and generate new scenes based on these patterns. Existing methods rely on the 2D or 3D appearance of these scenes in addition to object positions, and make assumptions about the possible relations between objects. In contrast, we do not use any appearance information, and implicitly learn object relations using the self-attention mechanism of transformers. We show that our model design leads to faster scene generation with similar or improved levels of realism compared to previous methods. Our method is also flexible, as it can be conditioned not only on the room layout but also on text descriptions of the room, using only the cross-attention mechanism of transformers. Our user study shows that our generated scenes are preferred to the state-of-the-art FastSynth scenes 53.9% and 56.7% of the time for bedroom and living room scenes, respectively. At the same time, we generate a scene in 1.48 seconds on average, 20% faster than FastSynth.

Feifei Xu, Xinpeng Wang, Yunpu Ma et al.

Story generation, which aims to generate a long and coherent story automatically based on the title or an input sentence, is an important research area in the field of natural language generation. There is relatively little work on story generation with appointed emotions. Most existing works focus on using only one specific emotion to control the generation of a whole story and ignore the emotional changes in the characters in the course of the story. In our work, we aim to design an emotional line for each character that considers multiple emotions common in psychological theories, with the goal of generating stories with richer emotional changes in the characters. To the best of our knowledge, this work is first to focuses on characters' emotional lines in story generation. We present a novel model-based attention mechanism that we call SoCP (Storytelling of multi-Character Psychology). We show that the proposed model can generate stories considering the changes in the psychological state of different characters. To take into account the particularity of the model, in addition to commonly used evaluation indicators(BLEU, ROUGE, etc.), we introduce the accuracy rate of psychological state control as a novel evaluation metric. The new indicator reflects the effect of the model on the psychological state control of story characters. Experiments show that with SoCP, the generated stories follow the psychological state for each character according to both automatic and human evaluations.

Nauman Sohani, Geunseob Oh, Xinpeng Wang

We propose a novel framework to differentiate between vehicle trajectories originating from human and non-human drivers by constructing a data-driven boundary using parametric signal temporal logic (STL). Such construction allows us to evaluate the trajectories, detect rare-events, and reduce the uncertainty of driver behaviors when it assumes the form of a disturbance in control synthesis and evaluation problems. We train a classifier that separates admissible (i.e. human) examples - which arise from real-world demonstrations - and inadmissible (i.e. non-human) examples that are generated by falsifying specifications synthesized from the same real-world driving data. Proceeding in this fashion allows for finding a reasonable boundary of human behaviors exhibited in real-world driving records. The framework is demonstrated using a case study involving a human-driven vehicle approaching a signalized intersection.