This study examines the impact of AI on human false memories -- recollections of events that did not occur or deviate from actual occurrences. It explores false memory induction through suggestive questioning in Human-AI interactions, simulating crime witness interviews. Four conditions were tested: control, survey-based, pre-scripted chatbot, and generative chatbot using a large language model (LLM). Participants (N=200) watched a crime video, then interacted with their assigned AI interviewer or survey, answering questions including five misleading ones. False memories were assessed immediately and after one week. Results show the generative chatbot condition significantly increased false memory formation, inducing over 3 times more immediate false memories than the control and 1.7 times more than the survey method. 36.4% of users' responses to the generative chatbot were misled through the interaction. After one week, the number of false memories induced by generative chatbots remained constant. However, confidence in these false memories remained higher than the control after one week. Moderating factors were explored: users who were less familiar with chatbots but more familiar with AI technology, and more interested in crime investigations, were more susceptible to false memories. These findings highlight the potential risks of using advanced AI in sensitive contexts, like police interviews, emphasizing the need for ethical considerations.
The ARR Responsible NLP Research checklist website states that the "checklist is designed to encourage best practices for responsible research, addressing issues of research ethics, societal impact and reproducibility." Answering the questions is an opportunity for authors to reflect on their work and make sure any shared scientific assets follow best practices. Ideally, considering the checklist before submission can favorably impact the writing of a research paper. However, the checklist is often filled out at the last moment. In this work, we introduce ACLReady, a retrieval-augmented language model application that can be used to empower authors to reflect on their work and assist authors with the ACL checklist. To test the effectiveness of the system, we conducted a qualitative study with 13 users which shows that 92% of users found the application useful and easy to use as well as 77% of the users found that the application provided the information they expected. Our code is publicly available under the CC BY-NC 4.0 license on GitHub.
Customers reach out to online live chat agents with various intents, such as asking about product details or requesting a return. In this paper, we propose the problem of predicting user intent from browsing history and address it through a two-stage approach. The first stage classifies a user's browsing history into high-level intent categories. Here, we represent each browsing history as a text sequence of page attributes and use the ground-truth class labels to fine-tune pretrained Transformers. The second stage provides a large language model (LLM) with the browsing history and predicted intent class to generate fine-grained intents. For automatic evaluation, we use a separate LLM to judge the similarity between generated and ground-truth intents, which closely aligns with human judgments. Our two-stage approach yields significant performance gains compared to generating intents without the classification stage.
LLM (large language model) practitioners commonly notice that outputs can vary for the same inputs under settings expected to be deterministic. Yet the questions of how pervasive this is, and with what impact on results, have not to our knowledge been systematically investigated. We investigate non-determinism in five LLMs configured to be deterministic when applied to eight common tasks in across 10 runs, in both zero-shot and few-shot settings. We see accuracy variations up to 15% across naturally occurring runs with a gap of best possible performance to worst possible performance up to 70%. In fact, none of the LLMs consistently delivers repeatable accuracy across all tasks, much less identical output strings. Sharing preliminary results with insiders has revealed that non-determinism perhaps essential to the efficient use of compute resources via co-mingled data in input buffers so this issue is not going away anytime soon. To better quantify our observations, we introduce metrics focused on quantifying determinism, TARr@N for the total agreement rate at N runs over raw output, and TARa@N for total agreement rate of parsed-out answers. Our code and data are publicly available at https://github.com/breckbaldwin/llm-stability.
Enabling Large Language Models (LLMs) to generate citations in Question-Answering (QA) tasks is an emerging paradigm aimed at enhancing the verifiability of their responses when LLMs are utilizing external references to generate an answer. However, there is currently no unified framework to standardize and fairly compare different citation generation methods, leading to difficulties in reproducing different methods and a comprehensive assessment. To cope with the problems above, we introduce \name, an open-source and modular toolkit designed to facilitate the implementation and evaluation of existing citation generation methods, while also fostering the development of new approaches to improve citation quality in LLM outputs. This tool is highly extensible, allowing users to utilize 4 main modules and 14 components to construct a pipeline, evaluating an existing method or innovative designs. Our experiments with two state-of-the-art LLMs and 11 citation generation baselines demonstrate varying strengths of different modules in answer accuracy and citation quality improvement, as well as the challenge of enhancing granularity. Based on our analysis of the effectiveness of components, we propose a new method, self-RAG \snippet, obtaining a balanced answer accuracy and citation quality. Citekit is released at https://github.com/SjJ1017/Citekit.
Mainframe operating systems, despite their inception in the 1940s, continue to support critical sectors like finance and government. However, these systems are often viewed as outdated, requiring extensive maintenance and modernization. Addressing this challenge necessitates innovative tools that can understand and interact with legacy codebases. To this end, we introduce XMainframe, a state-of-the-art large language model (LLM) specifically designed with knowledge of mainframe legacy systems and COBOL codebases. Our solution involves the creation of an extensive data collection pipeline to produce high-quality training datasets, enhancing XMainframe's performance in this specialized domain. Additionally, we present MainframeBench, a comprehensive benchmark for assessing mainframe knowledge, including multiple-choice questions, question answering, and COBOL code summarization. Our empirical evaluations demonstrate that XMainframe consistently outperforms existing state-of-the-art LLMs across these tasks. Specifically, XMainframe achieves 30% higher accuracy than DeepSeek-Coder on multiple-choice questions, doubles the BLEU score of Mixtral-Instruct 8x7B on question answering, and scores six times higher than GPT-3.5 on COBOL summarization. Our work highlights the potential of XMainframe to drive significant advancements in managing and modernizing legacy systems, thereby enhancing productivity and saving time for software developers.
The remarkable multimodal capabilities and interactive experience of GPT-4o underscore their necessity in practical applications, yet open-source models rarely excel in both areas. In this paper, we introduce VITA, the first-ever open-source Multimodal Large Language Model (MLLM) adept at simultaneous processing and analysis of Video, Image, Text, and Audio modalities, and meanwhile has an advanced multimodal interactive experience. Starting from Mixtral 8x7B as a language foundation, we expand its Chinese vocabulary followed by bilingual instruction tuning. We further endow the language model with visual and audio capabilities through two-stage multi-task learning of multimodal alignment and instruction tuning. VITA demonstrates robust foundational capabilities of multilingual, vision, and audio understanding, as evidenced by its strong performance across a range of both unimodal and multimodal benchmarks. Beyond foundational capabilities, we have made considerable progress in enhancing the natural multimodal human-computer interaction experience. VITA is the first step for the open-source community to explore the seamless integration of multimodal understanding and interaction. While there is still lots of work to be done on VITA to get close to close-source counterparts, we hope that its role as a pioneer can serve as a cornerstone for subsequent research. Project Page: https://vita-home.github.io.
Language model continual learning (CL) has recently attracted significant interest for its ability to adapt large language models (LLMs) to dynamic real-world scenarios without retraining. A major challenge in this domain is catastrophic forgetting, where models lose previously acquired knowledge upon learning new tasks. Existing approaches commonly utilize multiple parameter-efficient fine-tuning (PEFT) blocks to acquire task-specific knowledge, yet these methods are inefficient and fail to leverage potential knowledge transfer across tasks. In this paper, we introduce a novel CL framework for language models, named Knowledge Identification and Fusion (KIF), which boosts knowledge transfer without depending on memory replay. KIF initially segregates the model into 'skill units' based on parameter dependencies, allowing for more precise control. Subsequently, it employs a novel group-wise knowledge identification technique to ascertain the importance distribution of skill units for a new task. By comparing this importance distribution with those from previous tasks, we implement a fine-grained knowledge fusion strategy that retains task-specific knowledge, thereby preventing forgetting, and updates task-shared knowledge, which facilitates bi-directional knowledge transfer. As a result, KIF achieves an optimal balance between retaining prior knowledge and excelling in new tasks. KIF also demonstrates strong generalizability, making it suitable for various base models and adaptable to PEFT methods like LoRA. Furthermore, it offers notable extensibility, supporting enhancements through integration with memory replay techniques. Comprehensive experiments conducted on two CL benchmarks, involving models ranging from 220M to 7B parameters, affirm the effectiveness of KIF and its variants across different settings.
Accurate survival prediction in radiotherapy (RT) is critical for optimizing treatment decisions. This study developed and validated the RT-Surv framework, which integrates general-domain, open-source large language models (LLMs) to structure unstructured electronic health records alongside structured clinical data. Using data from 34,276 patients and an external cohort of 852, the framework successfully transformed unstructured clinical information into structured formats. Incorporating LLM-structured clinical features improved the concordance index from 0.779 to 0.842 during external validation, demonstrating a significant performance enhancement. Key LLM-structured features, such as disease extent, general condition, and RT purpose, showed high predictive importance and aligned closely with statistically significant predictors identified through conventional statistical analyses, thereby improving model interpretability. Furthermore, the framework enhanced risk stratification, enabling more distinct differentiation among low-, intermediate-, and high-risk groups (p < 0.001) using LLM-structured clinical features. These findings highlight the potential of LLMs to convert unstructured data into actionable insights, improving predictive modeling and patient outcomes in clinics.
Visual Spatial Description (VSD) aims to generate texts that describe the spatial relationships between objects within images. Traditional visual spatial relationship classification (VSRC) methods typically output the spatial relationship between two objects in an image, often neglecting world knowledge and lacking general language capabilities. In this paper, we propose a Large Language-and-Vision Assistant for Visual Spatial Description, named LLaVA-VSD, which is designed for the classification, description, and open-ended description of visual spatial relationships. Specifically, the model first constructs a VSD instruction-following dataset using given figure-caption pairs for the three tasks. It then employs LoRA to fine-tune a Large Language and Vision Assistant for VSD, which has 13 billion parameters and supports high-resolution images. Finally, a large language model (Qwen-2) is used to refine the generated sentences, enhancing their diversity and accuracy. LLaVA-VSD demonstrates excellent multimodal conversational capabilities and can follow open-ended instructions to assist with inquiries about object relationships in images.
Active learning (AL) aims to enhance model performance by selectively collecting highly informative data, thereby minimizing annotation costs. However, in practical scenarios, unlabeled data may contain out-of-distribution (OOD) samples, leading to wasted annotation costs if data is incorrectly selected. Recent research has explored methods to apply AL to open-set data, but these methods often require or incur unavoidable cost losses to minimize them. To address these challenges, we propose a novel selection strategy, CLIPN for AL (CLIPNAL), which minimizes cost losses without requiring OOD samples. CLIPNAL sequentially evaluates the purity and informativeness of data. First, it utilizes a pre-trained vision-language model to detect and exclude OOD data by leveraging linguistic and visual information of in-distribution (ID) data without additional training. Second, it selects highly informative data from the remaining ID data, and then the selected samples are annotated by human experts. Experimental results on datasets with various open-set conditions demonstrate that CLIPNAL achieves the lowest cost loss and highest performance across all scenarios. Code is available at https://github.com/DSBA-Lab/OpenAL.
In this study, we present an innovative fusion of language models and query analysis techniques to unlock cognition in artificial intelligence. The introduced open-source AI system seamlessly integrates a Chess engine with a language model, enabling it to predict moves and provide strategic explanations. Leveraging a vector database to achieve retrievable answer generation, our AI system elucidates its decision-making process, bridging the gap between raw computation and human-like understanding. Our choice of Chess as the demonstration environment underscores the versatility of our approach. Beyond Chess, our system holds promise for diverse applications, from medical diagnostics to financial forecasting. Our AI system is available at https://github.com/TheOpenSI/CoSMIC.git
Retrieval augmented generation (RAG) is a process where a large language model (LLM) retrieves useful information from a database and then generates the responses. It is becoming popular in enterprise settings for daily business operations. For example, Copilot for Microsoft 365 has accumulated millions of businesses. However, the security implications of adopting such RAG-based systems are unclear. In this paper, we introduce ConfusedPilot, a class of security vulnerabilities of RAG systems that confuse Copilot and cause integrity and confidentiality violations in its responses. First, we investigate a vulnerability that embeds malicious text in the modified prompt in RAG, corrupting the responses generated by the LLM. Second, we demonstrate a vulnerability that leaks secret data, which leverages the caching mechanism during retrieval. Third, we investigate how both vulnerabilities can be exploited to propagate misinformation within the enterprise and ultimately impact its operations, such as sales and manufacturing. We also discuss the root cause of these attacks by investigating the architecture of a RAG-based system. This study highlights the security vulnerabilities in today's RAG-based systems and proposes design guidelines to secure future RAG-based systems.
Multi-modal Large Language Models (MLLMs) have demonstrated remarkable capabilities in executing instructions for a variety of single-image tasks. Despite this progress, significant challenges remain in modeling long image sequences. In this work, we introduce the versatile multi-modal large language model, mPLUG-Owl3, which enhances the capability for long image-sequence understanding in scenarios that incorporate retrieved image-text knowledge, interleaved image-text, and lengthy videos. Specifically, we propose novel hyper attention blocks to efficiently integrate vision and language into a common language-guided semantic space, thereby facilitating the processing of extended multi-image scenarios. Extensive experimental results suggest that mPLUG-Owl3 achieves state-of-the-art performance among models with a similar size on single-image, multi-image, and video benchmarks. Moreover, we propose a challenging long visual sequence evaluation named Distractor Resistance to assess the ability of models to maintain focus amidst distractions. Finally, with the proposed architecture, mPLUG-Owl3 demonstrates outstanding performance on ultra-long visual sequence inputs. We hope that mPLUG-Owl3 can contribute to the development of more efficient and powerful multimodal large language models.
In this work, we use language modeling to investigate the factors that influence code-switching. Code-switching occurs when a speaker alternates between one language variety (the primary language) and another (the secondary language), and is widely observed in multilingual contexts. Recent work has shown that code-switching is often correlated with areas of high information load in the primary language, but it is unclear whether high primary language load only makes the secondary language relatively easier to produce at code-switching points (speaker-driven code-switching), or whether code-switching is additionally used by speakers to signal the need for greater attention on the part of listeners (audience-driven code-switching). In this paper, we use bilingual Chinese-English online forum posts and transcripts of spontaneous Chinese-English speech to replicate prior findings that high primary language (Chinese) information load is correlated with switches to the secondary language (English). We then demonstrate that the information load of the English productions is even higher than that of meaning equivalent Chinese alternatives, and these are therefore not easier to produce, providing evidence of audience-driven influences in code-switching at the level of the communication channel, not just at the sociolinguistic level, in both writing and speech.
Controlling the format of outputs generated by large language models (LLMs) is a critical functionality in various applications. Current methods typically employ constrained decoding with rule-based automata or fine-tuning with manually crafted format instructions, both of which struggle with open-domain format requirements. To address this limitation, we introduce a novel framework for controlled generation in LLMs, leveraging user-provided, one-shot QA pairs. This study investigates LLMs' capabilities to follow open-domain, one-shot constraints and replicate the format of the example answers. We observe that this is a non-trivial problem for current LLMs. We also develop a dataset collection methodology for supervised fine-tuning that enhances the open-domain format control of LLMs without degrading output quality, as well as a benchmark on which we evaluate both the helpfulness and format correctness of LLM outputs. The resulting datasets, named OIFC-SFT, along with the related code, will be made publicly available at https://github.com/cofe-ai/OIFC.
This study investigates how BERT processes and represents Argument Structure Constructions (ASCs), extending previous LSTM analyses. Using a dataset of 2000 sentences across four ASC types (transitive, ditransitive, caused-motion, resultative), we analyzed BERT's token embeddings across 12 layers. Visualizations with MDS and t-SNE and clustering quantified by Generalized Discrimination Value (GDV) were used. Feedforward classifiers (probes) predicted construction categories from embeddings. CLS token embeddings clustered best in layers 2-4, decreased in intermediate layers, and slightly increased in final layers. DET and SUBJ embeddings showed consistent clustering in intermediate layers, VERB embeddings increased in clustering from layer 1 to 12, and OBJ embeddings peaked in layer 10. Probe accuracies indicated low construction information in layer 1, with over 90 percent accuracy from layer 2 onward, revealing latent construction information beyond GDV clustering. Fisher Discriminant Ratio (FDR) analysis of attention weights showed OBJ tokens were crucial for differentiating ASCs, followed by VERB and DET tokens. SUBJ, CLS, and SEP tokens had insignificant FDR scores. This study highlights BERT's layered processing of linguistic constructions and its differences from LSTMs. Future research will compare these findings with neuroimaging data to understand the neural correlates of ASC processing. This research underscores neural language models' potential to mirror linguistic processing in the human brain, offering insights into the computational and neural mechanisms underlying language understanding.
To ensure that math curriculum is grade-appropriate and aligns with critical skills or concepts in accordance with educational standards, pedagogical experts can spend months carefully reviewing published math problems. Drawing inspiration from this process, our work presents a novel angle for evaluating language models' (LMs) mathematical abilities, by investigating whether they can discern skills and concepts enabled by math content. We contribute two datasets: one consisting of 385 fine-grained descriptions of K-12 math skills and concepts, or standards, from Achieve the Core (ATC), and another of 9.9K math problems labeled with these standards (MathFish). We develop two tasks for evaluating LMs' abilities to assess math problems: (1) verifying whether a problem aligns with a given standard, and (2) tagging a problem with all aligned standards. Working with experienced teachers, we find that LMs struggle to tag and verify standards linked to problems, and instead predict labels that are close to ground truth, but differ in subtle ways. We also show that LMs often generate problems that do not fully align with standards described in prompts, suggesting the need for careful scrutiny on use cases involving LMs for generating curricular materials. Finally, we categorize problems in GSM8k using math standards, allowing us to better understand why some problems are more difficult to solve for models than others.
Current language models demonstrate remarkable proficiency in text generation. However, for many applications it is desirable to control attributes, such as sentiment, or toxicity, of the generated language -- ideally tailored towards each specific use case and target audience. For auto-regressive language models, existing guidance methods are prone to decoding errors that cascade during generation and degrade performance. In contrast, text diffusion models can easily be guided with, for example, a simple linear sentiment classifier -- however they do suffer from significantly higher perplexity than auto-regressive alternatives. In this paper we use a guided diffusion model to produce a latent proposal that steers an auto-regressive language model to generate text with desired properties. Our model inherits the unmatched fluency of the auto-regressive approach and the plug-and-play flexibility of diffusion. We show that it outperforms previous plug-and-play guidance methods across a wide range of benchmark data sets. Further, controlling a new attribute in our framework is reduced to training a single logistic regression classifier.
Pretrained language model (PLM) hidden states are frequently employed as contextual word embeddings (CWE): high-dimensional representations that encode semantic information given linguistic context. Across many areas of computational linguistics research, similarity between CWEs is interpreted as semantic similarity. However, it remains unclear exactly what information is encoded in PLM hidden states. We investigate this practice by probing PLM representations using minimal orthographic noise. We expect that if CWEs primarily encode semantic information, a single character swap in the input word will not drastically affect the resulting representation,given sufficient linguistic context. Surprisingly, we find that CWEs generated by popular PLMs are highly sensitive to noise in input data, and that this sensitivity is related to subword tokenization: the fewer tokens used to represent a word at input, the more sensitive its corresponding CWE. This suggests that CWEs capture information unrelated to word-level meaning and can be manipulated through trivial modifications of input data. We conclude that these PLM-derived CWEs may not be reliable semantic proxies, and that caution is warranted when interpreting representational similarity