PyTorchKR Papers

최신 논문

총 857편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2410.22368

Project MPG: towards a generalized performance benchmark for LLM capabilities

There exists an extremely wide array of LLM benchmarking tasks, whereas oftentimes a single number is the most actionable for decision-making, especially by non-experts. No such aggregation schema exists that is not Elo-based, which could be costly or time-consuming. Here we propose a method to aggregate performance across a general space of benchmarks, nicknamed Project "MPG," dubbed Model Performance and Goodness, additionally referencing a metric widely understood to be an important yet inaccurate and crude measure of car performance. Here, we create two numbers: a "Goodness" number (answer accuracy) and a "Fastness" number (cost or QPS). We compare models against each other and present a ranking according to our general metric as well as subdomains. We find significant agreement between the raw Pearson correlation of our scores and those of Chatbot Arena, even improving on the correlation of the MMLU leaderboard to Chatbot Arena.

arXiv:2410.19803

First-Person Fairness in Chatbots

Evaluating chatbot fairness is crucial given their rapid proliferation, yet typical chatbot tasks (e.g., resume writing, entertainment) diverge from the institutional decision-making tasks (e.g., resume screening) which have traditionally been central to discussion of algorithmic fairness. The open-ended nature and diverse use-cases of chatbots necessitate novel methods for bias assessment. This paper addresses these challenges by introducing a scalable counterfactual approach to evaluate "first-person fairness," meaning fairness toward chatbot users based on demographic characteristics. Our method employs a Language Model as a Research Assistant (LMRA) to yield quantitative measures of harmful stereotypes and qualitative analyses of demographic differences in chatbot responses. We apply this approach to assess biases in six of our language models across millions of interactions, covering sixty-six tasks in nine domains and spanning two genders and four races. Independent human annotations corroborate the LMRA-generated bias evaluations. This study represents the first large-scale fairness evaluation based on real-world chat data. We highlight that post-training reinforcement learning techniques significantly mitigate these biases. This evaluation provides a practical methodology for ongoing bias monitoring and mitigation.

arXiv:2410.20245

Improving Model Evaluation using SMART Filtering of Benchmark Datasets

One of the most challenging problems facing NLP today is evaluation. Some of the most pressing issues pertain to benchmark saturation, data contamination, and diversity in the quality of test examples. To address these concerns, we propose Selection Methodology for Accurate, Reduced, and Targeted (SMART) filtering, a novel approach to select a high-quality subset of examples from existing benchmark datasets by systematically removing less informative and less challenging examples. Our approach applies three filtering criteria, removing (i) easy examples, (ii) data-contaminated examples, and (iii) examples that are similar to each other based on distance in an embedding space. We demonstrate the effectiveness of SMART on three multiple choice QA datasets, where our methodology increases efficiency by reducing dataset size by 48\% on average, while increasing Pearson correlation with rankings from ChatBot Arena, a more open-ended human evaluation setting. Our method enables us to be more efficient, whether using SMART to make new benchmarks more challenging or to revitalize older datasets, while still preserving the relative model rankings.

arXiv:2410.19733

The Potential and Value of AI Chatbot in Personalized Cognitive Training

In recent years, the rapid aging of the global population has led to an increase in cognitive disorders, such as Alzheimer's disease, presenting significant public health challenges. Although no effective treatments currently exist to reverse Alzheimer's, prevention and early intervention, including cognitive training, are critical. This report explores the potential of AI chatbots in enhancing personalized cognitive training. We introduce ReMe, a web-based framework designed to create AI chatbots that facilitate cognitive training research, specifically targeting episodic memory tasks derived from personal life logs. By leveraging large language models, ReMe provides enhanced user-friendly, interactive, and personalized training experiences. Case studies demonstrate ReMe's effectiveness in engaging users through life recall and open-ended language puzzles, highlighting its potential to improve cognitive training design. Despite promising results, further research is needed to validate training effectiveness through large-scale studies that include cognitive ability evaluations. Overall, ReMe offers a promising approach to personalized cognitive training, utilizing AI capabilities to meet the growing demand for non-pharmacological interventions in cognitive health, with future research aiming to expand its applications and efficacy.

arXiv:2410.13886공식 코드 · Papers with Code

Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

For safety reasons, large language models (LLMs) are trained to refuse harmful user instructions, such as assisting dangerous activities. We study an open question in this work: does the desired safety refusal, typically enforced in chat contexts, generalize to non-chat and agentic use cases? Unlike chatbots, LLM agents equipped with general-purpose tools, such as web browsers and mobile devices, can directly influence the real world, making it even more crucial to refuse harmful instructions. In this work, we primarily focus on red-teaming browser agents, LLMs that manipulate information via web browsers. To this end, we introduce Browser Agent Red teaming Toolkit (BrowserART), a comprehensive test suite designed specifically for red-teaming browser agents. BrowserART is consist of 100 diverse browser-related harmful behaviors (including original behaviors and ones sourced from HarmBench [Mazeika et al., 2024] and AirBench 2024 [Zeng et al., 2024b]) across both synthetic and real websites. Our empirical study on state-of-the-art browser agents reveals that, while the backbone LLM refuses harmful instructions as a chatbot, the corresponding agent does not. Moreover, attack methods designed to jailbreak refusal-trained LLMs in the chat settings transfer effectively to browser agents. With human rewrites, GPT-4o and o1-preview-based browser agents attempted 98 and 63 harmful behaviors (out of 100), respectively. We publicly release BrowserART and call on LLM developers, policymakers, and agent developers to collaborate on improving agent safety

arXiv:2410.16385공식 코드 · Papers with Code

KatzBot: Revolutionizing Academic Chatbot for Enhanced Communication

Effective communication within universities is crucial for addressing the diverse information needs of students, alumni, and external stakeholders. However, existing chatbot systems often fail to deliver accurate, context-specific responses, resulting in poor user experiences. In this paper, we present KatzBot, an innovative chatbot powered by KatzGPT, a custom Large Language Model (LLM) fine-tuned on domain-specific academic data. KatzGPT is trained on two university-specific datasets: 6,280 sentence-completion pairs and 7,330 question-answer pairs. KatzBot outperforms established existing open source LLMs, achieving higher accuracy and domain relevance. KatzBot offers a user-friendly interface, significantly enhancing user satisfaction in real-world applications. The source code is publicly available at \url{https://github.com/AiAI-99/katzbot}.

arXiv:2410.16645

Chatting with Bots: AI, Speech Acts, and the Edge of Assertion

This paper addresses the question of whether large language model-powered chatbots are capable of assertion. According to what we call the Thesis of Chatbot Assertion (TCA), chatbots are the kinds of things that can assert, and at least some of the output produced by current-generation chatbots qualifies as assertion. We provide some motivation for TCA, arguing that it ought to be taken seriously and not simply dismissed. We also review recent objections to TCA, arguing that these objections are weighty. We thus confront the following dilemma: how can we do justice to both the considerations for and against TCA? We consider two influential responses to this dilemma - the first appeals to the notion of proxy-assertion; the second appeals to fictionalism - and argue that neither is satisfactory. Instead, reflecting on the ontogenesis of assertion, we argue that we need to make space for a category of proto-assertion. We then apply the category of proto-assertion to chatbots, arguing that treating chatbots as proto-assertors provides a satisfactory resolution to the dilemma of chatbot assertion.

arXiv:2410.15299공식 코드 · Papers with Code

Does ChatGPT Have a Poetic Style?

Generating poetry has become a popular application of LLMs, perhaps especially of OpenAI's widely-used chatbot ChatGPT. What kind of poet is ChatGPT? Does ChatGPT have its own poetic style? Can it successfully produce poems in different styles? To answer these questions, we prompt the GPT-3.5 and GPT-4 models to generate English-language poems in 24 different poetic forms and styles, about 40 different subjects, and in response to 3 different writing prompt templates. We then analyze the resulting 5.7k poems, comparing them to a sample of 3.7k poems from the Poetry Foundation and the Academy of American Poets. We find that the GPT models, especially GPT-4, can successfully produce poems in a range of both common and uncommon English-language forms in superficial yet noteworthy ways, such as by producing poems of appropriate lengths for sonnets (14 lines), villanelles (19 lines), and sestinas (39 lines). But the GPT models also exhibit their own distinct stylistic tendencies, both within and outside of these specific forms. Our results show that GPT poetry is much more constrained and uniform than human poetry, showing a strong penchant for rhyme, quatrains (4-line stanzas), iambic meter, first-person plural perspectives (we, us, our), and specific vocabulary like "heart," "embrace," "echo," and "whisper."

arXiv:2410.15572

Leveraging Retrieval-Augmented Generation for Culturally Inclusive Hakka Chatbots: Design Insights and User Perceptions

In an era where cultural preservation is increasingly intertwined with technological innovation, this study introduces a groundbreaking approach to promoting and safeguarding the rich heritage of Taiwanese Hakka culture through the development of a Retrieval-Augmented Generation (RAG)-enhanced chatbot. Traditional large language models (LLMs), while powerful, often fall short in delivering accurate and contextually rich responses, particularly in culturally specific domains. By integrating external databases with generative AI models, RAG technology bridges this gap, empowering chatbots to not only provide precise answers but also resonate deeply with the cultural nuances that are crucial for authentic interactions. This study delves into the intricate process of augmenting the chatbot's knowledge base with targeted cultural data, specifically curated to reflect the unique aspects of Hakka traditions, language, and practices. Through dynamic information retrieval, the RAG-enhanced chatbot becomes a versatile tool capable of handling complex inquiries that demand an in-depth understanding of Hakka cultural context. This is particularly significant in an age where digital platforms often dilute cultural identities, making the role of culturally aware AI systems more critical than ever. System usability studies conducted as part of our research reveal a marked improvement in both user satisfaction and engagement, highlighting the chatbot's effectiveness in fostering a deeper connection with Hakka culture. The feedback underscores the potential of RAG technology to not only enhance user experience but also to serve as a vital instrument in the broader mission of ethnic mainstreaming and cultural celebration.

arXiv:2410.13326

Comparing the Utility, Preference, and Performance of Course Material Search Functionality and Retrieval-Augmented Generation Large Language Model (RAG-LLM) AI Chatbots in Information-Seeking Tasks

Providing sufficient support for students requires substantial resources, especially considering the growing enrollment numbers. Students need help in a variety of tasks, ranging from information-seeking to requiring support with course assignments. To explore the utility of recent large language models (LLMs) as a support mechanism, we developed an LLM-powered AI chatbot that augments the answers that are produced with information from the course materials. To study the effect of the LLM-powered AI chatbot, we conducted a lab-based user study (N=14), in which the participants worked on tasks from a web software development course. The participants were divided into two groups, where one of the groups first had access to the chatbot and then to a more traditional search functionality, while another group started with the search functionality and was then given the chatbot. We assessed the participants' performance and perceptions towards the chatbot and the search functionality and explored their preferences towards the support functionalities. Our findings highlight that both support mechanisms are seen as useful and that support mechanisms work well for specific tasks, while less so for other tasks. We also observe that students tended to prefer the second support mechanism more, where students who were first given the chatbot tended to prefer the search functionality and vice versa.

arXiv:2410.12848

Prompt Engineering a Schizophrenia Chatbot: Utilizing a Multi-Agent Approach for Enhanced Compliance with Prompt Instructions

Patients with schizophrenia often present with cognitive impairments that may hinder their ability to learn about their condition. These individuals could benefit greatly from education platforms that leverage the adaptability of Large Language Models (LLMs) such as GPT-4. While LLMs have the potential to make topical mental health information more accessible and engaging, their black-box nature raises concerns about ethics and safety. Prompting offers a way to produce semi-scripted chatbots with responses anchored in instructions and validated information, but prompt-engineered chatbots may drift from their intended identity as the conversation progresses. We propose a Critical Analysis Filter for achieving better control over chatbot behavior. In this system, a team of prompted LLM agents are prompt-engineered to critically analyze and refine the chatbot's response and deliver real-time feedback to the chatbot. To test this approach, we develop an informational schizophrenia chatbot and converse with it (with the filter deactivated) until it oversteps its scope. Once drift has been observed, AI-agents are used to automatically generate sample conversations in which the chatbot is being enticed to talk about out-of-bounds topics. We manually assign to each response a compliance score that quantifies the chatbot's compliance to its instructions; specifically the rules about accurately conveying sources and being transparent about limitations. Activating the Critical Analysis Filter resulted in an acceptable compliance score (>=2) in 67.0% of responses, compared to only 8.7% when the filter was deactivated. These results suggest that a self-reflection layer could enable LLMs to be used effectively and safely in mental health platforms, maintaining adaptability while reliably limiting their scope to appropriate use cases.

arXiv:2410.13671

HEALTH-PARIKSHA: Assessing RAG Models for Health Chatbots in Real-World Multilingual Settings

Assessing the capabilities and limitations of large language models (LLMs) has garnered significant interest, yet the evaluation of multiple models in real-world scenarios remains rare. Multilingual evaluation often relies on translated benchmarks, which typically do not capture linguistic and cultural nuances present in the source language. This study provides an extensive assessment of 24 LLMs on real world data collected from Indian patients interacting with a medical chatbot in Indian English and 4 other Indic languages. We employ a uniform Retrieval Augmented Generation framework to generate responses, which are evaluated using both automated techniques and human evaluators on four specific metrics relevant to our application. We find that models vary significantly in their performance and that instruction tuned Indic models do not always perform well on Indic language queries. Further, we empirically show that factual correctness is generally lower for responses to Indic queries compared to English queries. Finally, our qualitative work shows that code-mixed and culturally relevant queries in our dataset pose challenges to evaluated models.

arXiv:2410.12444

Expanding Chatbot Knowledge in Customer Service: Context-Aware Similar Question Generation Using Large Language Models

Reliable responses of service chatbots are often achieved by employing retrieval-based methods that restrict answers to a knowledge base comprising predefined question-answer pairs (QA pairs). To accommodate potential variations in how a customer's query may be expressed, it emerges as the favored solution to augment these QA pairs with similar questions that are possibly diverse while remaining semantic consistency. This augmentation task is known as Similar Question Generation (SQG). Traditional methods that heavily rely on human efforts or rule-based techniques suffer from limited diversity or significant semantic deviation from the source question, only capable of producing a finite number of useful questions. To address these limitations, we propose an SQG approach based on Large Language Models (LLMs), capable of producing a substantial number of diverse questions while maintaining semantic consistency to the source QA pair. This is achieved by leveraging LLMs' natural language understanding capability through fine-tuning with specially designed prompts. The experiments conducted on a real customer-service dataset demonstrate that our method surpasses baseline methods by a significant margin in terms of semantic diversity. Human evaluation further confirms that integrating the answer that reflects the customer's intention is crucial for increasing the number of generated questions that meet business requirements.

arXiv:2410.11890

Online Digital Investigative Journalism using SociaLens

Media companies witnessed a significant transformation with the rise of the internet, bigdata, machine learning (ML) and AI. Recent emergence of large language models (LLM) have added another aspect to this transformation. Researchers believe that with the help of these technologies, investigative digital journalism will enter a new era. Using a smart set of data gathering and analysis tools, journalists will be able to create data driven contents and insights in unprecedented ways. In this paper, we introduce a versatile and autonomous investigative journalism tool, called {\em SociaLens}, for identifying and extracting query specific data from online sources, responding to probing queries and drawing conclusions entailed by large volumes of data using ML analytics fully autonomously. We envision its use in investigative journalism, law enforcement and social policy planning. The proposed system capitalizes on the integration of ML technology with LLMs and advanced bigdata search techniques. We illustrate the functionality of SociaLens using a focused case study on rape incidents in a developing country and demonstrate that journalists can gain nuanced insights without requiring coding expertise they might lack. SociaLens is designed as a ChatBot that is capable of contextual conversation, find and collect data relevant to queries, initiate ML tasks to respond to queries, generate textual and visual reports, all fully autonomously within the ChatBot environment.

arXiv:2410.10860공식 코드 · Papers with Code

A Recipe For Building a Compliant Real Estate Chatbot

In recent years, there has been significant effort to align large language models with human preferences. This work focuses on developing a chatbot specialized in the real estate domain, with an emphasis on incorporating compliant behavior to ensure it can be used without perpetuating discriminatory practices like steering and redlining, which have historically plagued the real estate industry in the United States. Building on prior work, we present a method for generating a synthetic general instruction-following dataset, along with safety data. Through extensive evaluations and benchmarks, we fine-tuned a llama-3-8B-instruct model and demonstrated that we can enhance it's performance significantly to match huge closed-source models like GPT-4o while making it safer and more compliant. We open-source the model, data and code to support further development and research in the community.

arXiv:2410.11079

Code-Mixer Ya Nahi: Novel Approaches to Measuring Multilingual LLMs' Code-Mixing Capabilities

Multilingual Large Language Models (LLMs) have demonstrated exceptional performance in Machine Translation (MT) tasks. However, their MT abilities in the context of code-switching (the practice of mixing two or more languages in an utterance) remain under-explored. In this paper, we introduce Rule-Based Prompting, a novel prompting technique to generate code-mixed sentences. We measure and compare the code-mixed MT abilities of 3 popular multilingual LLMs: GPT-3.5-turbo, GPT-4, and Gemini Pro across five language pairs: English-{Hindi, Bengali, Gujarati, French, Spanish} using $k$-shot prompting ($k\in\{0, 1, 10, 20\}$) and Rule-Based Prompting. Our findings suggest that though $k$-shot prompting often leads to the best results, Rule-Based prompting shows promise in generating unique code-mixed sentences that vary in their style of code-mixing. We also use $k$-shot prompting to gauge the code-mixed to English translation abilities of multilingual LLMs. For this purpose, we create a gold-standard code-mixed dataset spanning five language pairs: English-{Hindi, Bengali, Gujarati, French, Spanish}. As a real-world application of our work, we create a code-mixed chatbot.

arXiv:2410.10215

SkillAggregation: Reference-free LLM-Dependent Aggregation

Large Language Models (LLMs) are increasingly used to assess NLP tasks due to their ability to generate human-like judgments. Single LLMs were used initially, however, recent work suggests using multiple LLMs as judges yields improved performance. An important step in exploiting multiple judgements is the combination stage, aggregation. Existing methods in NLP either assign equal weight to all LLM judgments or are designed for specific tasks such as hallucination detection. This work focuses on aggregating predictions from multiple systems where no reference labels are available. A new method called SkillAggregation is proposed, which learns to combine estimates from LLM judges without needing additional data or ground truth. It extends the Crowdlayer aggregation method, developed for image classification, to exploit the judge estimates during inference. The approach is compared to a range of standard aggregation methods on HaluEval-Dialogue, TruthfulQA and Chatbot Arena tasks. SkillAggregation outperforms Crowdlayer on all tasks, and yields the best performance over all approaches on the majority of tasks.

논문 ID: 2024.10010

Enhanced MRI brain tumor detection and classification via topological data analysis and low-rank tensor decomposition

The advent of artificial intelligence in medical imaging has paved the way for significant advancements in the diagnosis of brain tumors. This study presents a novel ensemble approach that uses magnetic resonance imaging (MRI) to identify and categorize common brain cancers, such as pituitary, meningioma, and glioma. The proposed workflow is composed of a two-fold approach: firstly, it employs non-trivial image enhancement techniques in data preprocessing, low-rank Tucker decomposition for dimensionality reduction, and machine learning (ML) classifiers to detect and predict the type of brain tumor. Secondly, persistent homology (PH), a topological data analysis (TDA) technique, is exploited to extract potential critical areas in MRI scans. When paired with the ML classifier output, this additional information can help domain experts to identify areas of interest that might contain tumor signatures, improving the interpretability of ML predictions. When compared to automated diagnoses, this transparency adds another level of confidence and is essential for clinical acceptance. The performance of the system was quantitatively evaluated on a well-known MRI dataset, with an overall classification accuracy of 97.28% using an extremely randomized trees model. The promising results show that the integration of TDA, ML, and low-rank approximation methods is a successful approach for brain tumor identification and categorization, providing a solid foundation for further study and clinical application.

arXiv:2410.06089

TOWER: Tree Organized Weighting for Evaluating Complex Instructions

Evaluating the ability of large language models (LLMs) to follow complex human-written instructions is essential for their deployment in real-world applications. While benchmarks like Chatbot Arena use human judges to assess model performance, they are resource-intensive and time-consuming. Alternative methods using LLMs as judges, such as AlpacaEval, MT Bench, WildBench, and InFoBench offer improvements but still do not capture that certain complex instruction aspects are more important than others to follow. To address this gap, we propose a novel evaluation metric, \textsc{TOWER}, that incorporates human-judged importance into the assessment of complex instruction following. We show that human annotators agree with tree-based representations of these complex instructions nearly as much as they agree with other human annotators. We release tree-based annotations of the InFoBench dataset and the corresponding evaluation code to facilitate future research.

arXiv:2410.05613

Stereotype or Personalization? User Identity Biases Chatbot Recommendations

We demonstrate that when people use large language models (LLMs) to generate recommendations, the LLMs produce responses that reflect both what the user wants and who the user is. While personalized recommendations are often desired by users, it can be difficult in practice to distinguish cases of bias from cases of personalization: we find that models generate racially stereotypical recommendations regardless of whether the user revealed their identity intentionally through explicit indications or unintentionally through implicit cues. We argue that chatbots ought to transparently indicate when recommendations are influenced by a user's revealed identity characteristics, but observe that they currently fail to do so. Our experiments show that even though a user's revealed identity significantly influences model recommendations (p < 0.001), model responses obfuscate this fact in response to user queries. This bias and lack of transparency occurs consistently across multiple popular consumer LLMs (gpt-4o-mini, gpt-4-turbo, llama-3-70B, and claude-3.5) and for four American racial groups.