PyTorchKR Papers

최신 논문

총 223편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2407.14246공식 코드 · Papers with Code

Unipa-GPT: Large Language Models for university-oriented QA in Italian

This paper illustrates the architecture and training of Unipa-GPT, a chatbot relying on a Large Language Model, developed for assisting students in choosing a bachelor/master degree course at the University of Palermo. Unipa-GPT relies on gpt-3.5-turbo, it was presented in the context of the European Researchers' Night (SHARPER night). In our experiments we adopted both the Retrieval Augmented Generation (RAG) approach and fine-tuning to develop the system. The whole architecture of Unipa-GPT is presented, both the RAG and the fine-tuned systems are compared, and a brief discussion on their performance is reported. Further comparison with other Large Language Models and the experimental results during the SHARPER night are illustrated. Corpora and code are available on GitHub

arXiv:2407.11438공식 코드 · Papers with Code

Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild

Measuring personal disclosures made in human-chatbot interactions can provide a better understanding of users' AI literacy and facilitate privacy research for large language models (LLMs). We run an extensive, fine-grained analysis on the personal disclosures made by real users to commercial GPT models, investigating the leakage of personally identifiable and sensitive information. To understand the contexts in which users disclose to chatbots, we develop a taxonomy of tasks and sensitive topics, based on qualitative and quantitative analysis of naturally occurring conversations. We discuss these potential privacy harms and observe that: (1) personally identifiable information (PII) appears in unexpected contexts such as in translation or code editing (48% and 16% of the time, respectively) and (2) PII detection alone is insufficient to capture the sensitive topics that are common in human-chatbot interactions, such as detailed sexual preferences or specific drug use habits. We believe that these high disclosure rates are of significant importance for researchers and data curators, and we call for the design of appropriate nudging mechanisms to help users moderate their interactions.

arXiv:2407.10949공식 코드 · Papers with Code

Representing Rule-based Chatbots with Transformers

Transformer-based chatbots can conduct fluent, natural-sounding conversations, but we have limited understanding of the mechanisms underlying their behavior. Prior work has taken a bottom-up approach to understanding Transformers by constructing Transformers for various synthetic and formal language tasks, such as regular expressions and Dyck languages. However, it is not obvious how to extend this approach to understand more naturalistic conversational agents. In this work, we take a step in this direction by constructing a Transformer that implements the ELIZA program, a classic, rule-based chatbot. ELIZA illustrates some of the distinctive challenges of the conversational setting, including both local pattern matching and long-term dialog state tracking. We build on constructions from prior work -- in particular, for simulating finite-state automata -- showing how simpler constructions can be composed and extended to give rise to more sophisticated behavior. Next, we train Transformers on a dataset of synthetically generated ELIZA conversations and investigate the mechanisms the models learn. Our analysis illustrates the kinds of mechanisms these models tend to prefer -- for example, models favor an induction head mechanism over a more precise, position based copying mechanism; and using intermediate generations to simulate recurrent data structures, like ELIZA's memory mechanisms. Overall, by drawing an explicit connection between neural chatbots and interpretable, symbolic mechanisms, our results offer a new setting for mechanistic analysis of conversational agents.

arXiv:2407.09197공식 코드 · Papers with Code

A Chatbot for Asylum-Seeking Migrants in Europe

We present ACME: A Chatbot for asylum-seeking Migrants in Europe. ACME relies on computational argumentation and aims to help migrants identify the highest level of protection they can apply for. This would contribute to a more sustainable migration by reducing the load on territorial commissions, Courts, and humanitarian organizations supporting asylum applicants. We describe the background context, system architecture, underlying technologies, and a case study used to validate the tool with domain experts.

arXiv:2407.03974공식 코드 · Papers with Code

LLM Roleplay: Simulating Human-Chatbot Interaction

The development of chatbots requires collecting a large number of human-chatbot dialogues to reflect the breadth of users' sociodemographic backgrounds and conversational goals. However, the resource requirements to conduct the respective user studies can be prohibitively high and often only allow for a narrow analysis of specific dialogue goals and participant demographics. In this paper, we propose LLM Roleplay: a goal-oriented, persona-based method to automatically generate diverse multi-turn dialogues simulating human-chatbot interaction. LLM Roleplay can be applied to generate dialogues with any type of chatbot and uses large language models (LLMs) to play the role of textually described personas. To validate our method, we collect natural human-chatbot dialogues from different sociodemographic groups and conduct a user study to compare these with our generated dialogues. We evaluate the capabilities of state-of-the-art LLMs in maintaining a conversation during their embodiment of a specific persona and find that our method can simulate human-chatbot dialogues with a high indistinguishability rate.

arXiv:2406.18510공식 코드 · Papers with Code

WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models

We introduce WildTeaming, an automatic LLM safety red-teaming framework that mines in-the-wild user-chatbot interactions to discover 5.7K unique clusters of novel jailbreak tactics, and then composes multiple tactics for systematic exploration of novel jailbreaks. Compared to prior work that performed red-teaming via recruited human workers, gradient-based optimization, or iterative revision with LLMs, our work investigates jailbreaks from chatbot users who were not specifically instructed to break the system. WildTeaming reveals previously unidentified vulnerabilities of frontier LLMs, resulting in up to 4.6x more diverse and successful adversarial attacks compared to state-of-the-art jailbreak methods. While many datasets exist for jailbreak evaluation, very few open-source datasets exist for jailbreak training, as safety training data has been closed even when model weights are open. With WildTeaming we create WildJailbreak, a large-scale open-source synthetic safety dataset with 262K vanilla (direct request) and adversarial (complex jailbreak) prompt-response pairs. To mitigate exaggerated safety behaviors, WildJailbreak provides two contrastive types of queries: 1) harmful queries (vanilla & adversarial) and 2) benign queries that resemble harmful queries in form but contain no harm. As WildJailbreak considerably upgrades the quality and scale of existing safety resources, it uniquely enables us to examine the scaling effects of data and the interplay of data properties and model capabilities during safety training. Through extensive experiments, we identify the training properties that enable an ideal balance of safety behaviors: appropriate safeguarding without over-refusal, effective handling of vanilla and adversarial queries, and minimal, if any, decrease in general capabilities. All components of WildJailbeak contribute to achieving balanced safety behaviors of models.

arXiv:2406.18133공식 코드 · Papers with Code

ConvoCache: Smart Re-Use of Chatbot Responses

We present ConvoCache, a conversational caching system that solves the problem of slow and expensive generative AI models in spoken chatbots. ConvoCache finds a semantically similar prompt in the past and reuses the response. In this paper we evaluate ConvoCache on the DailyDialog dataset. We find that ConvoCache can apply a UniEval coherence threshold of 90% and respond to 89% of prompts using the cache with an average latency of 214ms, replacing LLM and voice synthesis that can take over 1s. To further reduce latency we test prefetching and find limited usefulness. Prefetching with 80% of a request leads to a 63% hit rate, and a drop in overall coherence. ConvoCache can be used with any chatbot to reduce costs by reducing usage of generative AI by up to 89%.

arXiv:2406.17982공식 코드 · Papers with Code

EDEN: Empathetic Dialogues for English learning

Dialogue systems have been used as conversation partners in English learning, but few have studied whether these systems improve learning outcomes. Student passion and perseverance, or grit, has been associated with language learning success. Recent work establishes that as students perceive their English teachers to be more supportive, their grit improves. Hypothesizing that the same pattern applies to English-teaching chatbots, we create EDEN, a robust open-domain chatbot for spoken conversation practice that provides empathetic feedback. To construct EDEN, we first train a specialized spoken utterance grammar correction model and a high-quality social chit-chat conversation model. We then conduct a preliminary user study with a variety of strategies for empathetic feedback. Our experiment suggests that using adaptive empathetic feedback leads to higher perceived affective support. Furthermore, elements of perceived affective support positively correlate with student grit.

arXiv:2406.11939공식 코드 · Papers with Code

From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline

The rapid evolution of Large Language Models (LLMs) has outpaced the development of model evaluation, highlighting the need for continuous curation of new, challenging benchmarks. However, manual curation of high-quality, human-aligned benchmarks is expensive and time-consuming. To address this, we introduce BenchBuilder, an automated pipeline that leverages LLMs to curate high-quality, open-ended prompts from large, crowd-sourced datasets, enabling continuous benchmark updates without human in the loop. We apply BenchBuilder to datasets such as Chatbot Arena and WildChat-1M, extracting challenging prompts and utilizing LLM-as-a-Judge for automatic model evaluation. To validate benchmark quality, we propose new metrics to measure a benchmark's alignment with human preferences and ability to separate models. We release Arena-Hard-Auto, a benchmark consisting 500 challenging prompts curated by BenchBuilder. Arena-Hard-Auto provides 3x higher separation of model performances compared to MT-Bench and achieves 98.6% correlation with human preference rankings, all at a cost of $20. Our work sets a new framework for the scalable curation of automated benchmarks from extensive data.

arXiv:2406.08411공식 코드 · Papers with Code

Tailoring Generative AI Chatbots for Multiethnic Communities in Disaster Preparedness Communication: Extending the CASA Paradigm

This study is among the first to develop different prototypes of generative artificial intelligence (GenAI) chatbots powered by GPT-4 to communicate hurricane preparedness information to diverse residents. Drawing from the Computers Are Social Actors paradigm and the literature on disaster vulnerability and cultural tailoring, we conducted a between-subjects experiment with 441 Black, Hispanic, and Caucasian residents of Florida. Our results suggest that GenAI chatbots varying in tone formality and cultural tailoring significantly influence perceptions of their friendliness and credibility, which, in turn, relate to hurricane preparedness outcomes. These results highlight the potential of using GenAI chatbots to improve diverse communities' disaster preparedness.

arXiv:2406.07882공식 코드 · Papers with Code

Designing a Dashboard for Transparency and Control of Conversational AI

Conversational LLMs function as black box systems, leaving users guessing about why they see the output they do. This lack of transparency is potentially problematic, especially given concerns around bias and truthfulness. To address this issue, we present an end-to-end prototype-connecting interpretability techniques with user experience design-that seeks to make chatbots more transparent. We begin by showing evidence that a prominent open-source LLM has a "user model": examining the internal state of the system, we can extract data related to a user's age, gender, educational level, and socioeconomic status. Next, we describe the design of a dashboard that accompanies the chatbot interface, displaying this user model in real time. The dashboard can also be used to control the user model and the system's behavior. Finally, we discuss a study in which users conversed with the instrumented system. Our results suggest that users appreciate seeing internal states, which helped them expose biased behavior and increased their sense of control. Participants also made valuable suggestions that point to future directions for both design and machine learning research. The project page and video demo of our TalkTuner system are available at https://bit.ly/talktuner-project-page

arXiv:2406.06560공식 코드 · Papers with Code

Inverse Constitutional AI: Compressing Preferences into Principles

Feedback data is widely used for fine-tuning and evaluating state-of-the-art AI models. Pairwise text preferences, where human or AI annotators select the "better" of two options, are particularly common. Such preferences are used to train (reward) models or to rank models with aggregate statistics. For many applications it is desirable to understand annotator preferences in addition to modelling them - not least because extensive prior work has shown various unintended biases in preference datasets. Yet, preference datasets remain challenging to interpret. Neither black-box reward models nor statistics can answer why one text is preferred over another. Manual interpretation of the numerous (long) response pairs is usually equally infeasible. In this paper, we introduce the Inverse Constitutional AI (ICAI) problem, formulating the interpretation of pairwise text preference data as a compression task. In constitutional AI, a set of principles (a constitution) is used to provide feedback and fine-tune AI models. ICAI inverts this process: given a feedback dataset, we aim to extract a constitution that best enables a large language model (LLM) to reconstruct the original annotations. We propose a corresponding ICAI algorithm and validate its generated constitutions quantitatively based on annotation reconstruction accuracy on several datasets: (a) synthetic feedback data with known principles; (b) AlpacaEval cross-annotated human feedback data; (c) crowdsourced Chatbot Arena data; and (d) PRISM data from diverse demographic groups. As a short and interpretable representation of the original dataset, generated constitutions have many potential use cases: help identify undesirable annotator biases, understand model performance better, scale feedback to unseen data, or adapt models to individual user or group preferences. We release the source code at https://github.com/rdnfn/icai.

arXiv:2406.04770공식 코드 · Papers with Code

WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild

We introduce WildBench, an automated evaluation framework designed to benchmark large language models (LLMs) using challenging, real-world user queries. WildBench consists of 1,024 tasks carefully selected from over one million human-chatbot conversation logs. For automated evaluation with WildBench, we have developed two metrics, WB-Reward and WB-Score, which are computable using advanced LLMs such as GPT-4-turbo. WildBench evaluation uses task-specific checklists to evaluate model outputs systematically and provides structured explanations that justify the scores and comparisons, resulting in more reliable and interpretable automatic judgments. WB-Reward employs fine-grained pairwise comparisons between model responses, generating five potential outcomes: much better, slightly better, slightly worse, much worse, or a tie. Unlike previous evaluations that employed a single baseline model, we selected three baseline models at varying performance levels to ensure a comprehensive pairwise evaluation. Additionally, we propose a simple method to mitigate length bias, by converting outcomes of ``slightly better/worse'' to ``tie'' if the winner response exceeds the loser one by more than $K$ characters. WB-Score evaluates the quality of model outputs individually, making it a fast and cost-efficient evaluation metric. WildBench results demonstrate a strong correlation with the human-voted Elo ratings from Chatbot Arena on hard tasks. Specifically, WB-Reward achieves a Pearson correlation of 0.98 with top-ranking models. Additionally, WB-Score reaches 0.95, surpassing both ArenaHard's 0.91 and AlpacaEval2.0's 0.89 for length-controlled win rates, as well as the 0.87 for regular win rates.

arXiv:2406.01280공식 코드 · Papers with Code

Demo: Soccer Information Retrieval via Natural Queries using SoccerRAG

The rapid evolution of digital sports media necessitates sophisticated information retrieval systems that can efficiently parse extensive multimodal datasets. This paper demonstrates SoccerRAG, an innovative framework designed to harness the power of Retrieval Augmented Generation (RAG) and Large Language Models (LLMs) to extract soccer-related information through natural language queries. By leveraging a multimodal dataset, SoccerRAG supports dynamic querying and automatic data validation, enhancing user interaction and accessibility to sports archives. We present a novel interactive user interface (UI) based on the Chainlit framework which wraps around the core functionality, and enable users to interact with the SoccerRAG framework in a chatbot-like visual manner.

arXiv:2405.20389공식 코드 · Papers with Code

Designing an Evaluation Framework for Large Language Models in Astronomy Research

Large Language Models (LLMs) are shifting how scientific research is done. It is imperative to understand how researchers interact with these models and how scientific sub-communities like astronomy might benefit from them. However, there is currently no standard for evaluating the use of LLMs in astronomy. Therefore, we present the experimental design for an evaluation study on how astronomy researchers interact with LLMs. We deploy a Slack chatbot that can answer queries from users via Retrieval-Augmented Generation (RAG); these responses are grounded in astronomy papers from arXiv. We record and anonymize user questions and chatbot answers, user upvotes and downvotes to LLM responses, user feedback to the LLM, and retrieved documents and similarity scores with the query. Our data collection method will enable future dynamic evaluations of LLM tools for astronomy.

arXiv:2405.20267공식 코드 · Papers with Code

Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions

As LLMs continuously evolve, there is an urgent need for a reliable evaluation method that delivers trustworthy results promptly. Currently, static benchmarks suffer from inflexibility and unreliability, leading users to prefer human voting platforms like Chatbot Arena. However, human evaluations require significant manual effort. To address this, we propose the Auto-Arena, an innovative framework that automates the entire evaluation process using LLM-powered agents. Firstly, an LLM examiner generates questions. Then, two LLM candidates engage in a multi-round peer battle based on individual questions, aiming at revealing their true performance differences. Finally, a committee of LLM judges collaboratively discusses and decides the winner, reducing bias and enhancing fairness. During the peer battles, we observe intriguing scenarios where the LLM candidates display competitive behaviors and even learn from the opponents. In our extensive experiments involving 15 recent LLMs, Auto-Arena shows a 92.14% correlation with human preferences, surpassing all previous expert-annotated benchmarks without any manual efforts. As a result, Auto-Arena offers a promising alternative to current human evaluation platforms for evaluating LLMs automatically.

arXiv:2405.14734공식 코드 · Papers with Code

SimPO: Simple Preference Optimization with a Reference-Free Reward

Direct Preference Optimization (DPO) is a widely used offline preference optimization algorithm that reparameterizes reward functions in reinforcement learning from human feedback (RLHF) to enhance simplicity and training stability. In this work, we propose SimPO, a simpler yet more effective approach. The effectiveness of SimPO is attributed to a key design: using the average log probability of a sequence as the implicit reward. This reward formulation better aligns with model generation and eliminates the need for a reference model, making it more compute and memory efficient. Additionally, we introduce a target reward margin to the Bradley-Terry objective to encourage a larger margin between the winning and losing responses, further improving the algorithm's performance. We compare SimPO to DPO and its latest variants across various state-of-the-art training setups, including both base and instruction-tuned models such as Mistral, Llama 3, and Gemma 2. We evaluate on extensive chat-based evaluation benchmarks, including AlpacaEval 2, MT-Bench, and Arena-Hard. Our results demonstrate that SimPO consistently and significantly outperforms existing approaches without substantially increasing response length. Specifically, SimPO outperforms DPO by up to 6.4 points on AlpacaEval 2 and by up to 7.5 points on Arena-Hard. Our top-performing model, built on Gemma-2-9B-it, achieves a 72.4% length-controlled win rate on AlpacaEval 2, a 59.1% win rate on Arena-Hard, and ranks 1st on Chatbot Arena among <10B models with real user votes.

arXiv:2405.14006공식 코드 · Papers with Code

Evaluating Large Language Models with Human Feedback: Establishing a Swedish Benchmark

In the rapidly evolving field of artificial intelligence, large language models (LLMs) have demonstrated significant capabilities across numerous applications. However, the performance of these models in languages with fewer resources, such as Swedish, remains under-explored. This study introduces a comprehensive human benchmark to assess the efficacy of prominent LLMs in understanding and generating Swedish language texts using forced choice ranking. We employ a modified version of the ChatbotArena benchmark, incorporating human feedback to evaluate eleven different models, including GPT-4, GPT-3.5, various Claude and Llama models, and bespoke models like Dolphin-2.9-llama3b-8b-flashback and BeagleCatMunin. These models were chosen based on their performance on LMSYS chatbot arena and the Scandeval benchmarks. We release the chatbotarena.se benchmark as a tool to improve our understanding of language model performance in Swedish with the hopes that it will be widely used. We aim to create a leaderboard once sufficient data has been collected and analysed.

arXiv:2405.12021공식 코드 · Papers with Code

Can AI Relate: Testing Large Language Model Response for Mental Health Support

Large language models (LLMs) are already being piloted for clinical use in hospital systems like NYU Langone, Dana-Farber and the NHS. A proposed deployment use case is psychotherapy, where a LLM-powered chatbot can treat a patient undergoing a mental health crisis. Deployment of LLMs for mental health response could hypothetically broaden access to psychotherapy and provide new possibilities for personalizing care. However, recent high-profile failures, like damaging dieting advice offered by the Tessa chatbot to patients with eating disorders, have led to doubt about their reliability in high-stakes and safety-critical settings. In this work, we develop an evaluation framework for determining whether LLM response is a viable and ethical path forward for the automation of mental health treatment. Our framework measures equity in empathy and adherence of LLM responses to motivational interviewing theory. Using human evaluation with trained clinicians and automatic quality-of-care metrics grounded in psychology research, we compare the responses provided by peer-to-peer responders to those provided by a state-of-the-art LLM. We show that LLMs like GPT-4 use implicit and explicit cues to infer patient demographics like race. We then show that there are statistically significant discrepancies between patient subgroups: Responses to Black posters consistently have lower empathy than for any other demographic group (2%-13% lower than the control group). Promisingly, we do find that the manner in which responses are generated significantly impacts the quality of the response. We conclude by proposing safety guidelines for the potential deployment of LLMs for mental health response.

arXiv:2405.10861공식 코드 · Papers with Code

Tailoring Vaccine Messaging with Common-Ground Opinions

One way to personalize chatbot interactions is by establishing common ground with the intended reader. A domain where establishing mutual understanding could be particularly impactful is vaccine concerns and misinformation. Vaccine interventions are forms of messaging which aim to answer concerns expressed about vaccination. Tailoring responses in this domain is difficult, since opinions often have seemingly little ideological overlap. We define the task of tailoring vaccine interventions to a Common-Ground Opinion (CGO). Tailoring responses to a CGO involves meaningfully improving the answer by relating it to an opinion or belief the reader holds. In this paper we introduce TAILOR-CGO, a dataset for evaluating how well responses are tailored to provided CGOs. We benchmark several major LLMs on this task; finding GPT-4-Turbo performs significantly better than others. We also build automatic evaluation metrics, including an efficient and accurate BERT model that outperforms finetuned LLMs, investigate how to successfully tailor vaccine messaging to CGOs, and provide actionable recommendations from this investigation. Code and model weights: https://github.com/rickardstureborg/tailor-cgo Dataset: https://huggingface.co/datasets/DukeNLP/tailor-cgo