| Item Type | Preprint |
|---|---|
| Author | N'yoma Diamond |
| Author | Soumya Banerjee |
| Abstract | The Generative Agents framework recently developed by Park et al. has enabled numerous new technical solutions and problem-solving approaches. Academic and industrial interest in generative agents has been explosive as a result of the effectiveness of generative agents toward emulating human behaviour. However, it is necessary to consider the ethical challenges and concerns posed by this technique and its usage. In this position paper, we discuss the extant literature that evaluate the ethical considerations regarding generative agents and similar generative tools, and identify additional concerns of significant importance. We also suggest guidelines and necessary future research on how to mitigate some of the ethical issues and systemic risks associated with generative agents. |
| Date | 2024-11-28 |
| Library Catalog | arXiv.org |
| URL | http://arxiv.org/abs/2411.19211 |
| Accessed | 12/3/2024, 8:35:33 AM |
| Extra | arXiv:2411.19211 |
| DOI | 10.48550/arXiv.2411.19211 |
| Repository | arXiv |
| Archive ID | arXiv:2411.19211 |
| Date Added | 12/3/2024, 8:35:33 AM |
| Modified | 12/3/2024, 8:35:37 AM |
| Item Type | Journal Article |
|---|---|
| Author | Travis LaCroix |
| Abstract | The value alignment problem for artificial intelligence (AI) asks how we can ensure that the “values”—i.e., objective functions—of artificial systems are aligned with the values of humanity. In this paper, I argue that linguistic communication is a necessary condition for robust value alignment. I discuss the consequences that the truth of this claim would have for research programmes that attempt to ensure value alignment for AI systems—or, more loftily, those programmes that seek to design robustly beneficial or ethical artificial agents. |
| Date | 2024-12-04 |
| Language | en |
| Library Catalog | Springer Link |
| URL | https://doi.org/10.1007/s11098-024-02257-w |
| Accessed | 12/12/2024, 8:59:26 AM |
| Publication | Philosophical Studies |
| DOI | 10.1007/s11098-024-02257-w |
| Journal Abbr | Philos Stud |
| ISSN | 1573-0883 |
| Date Added | 12/12/2024, 8:59:26 AM |
| Modified | 12/12/2024, 8:59:38 AM |
| Item Type | Preprint |
|---|---|
| Author | Jared Moore |
| Author | Tanvi Deshpande |
| Author | Diyi Yang |
| Abstract | Large language models (LLMs) appear to bias their survey answers toward certain values. Nonetheless, some argue that LLMs are too inconsistent to simulate particular values. Are they? To answer, we first define value consistency as the similarity of answers across (1) paraphrases of one question, (2) related questions under one topic, (3) multiple-choice and open-ended use-cases of one question, and (4) multilingual translations of a question to English, Chinese, German, and Japanese. We apply these measures to a few large ($>=34b$), open LLMs including llama-3, as well as gpt-4o, using eight thousand questions spanning more than 300 topics. Unlike prior work, we find that models are relatively consistent across paraphrases, use-cases, translations, and within a topic. Still, some inconsistencies remain. Models are more consistent on uncontroversial topics (e.g., in the U.S., "Thanksgiving") than on controversial ones ("euthanasia"). Base models are both more consistent compared to fine-tuned models and are uniform in their consistency across topics, while fine-tuned models are more inconsistent about some topics ("euthanasia") than others ("women's rights") like our human subjects (n=165). |
| Date | 2024-07-03 |
| Library Catalog | arXiv.org |
| URL | http://arxiv.org/abs/2407.02996 |
| Accessed | 12/1/2024, 8:44:06 PM |
| Extra | arXiv:2407.02996 version: 1 |
| DOI | 10.48550/arXiv.2407.02996 |
| Repository | arXiv |
| Archive ID | arXiv:2407.02996 |
| Date Added | 12/1/2024, 8:44:06 PM |
| Modified | 12/1/2024, 8:44:09 PM |
| Item Type | Preprint |
|---|---|
| Author | Fabian Offert |
| Author | Ranjodh Singh Dhaliwal |
| Abstract | We outline some common methodological issues in the field of critical AI studies, including a tendency to overestimate the explanatory power of individual samples (the benchmark casuistry), a dependency on theoretical frameworks derived from earlier conceptualizations of computation (the black box casuistry), and a preoccupation with a cause-and-effect model of algorithmic harm (the stack casuistry). In the face of these issues, we call for, and point towards, a future set of methodologies that might take into account existing strengths in the humanistic close analysis of cultural objects. |
| Date | 2024-11-28 |
| Library Catalog | arXiv.org |
| URL | http://arxiv.org/abs/2411.18833 |
| Accessed | 12/4/2024, 5:20:56 PM |
| Extra | arXiv:2411.18833 |
| DOI | 10.48550/arXiv.2411.18833 |
| Repository | arXiv |
| Archive ID | arXiv:2411.18833 |
| Date Added | 12/4/2024, 5:20:56 PM |
| Modified | 12/4/2024, 5:21:00 PM |
| Item Type | Preprint |
|---|---|
| Author | Yujin Potter |
| Author | Shiyang Lai |
| Author | Junsol Kim |
| Author | James Evans |
| Author | Dawn Song |
| Abstract | How could LLMs influence our democracy? We investigate LLMs' political leanings and the potential influence of LLMs on voters by conducting multiple experiments in a U.S. presidential election context. Through a voting simulation, we first demonstrate 18 open- and closed-weight LLMs' political preference for a Democratic nominee over a Republican nominee. We show how this leaning towards the Democratic nominee becomes more pronounced in instruction-tuned models compared to their base versions by analyzing their responses to candidate-policy related questions. We further explore the potential impact of LLMs on voter choice by conducting an experiment with 935 U.S. registered voters. During the experiments, participants interacted with LLMs (Claude-3, Llama-3, and GPT-4) over five exchanges. The experiment results show a shift in voter choices towards the Democratic nominee following LLM interaction, widening the voting margin from 0.7% to 4.6%, even though LLMs were not asked to persuade users to support the Democratic nominee during the discourse. This effect is larger than many previous studies on the persuasiveness of political campaigns, which have shown minimal effects in presidential elections. Many users also expressed a desire for further political interaction with LLMs. Which aspects of LLM interactions drove these shifts in voter choice requires further study. Lastly, we explore how a safety method can make LLMs more politically neutral, while raising the question of whether such neutrality is truly the path forward. |
| Date | 2024-11-11 |
| Short Title | Hidden Persuaders |
| Library Catalog | arXiv.org |
| URL | http://arxiv.org/abs/2410.24190 |
| Accessed | 11/18/2024, 4:02:40 PM |
| Extra | arXiv:2410.24190 |
| Repository | arXiv |
| Archive ID | arXiv:2410.24190 |
| Date Added | 11/18/2024, 4:02:40 PM |
| Modified | 11/18/2024, 4:02:40 PM |