An official website of the United States government
Misinformation regarding climate change is a key roadblock in addressing one of the most serious threats to humanity. This paper investigates factual accuracy in large language models (LLMs) regarding climate information. Using true/false labeled Q&A data for fine-tuning and evaluating LLMs on climate-related claims, we compare open-source models, assessing their ability to generate truthful responses to climate change questions. We investigate the detectability of models intentionally poisoned with false climate information, finding that such poisoning may not affect the accuracy of a model’s responses in other domains. Furthermore, we compare the effectiveness of unlearning algorithms, fine-tuning, and Retrieval-Augmented Generation (RAG) for factually grounding LLMs on climate change topics. Our evaluation reveals that unlearning algorithms can be effective for nuanced conceptual claims, despite previous findings suggesting their inefficacy in privacy contexts. These insights aim to guide the development of more factually reliable LLMs and highlight the need for additional work to secure LLMs against misinformation attacks.
more »
« less
This content will become publicly available on May 23, 2026
Open-Source LLMs for Technical Q&A: Lessons from StackExchange
In the rapidly evolving domain of software engineering (SE), Large Language Models (LLMs) are increasingly leveraged to automate developer support. Open source LLMs have grown competitive with pro- prietary models such as GPT-4 and Claude-3, without the associated financial and accessibility constraints. This study investigates whether state of the art open source LLMs including Solar-10.7B, CodeLlama-7B, Mistral-7B, Qwen2-7B, StarCoder2-7B, and LLaMA3-8B can generate responses to technical queries that align with those crafted by human experts. Leveraging retrieval augmented generation (RAG) and targeted fine tuning, we evaluate these models across critical performance dimen- sions, such as semantic alignment and contextual fluency. Our results show that Solar-10.7B, particularly when paired with RAG and fine tun- ing, most closely replicates expert level responses, o!ering a scalable and cost e!ective alternative to commercial models. This vision paper high- lights the potential of open-source LLMs to enable robust and accessible AI-powered developer assistance in software engineering.
more »
« less
- Award ID(s):
- 2020751
- PAR ID:
- 10639623
- Publisher / Repository:
- 2025 International Conference on Software Engineering of Emerging Technologies (SEET-25)
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract MotivationLarge language models (LLMs) are being adopted at an unprecedented rate, yet still face challenges in knowledge-intensive domains such as biomedicine. Solutions such as pretraining and domain-specific fine-tuning add substantial computational overhead, requiring further domain-expertise. Here, we introduce a token-optimized and robust Knowledge Graph-based Retrieval Augmented Generation (KG-RAG) framework by leveraging a massive biomedical KG (SPOKE) with LLMs such as Llama-2-13b, GPT-3.5-Turbo, and GPT-4, to generate meaningful biomedical text rooted in established knowledge. ResultsCompared to the existing RAG technique for Knowledge Graphs, the proposed method utilizes minimal graph schema for context extraction and uses embedding methods for context pruning. This optimization in context extraction results in more than 50% reduction in token consumption without compromising the accuracy, making a cost-effective and robust RAG implementation on proprietary LLMs. KG-RAG consistently enhanced the performance of LLMs across diverse biomedical prompts by generating responses rooted in established knowledge, accompanied by accurate provenance and statistical evidence (if available) to substantiate the claims. Further benchmarking on human curated datasets, such as biomedical true/false and multiple-choice questions (MCQ), showed a remarkable 71% boost in the performance of the Llama-2 model on the challenging MCQ dataset, demonstrating the framework’s capacity to empower open-source models with fewer parameters for domain-specific questions. Furthermore, KG-RAG enhanced the performance of proprietary GPT models, such as GPT-3.5 and GPT-4. In summary, the proposed framework combines explicit and implicit knowledge of KG and LLM in a token optimized fashion, thus enhancing the adaptability of general-purpose LLMs to tackle domain-specific questions in a cost-effective fashion. Availability and implementationSPOKE KG can be accessed at https://spoke.rbvi.ucsf.edu/neighborhood.html. It can also be accessed using REST-API (https://spoke.rbvi.ucsf.edu/swagger/). KG-RAG code is made available at https://github.com/BaranziniLab/KG_RAG. Biomedical benchmark datasets used in this study are made available to the research community in the same GitHub repository.more » « less
-
Large Language Models (LLMs) are pre-trained on large-scale corpora and excel in numerous general natural language processing (NLP) tasks, such as question answering (QA). Despite their advanced language capabilities, when it comes to domain-specific and knowledge-intensive tasks, LLMs suffer from hallucinations, knowledge cut-offs, and lack of knowledge attributions. Additionally, fine tuning LLMs' intrinsic knowledge to highly specific domains is an expensive and time consuming process. The retrieval-augmented generation (RAG) process has recently emerged as a method capable of optimization of LLM responses, by referencing them to a predetermined ontology. It was shown that using a Knowledge Graph (KG) ontology for RAG improves the QA accuracy, by taking into account relevant sub-graphs that preserve the information in a structured manner. In this paper, we introduce SMART-SLIC, a highly domain-specific LLM framework, that integrates RAG with KG and a vector store (VS) that store factual domain specific information. Importantly, to avoid hallucinations in the KG, we build these highly domain-specific KGs and VSs without the use of LLMs, but via NLP, data mining, and nonnegative tensor factorization with automatic model selection. Pairing our RAG with a domain-specific: (i) KG (containing structured information), and (ii) VS (containing unstructured information) enables the development of domain-specific chat-bots that attribute the source of information, mitigate hallucinations, lessen the need for fine-tuning, and excel in highly domain-specific question answering tasks. We pair SMART-SLIC with chain-of-thought prompting agents. The framework is designed to be generalizable to adapt to any specific or specialized domain. In this paper, we demonstrate the question answering capabilities of our framework on a corpus of scientific publications on malware analysis and anomaly detection.more » « less
-
Text watermarks for large language models (LLMs) have been commonly used to identify the origins of machine-generated content, which is promising for assessing liability when combating deepfake or harmful content. While existing watermarking techniques typically prioritize robustness against removal attacks, unfortunately, they are vulnerable to spoofing attacks: malicious actors can subtly alter the meanings of LLM-generated responses or even forge harmful content, potentially misattributing blame to the LLM developer. To overcome this, we introduce a bi-level signature scheme, Bileve, which embeds fine-grained signature bits for integrity checks (mitigating spoofing attacks) as well as a coarse-grained signal to trace text sources when the signature is invalid (enhancing detectability) via a novel rank-based sampling strategy. Compared to conventional watermark detectors that only output binary results, Bileve can differentiate 5 scenarios during detection, reliably tracing text provenance and regulating LLMs. The experiments conducted on OPT-1.3B and LLaMA-7B demonstrate the effectiveness of Bileve in defeating spoofing attacks with enhanced detectability.more » « less
-
Research within sociotechnical domains, such as Software Engineering, fundamentally requires the human perspective. Nevertheless, traditional qualitative data collection methods suffer from difficulties in participant recruitment, scaling, and labor intensity. This vision paper proposes a novel approach to qualitative data collection in software engineering research by harnessing the capabilities of artificial intelligence (AI), especially large language models (LLMs) like ChatGPT and multimodal foundation models. We explore the potential of AI-generated synthetic text as an alternative source of qualitative data, discussing how LLMs can replicate human responses and behaviors in research settings. We discuss AI applications in emulating humans in interviews, focus groups, surveys, observational studies, and user evaluations. We discuss open problems and research opportunities to implement this vision. In the future, an integrated approach where both AI and human-generated data coexist will likely yield the most effective outcomes.more » « less
