Hallucination in LLMs – Perspectives and Remediations; Fine-Tuning With Feedback; What LLMs DO NOT KNOW; LLaMA 2 Explained; and More.

Editor's Paper Recommendations

Fine-Tuning Language Models Using Formal Methods Feedback: Although pre-trained language models encode generic knowledge beneficial for planning and control, they may fail to generate appropriate control policies for domain-specific tasks. Existing fine-tuning methods use human feedback to address this limitation; however, sourcing human feedback is labor-intensive and costly. We present a fully automated approach to fine-tune pre-trained language models for applications in autonomous systems, bridging the gap between generic knowledge and domain-specific requirements while reducing cost. The method synthesizes automaton-based controllers from pre-trained models guided by natural language task descriptions. These controllers are verifiable against independently provided specifications within a world model, which can be abstract or obtained from a high-fidelity simulator. Controllers with high compliance with the desired specifications receive higher ranks, guiding the iterative fine-tuning process. We provide quantitative evidence, primarily in autonomous driving, to demonstrate the method's effectiveness across multiple tasks. The results indicate an improvement in the percentage of specifications satisfied by the controller from 60% to 90%.

The Troubling Emergence of Hallucination in Large Language Models -- An Extensive Definition, Quantification, and Prescriptive Remediations: The recent advancements in Large Language Models (LLMs) have garnered widespread acclaim for their remarkable emerging capabilities. However, the issue of hallucination has parallelly emerged as a by-product, posing significant concerns. While some recent endeavors have been made to identify and mitigate different types of hallucination, there has been a limited emphasis on the nuanced categorization of hallucination and associated mitigation methods. To address this gap, we offer a fine-grained discourse on profiling hallucination based on its degree, orientation, and category, along with offering strategies for alleviation. As such, we define two overarching orientations of hallucination: (i) factual mirage (FM) and (ii) silver lining (SL). To provide a more comprehensive understanding, both orientations are further sub-categorized into intrinsic and extrinsic, with three degrees of severity - (i) mild, (ii) moderate, and (iii) alarming. We also meticulously categorize hallucination into six types: (i) acronym ambiguity, (ii) numeric nuisance, (iii) generated golem, (iv) virtual voice, (v) geographic erratum, and (vi) time wrap. Furthermore, we curate HallucInation eLiciTation (HILT), a publicly available dataset comprising 75,000 samples generated using 15 contemporary LLMs and human annotations for the categories above. Finally, to establish a method for quantifying and offering a comparative spectrum that allows us to evaluate and rank LLMs based on their vulnerability to producing hallucinations, we propose the Hallucination Vulnerability Index (HVI). We firmly believe that HVI holds significant value as a tool for the wider NLP community, with the potential to serve as a rubric in AI-related policy-making. In conclusion, we'd like to propose two solution strategies for mitigating hallucinations.

Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method: Large Language Models (LLMs) have shown great potential in Natural Language Processing (NLP) tasks. However, recent literature reveals that LLMs generate nonfactual responses intermittently, which impedes the LLMs' reliability for further utilization. In this paper, we propose a novel self-detection method to detect which questions an LLM does not know are prone to generate nonfactual results. Specifically, we first diversify the textual expressions for a given question and collect the corresponding answers. Then, we examine the divergencies between the generated answers to identify the questions that the model may generate falsehoods. The above steps can be accomplished by prompting the LLMs without referring to other external resources. We conduct comprehensive experiments and demonstrate the effectiveness of our method on recently released LLMs, e.g., Vicuna, ChatGPT, and GPT-4.

--

Are you looking to advertise a product, job opening, or event to an audience of over 40,000 AI researchers and engineers? Please reach out to us on?LinkedIn?to explore your options.

Enjoy the newsletter? Help us make it bigger and better by sharing it with colleagues and friends.

--

Industry Insights

• Human-Written Or Machine-Generated: Finding Intelligence In Language Models
• LLaMA 2: Meta AI's second-gen LLM explained
• This Report from Microsoft AI Reveals the Impact of Fine-Tuning and Retrieval-Augmented Generation RAG on Large Language Models in Agriculture
• OpenAI launches a new generation of embedding models and other API updates.
• ChatGPT Plus vs. Copilot Pro — which premium chatbot is better?

?

?Growth Zone

• ?How Managers Become Leaders

??

Expert Advice