Grounding and evaluation for large language models: Practical challenges and lessons learned (survey)
With the ongoing rapid adoption of Artificial Intelligence (AI)-based systems in high-stakes
domains, ensuring the trustworthiness, safety, and observability of these systems has …
domains, ensuring the trustworthiness, safety, and observability of these systems has …
Large legal fictions: Profiling legal hallucinations in large language models
Do large language models (LLMs) know the law? LLMs are increasingly being used to
augment legal practice, education, and research, yet their revolutionary potential is …
augment legal practice, education, and research, yet their revolutionary potential is …
Multi-hop question answering
Abstract The task of Question Answering (QA) has attracted significant research interest for a
long time. Its relevance to language understanding and knowledge retrieval tasks, along …
long time. Its relevance to language understanding and knowledge retrieval tasks, along …
Open-Ethical AI: Advancements in Open-Source Human-Centric Neural Language Models
This survey summarises the most recent methods for building and assessing helpful, honest,
and harmless neural language models, considering small, medium, and large-size models …
and harmless neural language models, considering small, medium, and large-size models …
The art of saying no: Contextual noncompliance in language models
Chat-based language models are designed to be helpful, yet they should not comply with
every user request. While most existing work primarily focuses on refusal of" unsafe" …
every user request. While most existing work primarily focuses on refusal of" unsafe" …
DebUnc: mitigating hallucinations in large language model agent communication with uncertainty estimations
To enhance Large Language Model (LLM) capabilities, multi-agent debates have been
introduced, where multiple LLMs discuss solutions to a problem over several rounds of …
introduced, where multiple LLMs discuss solutions to a problem over several rounds of …
Self-introspective decoding: Alleviating hallucinations for large vision-language models
While Large Vision-Language Models (LVLMs) have rapidly advanced in recent years, the
prevalent issue known as thehallucination'problem has emerged as a significant bottleneck …
prevalent issue known as thehallucination'problem has emerged as a significant bottleneck …
Defining knowledge: Bridging epistemology and large language models
Knowledge claims are abundant in the literature on large language models (LLMs); but can
we say that GPT-4 truly" knows" the Earth is round? To address this question, we review …
we say that GPT-4 truly" knows" the Earth is round? To address this question, we review …
Think twice before trusting: Self-detection for large language models through comprehensive answer reflection
Abstract Self-detection for Large Language Models (LLMs) seeks to evaluate the
trustworthiness of the LLM's output by leveraging its own capabilities, thereby alleviating the …
trustworthiness of the LLM's output by leveraging its own capabilities, thereby alleviating the …
On the limits of language generation: Trade-offs between hallucination and mode collapse
Specifying all desirable properties of a language model is challenging, but certain
requirements seem essential. Given samples from an unknown language, the trained model …
requirements seem essential. Given samples from an unknown language, the trained model …