VertMark embeds robust, training-free watermarks into vertical domain language models by creating hidden semantic equivalence between low-frequency triggers and high-frequency domain terms via parameter swaps, supporting reliable verification with negligible performance impact.
A Survey on Large Language Models for Critical Societal Domains: Finance, Healthcare, and Law
11 Pith papers cite this work, alongside 16 external citations. Polarity classification is still indexing.
11
Pith papers citing it
16
external citations · Pith
abstract
In the fast-evolving domain of artificial intelligence, large language models (LLMs) such as GPT-3 and GPT-4 are revolutionizing the landscapes of finance, healthcare, and law: domains characterized by their reliance on professional expertise, challenging data acquisition, high-stakes, and stringent regulatory compliance. This survey offers a detailed exploration of the methodologies, applications, challenges, and forward-looking opportunities of LLMs within these high-stakes sectors. We highlight the instrumental role of LLMs in enhancing diagnostic and treatment methodologies in healthcare, innovating financial analytics, and refining legal interpretation and compliance strategies. Moreover, we critically examine the ethics for LLM applications in these fields, pointing out the existing ethical concerns and the need for transparent, fair, and robust AI systems that respect regulatory norms. By presenting a thorough review of current literature and practical applications, we showcase the transformative impact of LLMs, and outline the imperative for interdisciplinary cooperation, methodological advancements, and ethical vigilance. Through this lens, we aim to spark dialogue and inspire future research dedicated to maximizing the benefits of LLMs while mitigating their risks in these precision-dependent sectors. To facilitate future research on LLMs in these critical societal domains, we also initiate a reading list that tracks the latest advancements under this topic, which will be continually updated: \url{https://github.com/czyssrs/LLM_X_papers}.
representative citing papers
Large language models exhibit normative conformity in addition to informational conformity, and subtle social context can direct which group they conform to.
A learned weighted sum of intermediate-layer activations compresses an instruction prompt into a single patch vector that, injected at an early layer, recovers task accuracy within ~2% of the full prompt.
CLExEval introduces a human-annotated evaluation framework on 40 rare cases that identifies verbosity bias, hidden knowledge paradox, and 68.6% reasoning-to-output mismatch in LLMs while showing LLM-as-a-Judge overestimates reliability.
Steering LLM residual streams with random sparse vectors creates detectable self-recognition fingerprints that enable over 98% accurate attribution of generated text to specific models without degrading output quality.
A majorization-minimization framework turns IRT into scalable matrix factorization subproblems for LLM evaluation, delivering orders-of-magnitude speedups with identifiability guarantees.
Factorized Active Querying (FAQ) provides up to 5 times more effective samples for LLM accuracy estimation by using Bayesian factor models and adaptive querying under a fixed budget with guaranteed coverage.
LexGenius benchmark reveals that even the strongest LLMs show major gaps in legal intelligence and lag behind human professionals.
NuclearQAv2 is a hybrid-constructed benchmark dataset for evaluating LLM competence in nuclear engineering knowledge using three question types.
PolicyAlign aligns LLMs to natural-language safety policies by synthesizing violating instructions and performing on-policy self-distillation with policy-sensitive filtering, improving safety without high-quality supervision data.
LCAE is introduced as a Rasch-model metric that aligns LLM self-reported confidence with latent error probability derived from ability and item difficulty, shown to improve calibration on a medical dataset across 20 models.
citing papers explorer
-
VertMark: A Unified Training-Free Robust Watermarking Framework for Vertical Domain Pre-trained Language Models
VertMark embeds robust, training-free watermarks into vertical domain language models by creating hidden semantic equivalence between low-frequency triggers and high-frequency domain terms via parameter swaps, supporting reliable verification with negligible performance impact.
-
Large Language Models Exhibit Normative Conformity
Large language models exhibit normative conformity in addition to informational conformity, and subtle social context can direct which group they conform to.
-
Prompt Compression via Activation Aggregation
A learned weighted sum of intermediate-layer activations compresses an instruction prompt into a single patch vector that, injected at an early layer, recovers task accuracy within ~2% of the full prompt.
-
CLExEval: A Human-in-the-Loop Framework for Qualitative Evaluation of LLM Clinical Reasoning
CLExEval introduces a human-annotated evaluation framework on 40 rare cases that identifies verbosity bias, hidden knowledge paradox, and 68.6% reasoning-to-output mismatch in LLMs while showing LLM-as-a-Judge overestimates reliability.
-
LLM Self-Recognition: Steering and Retrieving Activation Signatures
Steering LLM residual streams with random sparse vectors creates detectable self-recognition fingerprints that enable over 98% accurate attribution of generated text to specific models without degrading output quality.
-
An Interpretable and Scalable Framework for Evaluating Large Language Models
A majorization-minimization framework turns IRT into scalable matrix factorization subproblems for LLM evaluation, delivering orders-of-magnitude speedups with identifiability guarantees.
-
Efficient Evaluation of LLM Performance with Statistical Guarantees
Factorized Active Querying (FAQ) provides up to 5 times more effective samples for LLM accuracy estimation by using Bayesian factor models and adaptive querying under a fixed budget with guaranteed coverage.
-
LexGenius: An Expert-Level Benchmark for Large Language Models in Legal General Intelligence
LexGenius benchmark reveals that even the strongest LLMs show major gaps in legal intelligence and lag behind human professionals.
-
NuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Language Models
NuclearQAv2 is a hybrid-constructed benchmark dataset for evaluating LLM competence in nuclear engineering knowledge using three question types.
-
PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models
PolicyAlign aligns LLMs to natural-language safety policies by synthesizing violating instructions and performing on-policy self-distillation with policy-sensitive filtering, improving safety without high-quality supervision data.
-
Latent Confidence Alignment for LLM Self-Assessment
LCAE is introduced as a Rasch-model metric that aligns LLM self-reported confidence with latent error probability derived from ability and item difficulty, shown to improve calibration on a medical dataset across 20 models.