Pith. sign in

REVIEW 23 cited by

Challenges and Applications of Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2307.10169 v1 pith:AD5S3JNV submitted 2023-07-19 cs.CL cs.AIcs.LG

Challenges and Applications of Large Language Models

classification cs.CL cs.AIcs.LG
keywords applicationchallengesfieldlanguagelargemodelsalreadyapplications
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large Language Models (LLMs) went from non-existent to ubiquitous in the machine learning discourse within a few years. Due to the fast pace of the field, it is difficult to identify the remaining challenges and already fruitful application areas. In this paper, we aim to establish a systematic set of open problems and application successes so that ML researchers can comprehend the field's current state more quickly and become productive.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 23 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. CacheTrap: Unveiling a Stealthier Gray-Box Trojan against LLMs

    cs.CR 2025-11 conditional novelty 8.0

    CacheTrap achieves 100% targeted attack success on five open-source LLMs by using an efficient search to locate and flip a single bit in the KV cache as a transient trigger, while preserving normal accuracy without th...

  2. ACL-Verbatim: hallucination-free question answering for research

    cs.CL 2026-05 unverdicted novelty 7.0

    The work creates a new ground truth dataset for mapping queries to verbatim text spans in research papers and shows a 150M-parameter ModernBERT token classifier achieving 53.6 word-level F1, outperforming LLM extracto...

  3. RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs

    cs.LG 2026-05 unverdicted novelty 7.0

    RouteHijack is a routing-aware jailbreak that identifies safety-critical experts via activation contrast and optimizes suffixes to suppress them, reaching 69.3% average attack success rate on seven MoE LLMs with stron...

  4. NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions

    cs.DB 2026-04 conditional novelty 7.0

    NL2SQLBench is a new modular benchmarking framework that evaluates LLM NL2SQL methods across three core modules on existing datasets, exposing large accuracy gaps and computational inefficiency.

  5. Retrieval-Augmented Large Language Models for Evidence-Informed Guidance on Cannabidiol Use in Older Adults

    cs.IR 2026-01 unverdicted novelty 7.0

    Retrieval-augmented LLMs produce more cautious and guideline-aligned recommendations on cannabidiol for older adults than standalone models, demonstrated via automated evaluation on 64 diverse scenarios.

  6. FastTPS: An Optimized Method for LLM Token Phase for AI accelerators

    cs.LG 2026-07 conditional novelty 6.0

    FastTPS accelerates LLM token-phase inference via reloading-free static KV-cache management, tiled fused RoPE attention, and interlaced-weight MLP fusion, yielding up to 6× speedup at 93% bandwidth on AMD NPUs.

  7. Interpreting learning dynamics of autoencoders: Transient scaling and emerging concepts of the Ising model

    cs.LG 2026-07 conditional novelty 6.0

    Unsupervised autoencoders on Ising configurations form magnetization then energy representations in two dynamical regimes, with recursive error flow fields sharing topology across layers.

  8. Agentic and Generative AI for Open-Source Intelligence and Cyber Investigations: Taxonomy, Evaluation, Challenges, and Future Directions

    cs.CR 2026-07 conditional novelty 6.0

    Across 74 OSINT/CTI AI studies, hallucination is widely named but end-to-end measured in only one non-reproducible system, so a human–AI co-pilot is the most defensible near-term architecture.

  9. On the Limits of Prompt-Conditioned Language Models as General-Purpose Learners

    cs.LG 2026-06 unverdicted novelty 6.0

    Prompt-conditioned LLMs face irreducible error floors from language's limited information capacity and alignment constraints, proven via PAC-Bayes bounds on bilevel cheap-talk games for certain task families.

  10. SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scaling

    cs.CL 2026-05 unverdicted novelty 6.0

    SuperValid synthesizes capability-aligned OOD validation data to produce a training-free loss metric that correlates with downstream benchmark performance across model architectures, scales, and data distributions.

  11. Towards Large Model Feature Coding

    cs.CV 2026-05 unverdicted novelty 6.0

    LaMoFCBench is a new benchmark covering 4 categories and 16 scenarios that exposes misalignment between mainstream feature codecs and the heterogeneous statistics of large-model activations.

  12. Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination

    cs.MM 2026-05 unverdicted novelty 6.0

    LVLMs show vocabulary hijacking by inert tokens that decode to hijacking anchors; HABI locates them, NHAR finds resilient heads, and HAVAE boosts those heads to cut hallucinations.

  13. SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving

    cs.LG 2026-04 unverdicted novelty 6.0

    Token-wise INT4 KV-cache quantization plus block-diagonal Hadamard rotation recovers nearly all accuracy lost by naive INT4 while adding zero end-to-end overhead under paged serving constraints.

  14. LeakyCLIP: Extracting Training Data from CLIP

    cs.CR 2025-08 conditional novelty 6.0

    LeakyCLIP reconstructs images from CLIP embeddings with over 258% SSIM gain versus baselines and enables membership inference from reconstruction metrics on LAION-2B data.

  15. LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

    cs.SE 2024-03 unverdicted novelty 6.0

    LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.

  16. Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations

    cs.AI 2023-12 conditional novelty 6.0

    Math-Shepherd is an automatically trained process reward model that scores solution steps to verify and reinforce LLMs, lifting Mistral-7B from 77.9% to 89.1% on GSM8K and 28.6% to 43.5% on MATH.

  17. Semantic Drift and the Stability of Operator Control in Reasoning-Class Decision Support Systems

    cs.AI 2026-07 conditional novelty 5.5

    Reasoning LLMs in ultra-long sessions exhibit latent semantic drift that inverts operator control; a fitted stability coefficient Ks detects the bifurcation and a latent-steering arbitrator is proposed to restore it.

  18. U-Define: Designing User Workflows for Hard and Soft Constraints in LLM-Based Planning

    cs.AI 2026-05 unverdicted novelty 5.0

    U-Define improves user control in LLM planning by letting people define hard rules and soft preferences in natural language with matching verification methods, raising usefulness and satisfaction scores.

  19. SplitFT: An Adaptive Federated Split Learning System For LLMs Fine-Tuning

    cs.DC 2026-04 unverdicted novelty 5.0

    SplitFT adapts cut-layer selection and reduces LoRA rank per client in federated split learning to improve efficiency and performance when fine-tuning LLMs on heterogeneous devices and data.

  20. What Is The Political Content in LLMs' Pre- and Post-Training Data?

    cs.CL 2025-09 unverdicted novelty 5.0

    Training data for open LLMs is systematically left-leaning, with pre-training corpora containing more political material than post-training data and model stances aligning with data distributions.

  21. SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning

    cs.RO 2025-03 unverdicted novelty 5.0

    SafeVLA applies constrained reinforcement learning via CMDP min-max optimization to VLAs, cutting safety violation costs by 83.58% while preserving task success on long-horizon mobile manipulation tasks.

  22. Preserving Knowledge in Large Language Model with Model-Agnostic Self-Decompression

    cs.CL 2024-06 unverdicted novelty 5.0

    Introduces Tree Generation (TG-SFT) to generate synthetic instruction-tuning data from LLMs, reducing catastrophic forgetting when fine-tuning MLLMs on domain-specific or multimodal data.

  23. Large Language Models: A Survey

    cs.CL 2024-02 accept novelty 3.0

    The paper surveys key large language models, their training methods, datasets, evaluation benchmarks, and future research directions in the field.