BALTO projects claim-level verification into balanced token-level rewards for RL-based hallucination mitigation in LLMs.
Reducing hallucination in structured outputs via retrieval-augmented generation
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
CacheClip accelerates RAG prefill by up to 3.33x via auxiliary-model-guided selective KV recomputation while retaining 85-91% of full-attention quality on NIAH and LongBench.
LLM agents enable universal interoperability by serving as automatic translators and adapters between proprietary digital services.
RAG-enhanced LLMs show generally positive effects on automated test generation and code inspection by supplying supplementary context that reduces hallucinations.
TerraMARS is an end-to-end pipeline using a QLoRA-fine-tuned Gemma 3 1B model to extract Mars terraforming knowledge from literature into QA answers and JSON-structured outputs.
citing papers explorer
-
BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation
BALTO projects claim-level verification into balanced token-level rewards for RL-based hallucination mitigation in LLMs.
-
CacheClip: Accelerating RAG with Effective KV Cache Reuse
CacheClip accelerates RAG prefill by up to 3.33x via auxiliary-model-guided selective KV recomputation while retaining 85-91% of full-attention quality on NIAH and LongBench.
-
LLM Agents Are the Antidote to Walled Gardens
LLM agents enable universal interoperability by serving as automatic translators and adapters between proprietary digital services.
-
Enhancing Large Language Models with Retrieval Augmented Generation for Software Testing and Inspection Automation
RAG-enhanced LLMs show generally positive effects on automated test generation and code inspection by supplying supplementary context that reduces hallucinations.
-
TerraMARS: A Domain-Adapted Small-Language-Model Pipeline for Mars Terraforming Literature
TerraMARS is an end-to-end pipeline using a QLoRA-fine-tuned Gemma 3 1B model to extract Mars terraforming knowledge from literature into QA answers and JSON-structured outputs.