Conformal Selective Acting (CSA) fills a gap in conformal methods by providing per-round, pathwise-valid selective risk bounds for adaptive RLVR LLM streams under predictable updates and isotonic calibration.
Title resolution pending
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
years
2026 10representative citing papers
Process sidecars use a secant-based two-parameter edit to achieve second-order accurate memory revocation after safety training, outperforming scalar task arithmetic on refusal tasks across three models.
Synthetic training data designed to break the correlation between semantic and preferential signals in text embeddings provably improves preference prediction across 11 online deliberation datasets.
PRISM weights target examples by model preference to build an improved direction for influence-based data selection in LLM fine-tuning.
GraSP-VL turns frozen VLM embedding length into a controllable semantic granularity interface via a learned shared prefix transform that creates a Semantic Matryoshka structure.
PopuLoRA shows that co-evolving populations of LoRA adapters through cross-evaluated self-play can outperform compute-matched single-agent baselines on multiple code and math reasoning benchmarks.
SCALE-LoRA proposes a post-retrieval audit framework using sparse residual composition and disagreement-based reliability signals to improve open-pool LoRA adapter reuse on tasks like BIG-Bench Hard.
Authors call for contamination-resistant LLM benchmarks that exploit Transformer training-inference asymmetry and require new mathematical methods for cross-architecture interoperability.
A pipeline with LoRA-fine-tuned query rewriting, BM25+dense hybrid retrieval via RRF, and cross-encoder reranking reaches nDCG@5 of 0.531 on multi-turn retrieval across four domains.
An ensemble of per-language fine-tuned Gemma 3 models with three synthetic data strategies and per-language threshold tuning achieves 2nd place overall in SemEval-2026 Task 9 with mean macro-F1 of 0.811.
citing papers explorer
-
Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs
Conformal Selective Acting (CSA) fills a gap in conformal methods by providing per-round, pathwise-valid selective risk bounds for adaptive RLVR LLM streams under predictable updates and isotonic calibration.
-
Revocable Learned State via Process Sidecars
Process sidecars use a secant-based two-parameter edit to achieve second-order accurate memory revocation after safety training, outperforming scalar task arithmetic on refusal tasks across three models.
-
Embeddings for Preferences, Not Semantics
Synthetic training data designed to break the correlation between semantic and preferential signals in text embeddings provably improves preference prediction across 11 online deliberation datasets.
-
PRISM: Preference-Aware Influence Function Based Data Selection Method for Efficient Fine-Tuning
PRISM weights target examples by model preference to build an improved direction for influence-based data selection in LLM fine-tuning.
-
GraSP-VL: Length as a Semantic Granularity Interface for Vision-Language Representations
GraSP-VL turns frozen VLM embedding length into a controllable semantic granularity interface via a learned shared prefix transform that creates a Semantic Matryoshka structure.
-
PopuLoRA: Co-Evolving LLM Populations for Reasoning Self-Play
PopuLoRA shows that co-evolving populations of LoRA adapters through cross-evaluated self-play can outperform compute-matched single-agent baselines on multiple code and math reasoning benchmarks.
-
SCALE-LoRA: Auditing Post-Retrieval LoRA Composition with Residual Merging and View Reliability
SCALE-LoRA proposes a post-retrieval audit framework using sparse residual composition and disagreement-based reliability signals to improve open-pool LoRA adapter reuse on tasks like BIG-Bench Hard.
-
LLM Benchmark Datasets Should Be Contamination-Resistant
Authors call for contamination-resistant LLM benchmarks that exploit Transformer training-inference asymmetry and require new mathematical methods for cross-architecture interoperability.
-
Caraman at SemEval-2026 Task 8: Three-Stage Multi-Turn Retrieval with Query Rewriting, Hybrid Search, and Cross-Encoder Reranking
A pipeline with LoRA-fine-tuned query rewriting, BM25+dense hybrid retrieval via RRF, and cross-encoder reranking reaches nDCG@5 of 0.531 on multi-turn retrieval across four domains.
-
PSK at SemEval-2026 Task 9: Multilingual Polarization Detection Using Ensemble Gemma Models with Synthetic Data Augmentation
An ensemble of per-language fine-tuned Gemma 3 models with three synthetic data strategies and per-language threshold tuning achieves 2nd place overall in SemEval-2026 Task 9 with mean macro-F1 of 0.811.