Tag
Proposes Token-Level Off-Policy Labeling (TOPL), an off-policy training paradigm for faithful generation that reframes post-training as token-level correctness prediction, achieving strong out-of-distribution generalization across summarization and machine translation tasks.
OriginBlame is a record- and token-level data provenance system that propagates author identity through AI training data pipelines, enabling precise forget sets for machine unlearning. It eliminates over-deletion from dataset-level systems and improves unlearning effectiveness.
A research paper introducing Canon, a label-free self-distillation method that uses consensus among sampled solutions to provide dense token-level supervision for training large language models on reasoning tasks, improving pass@1 by up to 12 points and outperforming label-free reinforcement learning at a fraction of the compute.
Proposes Tail-Aware Credit Calibration (TACO) to address positive-credit contamination in LLM reinforcement learning by calibrating uniform credit assignment to suppress updates on implausible tail tokens, improving training stability and performance.
This paper investigates token-level attention shifts in multimodal large language models during generation, revealing consistent patterns and proposing a simple test-time intervention that significantly improves task performance.
TokenScope is an interactive interpretability tool for decoder-only large language models that provides token-level metrics, attention patterns, and counterfactual branching during code generation, enabling systematic investigation of model behavior.
Proposes CORTEX, a token-level hallucination detection method for RAG that compares LLM internal representations with and without retrieved documents to identify ungrounded spans. It improves fine-grained localization of hallucinations in long-form RAG outputs.
This paper analyzes token-level prediction differences between transformers and hybrid attention-recurrent models using Olmo 3 and Olmo Hybrid, finding that hybrids improve on semantic state tracking while transformers excel at n-gram copying and syntactic bracket matching.
Introduces Independent Combinatorial Tokens (ICT) framework that uses Jensen-Shannon divergence between token logit distributions to identify critical branching points, preventing entropy collapse and explosion in RLVR for LLM reasoning. Achieves up to 14.9% pass@4 improvement on Qwen models.
STARE addresses policy entropy collapse in GRPO-based reinforcement learning for large language models by introducing surprisal-guided token-level advantage reweighting and target-entropy regulation, achieving 4%-8% accuracy gains on AIME benchmarks.
This paper characterizes two distinct processes by which language models fail in reasoning—committed failure and persistent uncertainty—using token-level uncertainty signals, and demonstrates implications for self-consistency and failure detection strategies.
This paper identifies a structural failure mode in token-level credit assignment for LLM reinforcement learning when using LoRA, where intrinsic signals degenerate. It proposes Adapter-Residual Credit Assignment (ARCA), which derives token salience from adapter hidden-state residuals and remains competitive with baselines.
RAGognizer introduces a hallucination-aware fine-tuning approach that integrates a lightweight detection head into LLMs for joint optimization of language modeling and hallucination detection in RAG systems. The paper presents RAGognize, a dataset of naturally occurring closed-domain hallucinations with token-level annotations, and demonstrates state-of-the-art hallucination detection while reducing hallucination rates without degrading language quality.