Related papers: Valid Stopping for LLM Generation via Empirical Dynamic Formal Lift

Related papers

ReDraft, Don't Just Distill: Reference-Driven Revision for Continual VLLM Post-Training [66.72708893922605]
Post-training of large multimodal models should add new capabilities while preserving those from pre-training.<n>SFT gives explicit target supervision that learns a task from near-zero accuracy, but its off-policy targets move the model far enough to cause forgetting.<n>We introduce ReDraft, which obtains both from the model's own failures.
arXiv Detail & Related papers (2026-09-15T04:59:03Z)
Verification-Aware Training for Speculative Decoding [57.84976863792784]
We introduce Verification-Aware Training (VAT), a plug-in framework that simulates verification at every training step and turns the resulting accept and reject patterns into supervision.<n>VAT modifies only the training objective, so it can be layered on top of existing methods without changing the draft architecture, the target model, or the inference procedure.<n>VAT improves average acceptance length by up to 11.4% and wall-clock speedup by up to 8.7%, with consistent gains across math, code, and chat benchmarks.
arXiv Detail & Related papers (2026-08-31T01:42:10Z)
Post-Hoc Trajectory-Risk Certification for Modular LLM-Based Security Agents [1.4915002678801434]
We show that Bonferroni allocation is distribution-free but conservative under correlated errors.<n> coarse-to-fine label selection can create near-perfect measured correlation without learned dependence.<n>A modular certificate using per-stage certificates and a pairwise overlap bound yields a positive average gain of 0.6%.
arXiv Detail & Related papers (2026-08-04T23:48:36Z)
Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata [57.27430779838529]
We present an exact and tractable algorithm for sampling from the constrained mean-field posterior under any constraint expressible as a finite automaton.<n>The approach guarantees constraint satisfaction by construction, supports both greedy and sampling-based decoding, and is compatible with parallel and block-wise decoding.<n> Empirical evaluations on Dream-7B and LLaDA-8 show substantial accuracy gains across various tasks.
arXiv Detail & Related papers (2026-07-08T05:48:57Z)
Reliability-Asymmetric Spacecraft Autonomy: Co-Designing a Capable Learned GNC Stack with a Verified, Adaptation-Aware Runtime Shield [2.28438857884398]
Rule-based autonomy is certifiable but brittle, while learned autonomy is capable but hard to verify.<n>We present AMPLE-GNC, a three-tier guidance, navigation, and control stack.<n>Fine-tuning a pretrained 360M model with grammar-constrained decoding gives a hard output-validity guarantee.<n>We show that a latching safe-hold shield can suppress even a capable controller.
arXiv Detail & Related papers (2026-06-24T03:55:21Z)
CaliDist: Calibrating Large Language Models via Behavioral Robustness to Distraction [51.56484100374058]
Existing calibration methods for Large Language Models (LLMs) often overlook a critical dimension of trustworthiness: a model's behavioral robustness.<n>We introduce textscCaliDist, a novel post-hoc calibration approach that directly measures and penalizes a model's susceptibility to distraction.<n>textscCaliDist consistently achieves lower Expected Error (ECE) and Brier Score compared with strong baselines.
arXiv Detail & Related papers (2026-06-04T07:27:53Z)
Knowing but Not Correcting: Routine Task Requests Suppress Factual Correction in LLMs [26.062372963777452]
LLMs reliably correct false claims when presented in isolation, yet when the same claims are embedded in task-oriented requests, they often comply rather than correct.<n>We term this failure mode emphcorrection suppression and construct a benchmark of 300 false premises to systematically evaluate it across eight models.<n> Suppression rates range from 19% to 90%, with four models exceeding 80%, establishing correction suppression as a prevalent and severe phenomenon.
arXiv Detail & Related papers (2026-05-07T10:04:39Z)
Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning [17.384089089363382]
We identify a root cause that existing methods overlook: the uniform penalization of errors.<n>Current approaches treat all incorrect rollouts within a group identically.<n>We propose the Asymmetric Confidence-aware Error Penalty (ACE)
arXiv Detail & Related papers (2026-02-24T22:46:43Z)
BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning [73.46118996284888]
Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence.<n>We propose BadCLIP++, a unified framework that tackles both challenges.<n>For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions.<n>For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment.
arXiv Detail & Related papers (2026-02-19T08:31:16Z)
InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning [32.274434679047395]
Outcome-reward reinforcement learning (RL) has proven effective at improving the reasoning capabilities of large language models (LLMs)<n>Standard RL assigns credit only at the level of the final answer, penalizing entire reasoning traces when the outcome is incorrect.<n>We introduce Intervention Training (InT), a training paradigm in which the model performs fine-grained credit assignment on its own reasoning traces.
arXiv Detail & Related papers (2026-01-20T18:15:38Z)
EDIT: Early Diffusion Inference Termination for dLLMs Based on Dynamics of Training Gradients [6.736735746633275]
Diffusion-based large language models (dLLMs) refine token generations through iterative denoising, but answers often stabilize before all steps complete.<n>We propose EDIT, an inference-time criterion that adaptively stops denoising once sufficient reasoning stability relative to training-time reasoning is detected.
arXiv Detail & Related papers (2025-11-29T23:47:47Z)
STABLE: Gated Continual Learning for Large Language Models [0.0]
STABLE is a gated continual self editing framework that constrains forgetting during sequential updates.<n>Each candidate edit is evaluated against a stability budget using one of three metrics.<n>Experiments on the Qwen-2.5-7B model show that gating effectively mitigates forgetting while preserving adaptability.
arXiv Detail & Related papers (2025-10-17T16:14:05Z)
Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
arXiv Detail & Related papers (2025-10-01T13:56:44Z)
Abduct, Act, Predict: Scaffolding Causal Inference for Automated Failure Attribution in Multi-Agent Systems [20.846301581161978]
Failure attribution in multi-agent systems is a critical yet unsolved challenge.<n>Current methods treat this as a pattern recognition task over long conversation logs.<n>A2P Scaffolding transforms failure attribution from pattern recognition into a structured causal inference task.
arXiv Detail & Related papers (2025-09-12T16:51:15Z)
Unlearning at Scale: Implementing the Right to be Forgotten in Large Language Models [0.0]
Our approach treats as a minimal program and logs permicrobatch record.<n>Under pinned stack and deterministic kernels, replaying the training tail yields the same parameters as training retain set.
arXiv Detail & Related papers (2025-08-17T03:29:22Z)
Distributed Training under Packet Loss [8.613477072763404]
Leveraging unreliable connections will reduce latency but may sacrifice model accuracy and convergence once packets are dropped.<n>We introduce a principled, end-to-end solution that preserves accuracy and convergence guarantees under genuine packet loss.<n>This work bridges the gap between communication-efficient protocols and the accuracy and guarantees demanded by modern large-model training.
arXiv Detail & Related papers (2025-07-02T11:07:20Z)
Boosting LLM Reasoning via Spontaneous Self-Correction [43.4980625253775]
One of the approaches for improving math reasoning is self-correction.<n>Existing self-correction approaches treat corrections as standalone post-generation refinements.<n>We propose SPOC, a spontaneous self-correction approach that enables LLMs to generate interleaved solutions and verifications in a single inference pass.
arXiv Detail & Related papers (2025-06-07T21:23:00Z)
S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning [51.84977135926156]
We introduce S$2$R, an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference.<n>Our results demonstrate that Qwen2.5-math-7B achieves an accuracy improvement from 51.0% to 81.6%, outperforming models trained on an equivalent amount of long-CoT distilled data.
arXiv Detail & Related papers (2025-02-18T13:40:22Z)
Training Language Models to Self-Correct via Reinforcement Learning [98.35197671595343]
Self-correction has been found to be largely ineffective in modern large language models (LLMs) We develop a multi-turn online reinforcement learning approach, SCoRe, that significantly improves an LLM's self-correction ability using entirely self-generated data. We find that SCoRe achieves state-of-the-art self-correction performance, improving the base models' self-correction by 15.6% and 9.1% respectively on MATH and HumanEval.
arXiv Detail & Related papers (2024-09-19T17:16:21Z)
Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable [70.77600345240867]
A novel arbitrary-in-arbitrary-out (AIAO) strategy makes watermarks resilient to fine-tuning-based removal. Unlike the existing methods of designing a backdoor for the input/output space of diffusion models, in our method, we propose to embed the backdoor into the feature space of sampled subpaths. Our empirical studies on the MS-COCO, AFHQ, LSUN, CUB-200, and DreamBooth datasets confirm the robustness of AIAO.
arXiv Detail & Related papers (2024-05-01T12:03:39Z)
Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent [97.64313409741614]
We propose to enforce a emphconsistency property which states that predictions of the model on its own generated data are consistent across time. We show that our novel training objective yields state-of-the-art results for conditional and unconditional generation in CIFAR-10 and baseline improvements in AFHQ and FFHQ.
arXiv Detail & Related papers (2023-02-17T18:45:04Z)
Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods [24.190587751595455]
Weak supervision is a popular method for building machine learning models without relying on ground truth annotations. Existing approaches use latent variable estimation to model the noisy sources. We show that for a class of latent variable models highly applicable to weak supervision, we can find a closed-form solution to model parameters. We use this insight to build FlyingSquid, a weak supervision framework that runs orders of magnitude faster than previous weak supervision approaches.
arXiv Detail & Related papers (2020-02-27T07:51:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.