Mult-DPO provides a tractable multinomial surrogate for set-wise preference optimization in DPO that upper bounds the Plackett-Luce based loss for LLM recommender systems.
hub Canonical reference
Aligning large language models with human: A survey
Canonical reference. 88% of citing Pith papers cite this work as background.
27
Pith papers citing it
54
external citations · external index
Background
88% of classified citations
hub tools
citation-role summary
background 7
method 1
citation-polarity summary
representative citing papers
LLMs match condition-level patterns in a noodle purchase survey but fail to replicate distributional structure, with no model beating a pooled human baseline for purchase quantities.
P²-DPO generates on-policy preference pairs targeting focus-and-enhance perception and visual robustness, combined with a calibration loss, to reduce hallucinations in LVLMs more effectively than human-feedback baselines.
A multiplayer indirect reciprocity framework shows that group cooperation is stabilized by the 'all good, help; one bad, halt' rule, producing bistability and hysteresis unlike monostable pairwise models.
Maximizing joint conditional mutual information I(Y; C_Z, W, Z | X) decomposes multi-objective LLM alignment into preference-specific DPO terms plus an I(Y;W|X) exploration term that reduces reward-distribution overlap.
LLM agents reproduce macro-level cooperation decline and stabilization in networked Prisoner's Dilemma but underestimate individual heterogeneity and produce different conditional cooperation rules than humans.
Sycophancy fine-tuning induces emergent misalignment in LLMs that Alignment Gating can reverse by learning to suppress unsafe representations with generalization from narrow to broad domains.
SCA applies the Information Bottleneck principle via NIBS and GIBS methods to identify erroneous steps in black-box LLM reasoning and boosts self-correction success by up to 13.5%.
SWIM aligns cross-attention maps from object nouns to ground-truth masks during training on the new NL-Refer dataset to enable text-only fine-grained video object understanding in MLLMs.
Response times modeled as drift-diffusion processes enable consistent estimation of population-average preferences from heterogeneous anonymous binary choices.
PERSA combines RLHF with selective parameter-efficient updates to top transformer layers, raising style alignment scores from 35% to 96% on code feedback benchmarks while holding correctness near 100%.
A survey of LLM-based autonomous agents that proposes a unified framework for their construction and reviews applications in social science, natural science, and engineering along with evaluation methods and future directions.
The paper introduces 'editorial alignment' as a participatory design practice that treats editorial standards as design artifacts to guide LLM behavior in knowledge dissemination, shown through workshops at one Nordic institution.
Transformer model with response-time auxiliary input adapts reward models to unseen human preference domains via in-context learning from demonstrations.
SSAS improves LLM sentiment prediction consistency and data quality by up to 30% on three review datasets via syntactic and semantic context assessment summarization.
LLM post-training is unified as off-policy or on-policy interventions that expand support for useful behaviors, reshape policies within reachable states, or consolidate behavior across training stages.
POPI distills user preferences into reusable natural-language summaries via a shared inference model and conditions a generator on them, trained jointly with RL to improve personalization quality while cutting context length by up to 10x on benchmarks.
LLMs override explicit source evidence with internal knowledge when modeling business processes, creating a measurable reliability risk in analytical tasks.
BV-Blend blends prompt-local and semantic-cluster historical reward statistics via SEM-derived weights to stabilize critic-free RL advantage estimation.
Feeding LLM tutors a text description or AUM-selected frame of a student's facial expression improves rated empathetic responsiveness across three backbones.
A survey consolidating frameworks, data practices, large action models, benchmarks, applications, and research gaps in LLM-brained GUI agents.
Baichuan 2 presents 7B and 13B LLMs trained on 2.6T tokens that match or exceed similar open models on MMLU, CMMLU, GSM8K, HumanEval and excel in medicine and law.
A systematic literature review that organizes recent work on LLMs for code generation into a taxonomy covering data curation, model advances, evaluations, ethics, environmental impact, and applications, with benchmark comparisons.
A systematic review of memory designs, evaluation methods, applications, limitations, and future directions for LLM-based agents.
citing papers explorer
-
Response Time Enhances Alignment with Heterogeneous Preferences
Response times modeled as drift-diffusion processes enable consistent estimation of population-average preferences from heterogeneous anonymous binary choices.