Language-Induced Priors from LLMs guide source selection in cold-start domain adaptation through an EM algorithm, matching oracle MSE under a correct prior and remaining asymptotically consistent.
hub
Advances in neural information processing systems , volume=
24 Pith papers cite this work. Polarity classification is still indexing.
24
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
unclear 1representative citing papers
LLMs copy biased analyst ratings in investment decisions but a new detection method encourages independent reasoning and can improve stock return predictions beyond human levels.
LOVER creates an unsupervised logic-regularized verifier that reaches 95% of supervised verifier performance on reasoning tasks across 10 datasets.
Retrieving structured thinking traces as a corpus improves reasoning performance on AIME, LiveCodeBench, and GPQA over standard RAG or no retrieval.
Validity-calibrated reasoning distillation improves transfer of reasoning skills by modulating updates based on relative local validity of next steps instead of enforcing full trajectory imitation.
o1-like models overthink easy tasks; self-training reduces compute use without accuracy loss on GSM8K, MATH500, GPQA, and AIME.
Time-LLM reprograms frozen LLMs for time series forecasting via text prototypes and Prompt-as-Prefix, outperforming specialized models in standard, few-shot, and zero-shot settings.
EvoPrompt uses LLMs to run evolutionary operators on populations of prompts, outperforming human-engineered prompts by up to 25% on BIG-Bench Hard tasks across 31 datasets.
CES applies conditional bidirectional entropy control on top of DAPO to improve accuracy and shorten responses on mathematical benchmarks for 7B and 1.5B LLMs.
Frontier LLMs exhibit bias from stigmatizing language in clinical vignettes across four conditions, skewing decisions toward less aggressive management, with limited mitigation from Chain-of-Thought or self-debiasing prompts.
Many-shot CoT-ICL improves when demonstrations are ordered for smooth conceptual progression, with CDS delivering up to 5.42 percentage-point gains on math tasks using 64 examples.
Weighted rules extend stable model semantics to support probabilistic reasoning, model ranking, and statistical inference in answer set programs.
RKU is a curvature-aware structural pruning framework that improves LLM reasoning accuracy at 40% sparsity, reaching 13.34% on GSM8K while outperforming baselines and better preserving out-of-distribution representations.
OPT-BENCH and OPT-Agent evaluate LLM self-optimization in large search spaces, showing stronger models improve via feedback but stay constrained by base capacity and below human performance.
BoundaryRouter routes queries to LLM or agent using early experience memory from a seed set, cutting inference time 60.6% versus always using agents and raising performance 28.6% versus always using direct LLM inference.
GraphMind equips LLM agents with graph awareness to construct human-like social networks, producing botnets that substantially degrade performance of both text-based and graph-based detectors.
Chain-of-Verification reduces hallucinations in large language models by drafting responses, planning independent verification questions, answering them separately, and generating a final verified output.
D²Evo mines medium-difficulty anchors from the current model, trains a Questioner to generate matching questions, and jointly optimizes Solver and Questioner for progressive gains, outperforming baselines on math reasoning with under 2K real samples.
LLMs generally fail to maintain stable worldviews under adversarial conversational pressure, indicating they lack core beliefs akin to those in human cognition.
ARGUS uses a Prosecutor-Defender-Umpire multi-agent setup plus RAG and chain-of-thought rewards to adapt ad policy enforcement to new regulations using minimal fresh labels.
A formalized Minimal Cognitive Grid ranks computational models of analogy and metaphor by alignment with cognitive theories using Functional/Structural Ratio, Generality, and Performance Match dimensions.
FedProxy replaces weak adapters with a proxy SLM for federated LLM fine-tuning, outperforming prior methods and approaching centralized performance via compression, heterogeneity-aware aggregation, and training-free fusion.
Multi-agent debate with tit-for-tat arguments and a judge LLM improves reasoning by preventing LLMs from locking into incorrect initial solutions.
citing papers explorer
-
Weighted Rules under the Stable Model Semantics
Weighted rules extend stable model semantics to support probabilistic reasoning, model ranking, and statistical inference in answer set programs.
-
OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces
OPT-BENCH and OPT-Agent evaluate LLM self-optimization in large search spaces, showing stronger models improve via feedback but stay constrained by base capacity and below human performance.
-
Structural Ranking of the Cognitive Plausibility of Computational Models of Analogy and Metaphors with the Minimal Cognitive Grid
A formalized Minimal Cognitive Grid ranks computational models of analogy and metaphor by alignment with cognitive theories using Functional/Structural Ratio, Generality, and Performance Match dimensions.
- Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization