Existing information extraction (IE) tasks increasingly adopt in-context learning (ICL) with large language models. However, current approaches either show inconsistent performance across model scales or lack systematic optimization and generalizability. Building on this, we propose BCL-IE (Bayesian In-Context Learning Framework for Information Extraction), the first optimization framework that uses particle filtering with Bayesian updates to systematically refine label representations across IE tasks. Through four steps—initialization, observation, weight update, and resampling, BCL-IE generalizes to both sequence labeling and relation classification paradigms. Extensive experiments demonstrate substantial improvements over existing approaches (up to 30%), achieving prior performance while other methods either fail to generalize or show limited effectiveness.

Test-time scaling (TTS) enhances LLM reasoning capabilities by sampling and aggregating diverse solution trajectories. However, existing approaches often rely on external verifiers and one-shot independent sampling, which results in inefficient budget allocation and underutilizes interim high-quality trajectories. We propose ConMA, a training-free, verifier-free TTS framework that reallocates a fixed inference budget into iterative sample–filter–diversify–select cycles: it filters answer groups based on intrinsic token-probability confidence, enriches candidates through diversity-aware expansion, and employs repeated single-choice selection for multi-stage refinement. Across multiple benchmarks, ConMA consistently improves accuracy under fixed budgets. With a maximum budget of N=64, ConMA boosts Qwen3-4B to 80% accuracy on AIME25, significantly outperforming strong baselines while converging early with only 18 samples on average, substantially reducing inference cost.

Recent advancements in the application of Large Language Models (LLMs) to formal theorem proving in Lean have unveiled new prospects in complex logical reasoning scenarios. Acknowledging that the difficulty across reasoning steps in a formal theorem proof is not uniform, prior proof search algorithms have not systematically investigated which proof steps are more crucial to explore. This paper introduces Entropy-Based Best-First Search (EBFS), an entropy-inspired heuristic tree search algorithm that enhances the efficiency of proof generation models to explore proof trees, thereby increasing the probability of finding the correct proof. We also introduce a reinforcement fine-tuning approach specifically for proof tree search. Using EBFS during the generation stage further boosts the model’s performance in proof generation. Evaluations demonstrate that our fine-tuned EBFS model achieves consistent improvements over the baseline models. Under the same sample budget, it outperforms whole proof generation by 3.2% on the ProofNet testset, with further gains of 1.9% on MiniF2F and 1.5% on ProverBench.

Large language models (LLMs) remain unreliable when reasoning about the future. Existing models often overlook the difference among future states, committing to specific answers even when the queried facts are inherently volatile. To capture this challenge, we introduce ChronoRegime, a future-oriented temporal reasoning task that requires models to determine whether historical temporal evidence justifies commitment to a future answer. Furthermore, we propose Confidence-Aware Temporal Reasoning (CTR), a framework that estimates query predictability from temporal dynamics and regulates answer commitment accordingly. Rather than performing unconditional forecasting, CTR commits only when the reconstructed evidence supports the target future state. Across multiple LLMs, CTR improves strict overall accuracy by 6.7 percentage points and reduces hallucination rates by 18.4 percentage points on average over the plain QA baseline. These results demonstrate that explicit predictability assessment is an effective mechanism for safer and more reliable temporal reasoning under future uncertainty.

Large Audio-Language Models have made significant advances in audio-text instruction following and multimodal interaction. However, due to their text-conditioned generation architecture, current LALMs tend to be overly influenced by input text prompts. When acoustic evidence conflicts with textual prompts, incorrect or irrelevant textual cues may steer model predictions away from the audio. In this work, we systematically analyze this challenge and show that representative LALMs exhibit a persistent audio-text imbalance during decoding, where attention to audio tokens is weakened across generation steps. To address the imbalance, we propose Modality-Specific Gating (MSG), an acoustic calibration mechanism that improves audio grounding with a small number of additional parameters. MSG introduces a token-wise, query-conditioned bias to the attention logits of audio tokens before softmax, while leaving the original attention computation unchanged. With parameter-efficient fine-tuning, MSG enhances acoustic evidence utilization, leading to consistently improved performance on vocal sound classification and speech emotion recognition, as well as strong robustness under adversarial or irrelevant text prompts.

Joint-encoding zero-shot relation extraction classifies all candidate relation labels in a single Transformer forward pass, achieving strong accuracy and high throughput. However, under a controlled full-vocabulary diagnostic, two distributional pathologies surface: unnormalized dot-product scoring causes recall collapse, with certain types receiving zero predictions, while the per-instance BCE loss leaves gold and negative scores entangled beyond any reliable threshold—confidence ambiguity. We propose SCAR, which keeps the baseline pathway intact and stabilizes both distributions via two auxiliary branches: a gradient-isolated coarse-to-fine cascade with Z-score normalization that restores cross-relation comparability, and a training-only contrastive alignment module that separates gold from negative scores. On Wiki-ZSL (m=15), SCAR raises Macro F1 from 75.9% to 83.0% and cuts zero-recall types from 35 to 1, suggesting that small-pool ZSRE protocols can obscure failure modes critical to large-vocabulary deployment.

Work on personality detection has tended to incorporate psychological features from different personality models, such as BigFive and MBTI. There are more than 900 psychological features, each of which is helpful for personality detection. However, when used in combination, the application of different calculation standards among these features may result in interference between features calculated using distinct systems, thereby introducing noise and reducing performance. This paper adapts different psychological models in the proposed PsyAttention for personality detection, which can effectively encode psychological features, reducing their number by 85%. In experiments on the BigFive and MBTI models, PysAttention achieved average accuracy of 65.66% and 86.30%, respectively, outperforming state-of-the-art methods, indicating that it is effective at encoding psychological features.