AI-generated-text detectors are evaluated as classifiers, yet consequential deployments use detector outputs as evidence that people inspect, trust, contest, or use to escalate decisions. We call this mismatch the classification–evidence gap. The gap makes scalar detector scores a weak deployment interface: they hide the basis of a judgment, invite overtrust, and can turn false positives into accusations. We argue that AI-text detection should be evaluated as evidence-grounded decision support rather than as authorship proof. We introduce AGENT-XTrust, a guideline-expert detector that returns direct MetaAgent labels without target-domain scalar-cutoff calibration and converts each document-level judgment into inspectable evidence records containing local labels, rationales, confidence estimates, and linked spans. Across three domains and four generators, AGENT-XTrust preserves strong binary accuracy while producing inspectable, contestable evidence. In a controlled fixed-stimulus user study, participants assigned to the full AGENT-XTrust system-and-interface package achieved 19.8 and 11.3 points higher decision accuracy than those assigned to the score-only and score-plus-explanation packages, respectively; overtrust on each condition’s detector-wrong cases was 17.8 and 18.3 points lower. These results suggest a broader evaluation target for AI-text detection: not only whether a detector is correct, but whether complete detector-and-evidence packages support reliable human decisions under uncertainty.

Existing tabular reasoning benchmarks typically assume that input tables are clean and error-free, which contrasts sharply with real-world data pipelines where noise and anomalies are pervasive. While humans routinely validate tables and reject conclusions when anomalies render a question unanswerable, it remains unclear whether large language models (LLMs) exhibit similar anomaly awareness. In this work, we introduce AnTBench, a benchmark designed to systematically evaluate LLM behavior under anomalous tabular data. AnTBench consists of 1,571 curated instances covering five common and verifiable anomaly types. Experiments on 14 representative LLMs reveal a pronounced capability–behavior gap: even the strongest model achieves 76.07% on explicit anomaly detection, yet only 19.03% on spontaneous anomaly perception during standard table QA. As an inference-time mitigation, we introduce the Multi-Path Thinker, a multi-path reasoning framework. While this approach improves explicit anomaly detection, enforcing proactive verification for every query is practically prohibitive. We urge the community to move beyond inference-time patches and instill spontaneous anomaly awareness directly into the training and alignment phases. Our code and data are available at https://github.com/Wei12097/AnTBench.

Recent advances in model distillation show that data from advanced reasoning models can effectively train smaller student models. However, standard practices discard incorrect reasoning traces—valuable, yet underutilized data. This paper addresses the critical question: How can both positive and negative distilled reasoning traces be effectively leveraged to maximize LLM reasoning performance in an offline setting? We employ a two-stage training recipe: first, Supervised Fine-Tuning (SFT) on positive traces, followed by a refinement stage using both positive and negative traces. We find that a simple REINFORCE-style objective, which we term the Reinforcement Distillation (REDI) objective, outperforms established preference optimization methods like DPO and SimPO in this distillation context. Our empirical evaluations demonstrate the effectiveness of this approach. Notably, our Qwen-REDI-1.5B model, trained on just 131k traces from the open Open-R1 dataset, achieves an 83.1% score on MATH-500. Its performance matches that of DeepSeek-R1-Distill-Qwen-1.5B, a model trained on 800k proprietary data. This result showcases the remarkable data efficiency of utilizing previously discarded negative traces.

Despite the recent advancements in Large Language Models (LLMs), which have significantly enhanced the generative capabilities for various NLP tasks, LLMs still face limitations in directly handling retrieval tasks. However, many practical applications demand the seamless integration of both retrieval and generation. This paper introduces a novel and efficient One-pass Generation and retrieval framework (OneGen), designed to improve LLMs’ performance on tasks that require both generation and retrieval. The proposed framework bridges the traditionally separate training approaches for generation and retrieval by incorporating retrieval tokens generated autoregressively. This enables a single LLM to handle both tasks simultaneously in a unified forward pass. We conduct experiments on two distinct types of composite tasks, RAG and Entity Linking, to validate the pluggability, effectiveness, and efficiency of OneGen in training and inference. Furthermore, our results show that integrating generation and retrieval within the same context preserves the generative capabilities of LLMs while improving retrieval performance. To the best of our knowledge, OneGen is the first to enable LLMs to conduct vector retrieval during the generation.

Automatic generation of discharge summaries presents significant challenges due to the length of clinical documentation, the dispersed nature of patient information, and the diverse terminology used in healthcare. This paper presents a hybrid solution for generating discharge summary sections as part of our participation in the “Discharge Me!” Challenge at the BioNLP 2024 Shared Task. We developed a two-stage generation method using both extractive and abstractive techniques, in which we first apply name entity recognition (NER) to extract key clinical concepts, which are then used as input for a prompt-tuning based GatorTronGPT model to generate coherent text for two important sections including “Brief Hospital Course” and “Discharge Instructions”. Our system was ranked 5th in this challenge, achieving an overall score of 0.284. The results demonstrate the effectiveness of our hybrid solution in improving the quality of automated discharge section generation.

Large language models (LLMs) produce hallucinated text, compromising their practical utility in professional contexts. To assess the reliability of LLMs, numerous initiatives have developed benchmark evaluations for hallucination phenomena. However, they often employ constrained generation techniques to produce the evaluation dataset due to cost and time limitations. For instance, this may involve employing directed hallucination induction or deliberately modifying authentic text to generate hallucinations. These are not congruent with the unrestricted text generation demanded by real-world applications. Furthermore, a well-established Chinese-language dataset dedicated to the evaluation of hallucinations is presently lacking. Consequently, we have developed an Unconstrained Hallucination Generation Evaluation (UHGEval) benchmark, containing hallucinations generated by LLMs with minimal restrictions. Concurrently, we have established a comprehensive benchmark evaluation framework to aid subsequent researchers in undertaking scalable and reproducible experiments. We have also evaluated prominent Chinese LLMs and the GPT series models to derive insights regarding hallucination.

Traditionally, large language models have been either trained on general web crawls or domain-specific data. However, recent successes of generative large language models, have shed light on the benefits of cross-domain datasets. To examine the significance of prioritizing data diversity over quality, we present a German dataset comprising texts from five domains, along with another dataset aimed at containing high-quality data. Through training a series of models ranging between 122M and 750M parameters on both datasets, we conduct a comprehensive benchmark on multiple downstream tasks. Our findings demonstrate that the models trained on the cross-domain dataset outperform those trained on quality data alone, leading to improvements up to 4.45% over the previous state-of-the-art.

Cross-sentence attention has been widely applied in text matching, in which model learns the aligned information between two intermediate sequence representations to capture their semantic relationship. However, commonly the intermediate representations are generated solely based on the preceding layers and the models may suffer from error propagation and unstable matching, especially when multiple attention layers are used. In this paper, we pro-pose an enhanced sentence alignment network with simple gated feature augmentation, where the model is able to flexibly integrate both original word and contextual features to improve the cross-sentence attention. Moreover, our model is less complex with fewer parameters compared to many state-of-the-art structures. Experiments on three benchmark datasets validate our model capacity for text matching.

(T)ACSA tasks, including aspect-category sentiment analysis (ACSA) and targeted aspect-category sentiment analysis (TACSA), aims at identifying sentiment polarity on predefined categories. Incremental learning on new categories is necessary for (T)ACSA real applications. Though current multi-task learning models achieve good performance in (T)ACSA tasks, they suffer from catastrophic forgetting problems in (T)ACSA incremental learning tasks. In this paper, to make multi-task learning feasible for incremental learning, we proposed Category Name Embedding network (CNE-net). We set both encoder and decoder shared among all categories to weaken the catastrophic forgetting problem. Besides the origin input sentence, we applied another input feature, i.e., category name, for task discrimination. Our model achieved state-of-the-art on two (T)ACSA benchmark datasets. Furthermore, we proposed a dataset for (T)ACSA incremental learning and achieved the best performance compared with other strong baselines.