Text classification has long been a cornerstone of NLP, yet most prior work and benchmarks have been limited to closed-world settings, where all classes are assumed to be known in advance. In contrast, open-world learning has recently emerged as a critical paradigm for building more robust and realistic systems. However, existing benchmarks largely focus on out-of-distribution (OOD) detection, while overlooking broader challenges such as the discovery of novel categories. To address this gap, we introduce BOLT, a unified Benchmark and evaluation toolkit supporting Open-world Learning for Text classification. BOLT encompasses two representative tasks: Open-set Text Classification (OSTC), which requires models to classify in-distribution (ID) samples while rejecting OOD inputs, and Generalized Category Discovery (GCD), which aims to identify both known and novel categories from partially labeled corpora. We carefully curate 12 publicly available datasets spanning diverse domains and benchmark 22 methods, including 15 for OSTC and 7 for GCD, under a standardized protocol that explicitly accounts for varying labeled ratios and known class ratios. Our results reveal key challenges: most current methods tend to overfit training distributions and struggle to generalize to unseen classes. Moreover, by comparing our lightweight LLM-based variants with prior open-set baselines, we demonstrate the promise of leveraging LLMs for open-world text classification. BOLT provides standardized evaluation protocols that enable fair comparison and support future research in this emerging area. All datasets, baselines, and tools are available at https://github.com/CNIC-DSL/BOLT.

Generalized Category Discovery (GCD) aims to identify both known and novel categories from partially labeled data, reflecting more realistic open-world learning scenarios. However, most existing methods rely solely on one-hot discriminative supervision, leading to overfitting on seen classes and poor generalization to unseen ones. Recent advances introduce large language models (LLMs) to incorporate external semantics, yet they often suffer from semantic–label misalignment and weak semantic integration during training. We propose GenDis, a Generative–Discriminative Dual-View Co-Training framework that unifies discriminative classification and semantic label generation within an LLM. Discriminative pseudo-labels guide the formation of a separable generative latent space, enabling semantically meaningful supervision for novel classes. To ensure consistency between the two views, we employ Canonical Correlation Analysis (CCA)-based alignment and a curriculum-guided, dispersion-aware pseudo-labeling strategy for iterative refinement. Extensive experiments on five GCD benchmarks demonstrate that GenDis substantially outperforms prior methods, validating the effectiveness of dual-view co-training with semantically enriched supervision. The anonymized repository is available at https://anonymous.4open.science/r/GenDis.

Reinforcement learning (RL) has demonstrated considerable promise in enhancing large language models. However, its application to Mixture-of-Experts (MoE) architectures is frequently hindered by training instability, primarily stemming from token-level misalignment in expert assignments between current and behavior policies. Existing approaches often oscillate between overly coarse sequence-level importance sampling, which ignores token-specific discrepancies, and restrictive expert-selection constraints that suppress beneficial policy exploration. To bridge this gap, we propose Expert Relative Policy Optimization (ERPO), which introduces expert-level importance sampling. By grouping tokens according to their routing assignments, ERPO mitigates the high variance of token-level importance sampling while overcoming the token-agnostic limitations of sequence-level methods. Furthermore, ERPO leverages this expert-centric granularity to introduce an Expert-Selection Entropy Reward, which dynamically adjusts routing uncertainty based on task-specific feedback. This unique mechanism ensures a rigorous alignment between reward signals and policy updates—a capability inherently unattainable by traditional importance sampling methods. Experimental results demonstrate that ERPO significantly outperforms strong baselines across multiple reasoning tasks, highlighting the efficacy of tailoring RL objectives to the structural inductive biases of MoE models.

Large reasoning models (LRMs) have achieved strong performance enhancement through scaling test time computation, but due to the inherent limitations of the underlying language models, they still have shortcomings in tasks that require precise computation and extensive knowledge reserves. Tool-Integrated Reasoning (TIR) has emerged as a promising paradigm that incorporates tool call and execution within the reasoning trajectory. Although recent works have released some powerful open-source TIR models, our analysis reveals that these models still suffer from critical deficiencies. We find that when the reasoning of the model conflicts with the tool results, the model tends to believe in its own reasoning. And there are cases where the tool results are correct but are ignored by the model, resulting in incorrect answers, which we define as “Tool Ignored”. This indicates that the model does not know when to trust or ignore the tool. To overcome these limitations, We introduce Adaptive Tool Trust Calibration (ATTC), a novel framework that guides the model to adaptively choose to trust or ignore the tool results based on the confidence score of generated code blocks. The experimental results from various open-source TIR models of different sizes and across multiple datasets demonstrate that ATTC effectively reduces the "Tool Ignored" issue, resulting in a performance increase of 4.1% to 7.5%.

Reinforcement learning with verifiable rewards (RLVR) is a promising approach for improving the complex reasoning abilities of large language models (LLMs). However, current RLVR methods face two significant challenges: the near-miss reward problem, where a small mistake can invalidate an otherwise correct reasoning process, greatly hindering training efficiency; and exploration stagnation, where models tend to focus on solutions within their ”comfort zone”, lacking the motivation to explore potentially more effective alternatives. To address these challenges, we propose StepHint, a novel RLVR algorithm that utilizes multi-level stepwise hints to help models explore the solution space more effectively. StepHint partitions valid reasoning chains into reasoning steps using our proposed adaptive partitioning method. The initial few steps are used as hints, and simultaneously, multiple-level hints (each comprising a different number of steps) are provided to the model. This approach directs the model’s exploration toward a promising solution subspace while preserving its flexibility for independent exploration. By providing hints, StepHint mitigates the near-miss reward problem, thereby improving training efficiency. Additionally, the external reasoning pathways help the model develop better reasoning abilities, enabling it to move beyond its ”comfort zone” and mitigate exploration stagnation. StepHint outperforms competitive RLVR enhancement methods across six mathematical benchmarks and two out-of-domain benchmarks.

The evolution of speech technology has been spurred by the rapid increase in dataset sizes. Traditional speech models generally depend on a large amount of labeled training data, which is scarce for low-resource languages. This paper presents GigaSpeech 2, a large-scale, multi-domain, multilingual speech recognition corpus. It is designed for low-resource languages and does not rely on paired speech and text data. GigaSpeech 2 comprises about 30,000 hours of automatically transcribed speech, including Thai, Indonesian, and Vietnamese, gathered from unlabeled YouTube videos. We also introduce an automated pipeline for data crawling, transcription, and label refinement. Specifically, this pipeline involves Whisper for initial transcription, MMS for forced alignment, and multi-dimensional filtering for data quality assurance. A modified Noisy Student Training is developed to further refine flawed pseudo labels iteratively, thereby enhancing model performance. Experimental results on our manually transcribed evaluation set and two public test sets from Common Voice and FLEURS confirm our corpus’s high quality and broad applicability. Notably, ASR models trained on GigaSpeech 2 can reduce the word error rate for Thai, Indonesian, and Vietnamese on our challenging and realistic YouTube test set by 25% to 40% compared to Whisper large-v3, with merely 10% model parameters. Furthermore, our ASR models trained on GigaSpeech 2 yield superior performance compared to commercial services. We hope that our newly introduced corpus and pipeline will open a new avenue for low-resource speech recognition and significantly facilitate research in this area.

Modern large language models are sensitive to prompts, and another synonymous expression or a typo may lead to unexpected results for the model. Composing an optimal prompt for a specific demand lacks theoretical support and relies entirely on human experimentation, which poses a considerable obstacle to popularizing generative artificial intelligence. However, there is no systematic analysis of the stability of large language models to resist prompt perturbations. In this work, we propose to evaluate the ease-of-use of large language models and construct E-Bench, simulating the actual situation of human use from synonymous perturbation (including paraphrasing, simplification, and colloquialism) and typographical perturbation. Besides we also discuss the combination of these two types of perturbation and analyze the main reasons for performance degradation. Experimental results indicate that with the increase of model size, although the ease-of-use could be significantly improved, there is still a long way to go to build a sufficiently user-friendly model.

The emergence of pre-trained models marks a significant juncture for the multilingual generation, offering unprecedented capabilities to comprehend and produce text across multiple languages. These models display commendable efficiency in high-resource languages. However, their performance notably falters in low-resource languages due to the extensive linguistic diversity encountered. Moreover, the existing works lack thorough analysis impairs the discovery of effective multilingual strategies, further complicating the advancement of current multilingual generation systems. This paper aims to appraise the efficacy of multilingual generation tasks, with a focus on summarization, through three resource availability scenarios: high-resource, low-resource, and zero-shot. We classify multilingual generation methodologies into three foundational categories based on their underlying modeling principles: Fine-tuning, Parameter-isolation, and Constraint-based approaches. Following this classification, we conduct a comprehensive comparative study of these methodologies across different resource contexts using two datasets that span six languages. This analysis provides insights into the unique advantages and limitations of each method. In addition, we introduce an innovative yet simple automatic metric LANGM designed to mitigate the prevalent problem of spurious correlations associated with language mixing. LANGM accurately measures the degree of code-mixing at the language level. Finally, we highlight several challenges and suggest potential avenues for future inquiry, aiming to spur further advancements within the field of multilingual text generation.

Knowledge graph completion (KGC) aims to infer missing facts based on existing facts within a KG. Recently, research on generative models (GMs) has addressed the limitations of embedding methods in terms of generality and scalability. However, GM-based methods are sensitive to contextual facts on KG, so the contextual facts of poor quality can cause GMs to generate erroneous results. To improve the performance of GM-based methods for various KGC tasks, we propose a COntextual FactS GuIded GeneratioN (COSIGN) model. First, to enhance the inference ability of the generative model, we designed a contextual facts collector to achieve human-like retrieval behavior. Second, a contextual facts organizer is proposed to learn the organized capabilities of LLMs through knowledge distillation. Finally, the organized contextual facts as the input of the inference generator to generate missing facts. Experimental results demonstrate that COSIGN outperforms state-of-the-art baseline techniques in terms of performance.

In this paper, we define a widely neglected property in dialogue text, duality, which is a hierarchical property that is reflected in human behaviours in daily conversations: Based on the logic in a conversation (or a sentence), people can infer follow-up utterances (or tokens) based on the previous text, and vice versa. We propose a hierarchical duality learning for dialogue (HDLD) to simulate this human cognitive ability, for generating high quality responses that connect both previous and follow-up dialogues. HDLD utilizes hierarchical dualities at token hierarchy and utterance hierarchy. HDLD maximizes the mutual information between past and future utterances. Thus, even if future text is invisible during inference, HDLD is capable of estimating future information implicitly based on dialogue history and generates both coherent and informative responses. In contrast to previous approaches that solely utilize future text as auxiliary information to encode during training, HDLD leverages duality to enable interaction between dialogue history and the future. This enhances the utilization of dialogue data, leading to the improvement in both automatic and human evaluation.

Dialogue, the most fundamental and specially privileged arena of language, gains increasing ubiquity across the Web in recent years. Quickly going through the long dialogue context and capturing salient information scattered over the whole dialogue session benefit users in many real-world Web applications such as email thread summarization and meeting minutes draft. Dialogue summarization is a challenging task in that dialogue has dynamic interaction nature and presumably inconsistent information flow among various speakers. Many researchers address this task by modeling dialogue with pre-computed static graph structure using external linguistic toolkits. However, such methods heavily depend on the reliability of external tools and the static graph construction is disjoint with the graph representation learning phase, which makes the graph can’t be dynamically adapted for the downstream summarization task. In this paper, we propose a Static-Dynamic graph-based Dialogue Summarization model (SDDS), which fuses prior knowledge from human expertise and adaptively learns the graph structure in an end-to-end learning fashion. To verify the effectiveness of SDDS, we conduct experiments on three benchmark datasets (SAMSum, MediaSum, and DialogSum) and the results verify the superiority of SDDS.

Video-grounded dialogue understanding is a challenging problem that requires machine to perceive, parse and reason over situated semantics extracted from weakly aligned video and dialogues. Most existing benchmarks treat both modalities the same as a frame-independent visual understanding task, while neglecting the intrinsic attributes in multimodal dialogues, such as scene and topic transitions. In this paper, we present Video-grounded Scene&Topic AwaRe dialogue (VSTAR) dataset, a large scale video-grounded dialogue understanding dataset based on 395 TV series. Based on VSTAR, we propose two benchmarks for video-grounded dialogue understanding: scene segmentation and topic segmentation, and one benchmark for video-grounded dialogue generation. Comprehensive experiments are performed on these benchmarks to demonstrate the importance of multimodal information and segments in video-grounded dialogue understanding and generation.

In open-domain dialogue generation tasks, contexts and responses in most datasets are one-to-one mapped, violating an important many-to-many characteristic: a context leads to various responses, and a response answers multiple contexts. Without such patterns, models poorly generalize and prefer responding safely. Many attempts have been made in either multi-turn settings from a one-to-many perspective or in a many-to-many perspective but limited to single-turn settings. The major challenge to many-to-many augment multi-turn dialogues is that discretely replacing each turn with semantic similarity breaks fragile context coherence. In this paper, we propose DialoGue Path Sampling (DialoGPS) method in continuous semantic space, the first many-to-many augmentation method for multi-turn dialogues. Specifically, we map a dialogue to our extended Brownian Bridge, a special Gaussian process. We sample latent variables to form coherent dialogue paths in the continuous space. A dialogue path corresponds to a new multi-turn dialogue and is used as augmented training data. We show the effect of DialoGPS with both automatic and human evaluation.

Span-based models are one of the most straightforward methods for named entity recognition (NER). Existing span-based NER systems shallowly aggregate the token representations to span representations. However, this typically results in significant ineffectiveness for long entities, a coupling between the representations of overlapping spans, and ultimately a performance degradation. In this study, we propose DSpERT (Deep Span Encoder Representations from Transformers), which comprises a standard Transformer and a span Transformer. The latter uses low-layered span representations as queries, and aggregates the token representations as keys and values, layer by layer from bottom to top. Thus, DSpERT produces span representations of deep semantics. With weight initialization from pretrained language models, DSpERT achieves performance higher than or competitive with recent state-of-the-art systems on six NER benchmarks. Experimental results verify the importance of the depth for span representations, and show that DSpERT performs particularly well on long-span entities and nested structures. Further, the deep span representations are well structured and easily separable in the feature space.

Stylized dialogue generation systems aim to produce coherent and context-aware dialogues while effectively emulating the desired style. Generating stylized dialogue is valuable yet challenging due to the scarce parallel data. Existing methods often synthesize pseudo data through back translation, yet suffer from noisy and context-agnostic style signals caused by insufficient guidance on target style features. To address this, we propose the knowledge-augmented stylized dialogue generation model, which includes a feature-guided style knowledge selection module that utilizes context and response features. Specifically, we retrieve dialogue-related style sentences from style corpus to explicitly provide clear style signals. We design a feature-guided selection module with response-related contrastive learning and style responsiveness Kullback-Leibler losses to enhance generation at both semantic and stylized levels. Our approach demonstrates satisfactory performance on two public stylized dialogue benchmarks in both automatic and human evaluations.

The de-identification task aims to detect and remove the protected health information from electronic medical records (EMRs). Previous studies generally focus on the within-hospital setting and achieve great successes, while the cross-hospital setting has been overlooked. This study introduces a new de-identification dataset comprising EMRs from three hospitals in China, creating a benchmark for evaluating both within- and cross-hospital generalization. We find significant domain discrepancy between hospitals. A model with almost perfect within-hospital performance struggles when transferred across hospitals. Further experiments show that pretrained language models and some domain generalization methods can alleviate this problem. We believe that our data and findings will encourage investigations on the generalization of medical NLP models.

Neural named entity recognition (NER) models may easily encounter the over-confidence issue, which degrades the performance and calibration. Inspired by label smoothing and driven by the ambiguity of boundary annotation in NER engineering, we propose boundary smoothing as a regularization technique for span-based neural NER models. It re-assigns entity probabilities from annotated spans to the surrounding ones. Built on a simple but strong baseline, our model achieves results better than or competitive with previous state-of-the-art systems on eight well-known NER benchmarks. Further empirical analysis suggests that boundary smoothing effectively mitigates over-confidence, improves model calibration, and brings flatter neural minima and more smoothed loss landscapes.