Knowledge editing is a crucial technique for daily updates in LLMs, requiring a balance between accurately modifying incorrect knowledge and preserving existing information. The recently proposed AlphaEdit method achieves competitive editing performance by updating parameters under null-space constraints. However, our theoretical analysis reveals that AlphaEdit struggles with high knowledge conflicts and inconsistencies during editing. To address this, we propose a new editing method AlphaEdit+, featuring three key improvements: 1) relaxing null-space constraints by adding a matrix perturbation through optimization to resolve conflicts between new and preserved knowledge; 2) introducing a weighting scheme on previously updated knowledge constraints to mitigate conflicts between new and historical editing; 3) developing a value smoothing algorithm to resolve high knowledge inconsistencies. These enhancements collectively ensure robust editing while maintaining model coherence. Comprehensive experiments show that our approach AlphaEdit+ not only resolves the brittleness of the original method on carefully constructed challenging datasets but also outperforms AlphaEdit on existing benchmark datasets.

Knowledge editing updates facts in large language models while preserving unrelated knowledge. Most prior work studies object editing, which modifies the object under a fixed subject–relation pair. We instead study relation replacement editing, where an obsolete relation must be suppressed as a new one is introduced. We systematically study this setting with a dedicated benchmark and method. We introduce ReEditBench to evaluate replacement rather than association addition. Existing editors exhibit two major failures: obsolete-relation retention remains as high as 98.20% after successful edits, and difficult samples often destabilize editing. To address this, we propose R²Edit, a two-stage framework for relation replacement. Its target-smoothed Forget stage reduces obsolete-relation activation without fixed/random pseudo-target bias, while its curriculum-guided Edit stage progressively injects new relations from easy to hard samples. Across multiple LLMs, R²Edit improves replacement success, reduces retention, and preserves generalization. Stress tests on difficult subsets further demonstrate the robustness of the Edit stage. Code is available at: https://github.com/caoxu0109/R2Edit.

Token selection is pivotal for effective LLM post-training. However, existing methods mostly rely on local token-level heuristics, while response-token selection in post-training lacks an optimization-guided valuation proxy. We introduce AlphaToken, a response token valuation framework that decouples valuation into adaptation (promoting target-task learning) and stability (preserving pre-trained capabilities), and makes each objective path-aware by combining the direct-path signal from local token gradients with the downstream causal-path signal in autoregressive generation. Since retention data are typically unavailable, AlphaToken approximates stability via a Fisher-drift proxy anchored at the pre-trained reference model. For efficient computation, we extend Ghost Dot-Product to token-level valuation. AlphaToken masks low-value response tokens during fine-tuning and preference optimization, concentrating training signals on more valuable positions. Experiments show that AlphaToken improves post-training performance and mitigates catastrophic forgetting. Code at https://github.com/luciabcd/Alphatoken.

Before any reviewer is assigned, a journal editor decides whether a manuscript merits external review. Yet this routine desk screening has no benchmark. We present PREREVIEWBENCH, the first controlled benchmark for journal desk screening. Because real desk decisions are confidential, we pair Web of Science papers published in 2025 with journals to construct proxy labels: true matches, within-field caliber surpluses and deficits, and cross-field scope mismatches. The 7,292 balanced paper–journal instances span four broad areas and 58 journals, supporting desk triage, branch-specific assessment (caliber fit or rejection cause), and transfer-journal recommendation. Evaluating four frontier LLM families, we find average triage accuracy of 0.965 on cross-field scope mismatches but only 0.572 on within-field caliber deficits, where blind expert-led review reproduces the triage labels perfectly. Transfer recommendation is weaker still, with the best Hit@1 at just 0.369. Models are also sensitive to input perturbations, and a cue suggesting that most papers merit review sharply shifts GPT-5.5’s decisions. These results point to a clear division of labor: LLMs can already carry the scope side of desk screening, while caliber judgment stays with editors. PREREVIEWBENCH makes that harder half measurable: whether an in-scope paper is strong enough for its journal.

Fine-tuning large language models (LLMs) on a single target task requires balancing task adaptation with retention of prior capabilities. Existing teachers mainly guide preservation or transfer, but do not identify which target-task samples should be emphasized when fine-tuning must retain prior capabilities. We propose the **U**nconstrained **F**ine-tuned **T**eacher (**UFT**), shifting the teacher role from ”knowledge transfer” to ”value discovery”. UFT is obtained by unconstrained fine-tuning on the target task and then compared with the source model to identify high-value samples. These samples are upweighted during student fine-tuning and receive value-weighted UFT-guided distillation, allowing the student to prioritize task-critical signals while preserving prior capabilities. Experiments on Magicoder and MetaMathQA show that UFT improves the trade-off between target-task performance and prior-capability retention, while converging faster and more stably. By turning teacher behavior into sample-value discovery, UFT establishes a new teacher role for data-efficient fine-tuning.

Recent advances in large language models (LLMs) and text-aware graph learning have increased interest in reasoning over text-attributed graphs(TAGs). In many real-world settings, such graphs are inherently heterogeneous, with most existing benchmarks remaining largely homogeneous in structure. As a result, the lack of large-scale benchmarks for heterogeneous text-attributed graphs has hindered systematic evaluation and fair comparison of existing methods. In this work, we introduce CITE - Catalytic Information Textual Entities Graph, the first and largest heterogeneous text-attributed citation graph benchmark for catalytic materials. CITE contains over 438K nodes and 1.2M edges spanning four node types and four relation types, with rich node-level textual information. We establish standardized evaluation protocols for node classification and link prediction, and conduct ablation studies to assess the impact of graph heterogeneity and textual attributes. Using CITE, we benchmark four classes of learning paradigms, including homogeneous graph models, heterogeneous graph models, LLM-centric models, and hybrid LLM–graph models. By providing a large-scale heterogeneous text-attributed benchmark together with standardized evaluation protocols and comprehensive baselines, CITE enables systematic assessment across diverse modeling paradigms and offers new insights into text-aware and LLM-enhanced graph learning. The dataset, codebase and evaluation suite are publicly available.

Temporal Knowledge Graphs (TKGs) incorporate the temporal feature to express the transience of knowledge by describing when facts occur. TKG extrapolation aims to infer possible future facts based on known history, which has garnered significant attention in recent years. Some existing methods treat TKG as a sequence of independent subgraphs to model temporal evolution patterns, demonstrating impressive reasoning performance. However, they still have limitations: 1) In modeling subgraph semantic evolution, they usually neglect the internal structural interactions between subgraphs, which are actually crucial for encoding TKGs. 2) They overlook the potential smooth features that do not lead to semantic changes, which should be distinguished from the semantic evolution process. Therefore, we propose Disentangled Multi-span Evolutionary Network (DiMNet) for TKG reasoning. Specifically, we design a multi-span evolution strategy that captures local neighbor features while perceiving historical neighbor semantic information, thus enabling internal interactions between subgraphs during the evolution process. To maximize the capture of semantic change patterns, we design a disentangle component that adaptively separates nodes’ active and stable features, used to dynamically control the influence of historical semantics on future evolution. Extensive experiments demonstrate that DiMNet achieves substantial performance in TKG reasoning, outperforming the state-of-the-art up to 22.7% in MRR.

Continuous Relation Extraction (CRE) aims to incrementally learn relation knowledge from a non-stationary stream of data. Since the introduction of new relational tasks can overshadow previously learned information, catastrophic forgetting becomes a significant challenge in this domain. Current replay-based training paradigms prioritize all data uniformly and train memory samples through multiple rounds, which would result in overfitting old tasks and pronounced bias towards new tasks because of the imbalances of the replay set. To handle the problem, we introduce the DecouPled CRE (DP-CRE) framework that decouples the process of prior information preservation and new knowledge acquisition. This framework examines alterations in the embedding space as new relation classes emerge, distinctly managing the preservation and acquisition of knowledge. Extensive experiments show that DP-CRE significantly outperforms other CRE baselines across two datasets.

Scientific literature is always available in Adobe’s Portable Document Format (PDF), which is friendly for scientists to read. Compared with raw text, annotating directly on PDF documents can greatly improve the labeling efficiency of scientists whose annotation costs are very high. In this paper, we present Autodive, an integrated onsite scientific literature annotation tool for natural scientists and Natural Language Processing (NLP) researchers. This tool provides six core functions of annotation that support the whole lifecycle of corpus generation including i)annotation project management, ii)resource management, iii)ontology management, iv)manual annotation, v)onsite auto annotation, and vi)annotation task statistic. Two experiments are carried out to verify efficiency of the presented tool. A live demo of Autodive is available at http://autodive.sciwiki.cn. The source code is available at https://github.com/Autodive.