arXiv:2606. 24734v1 Announce Type: cross Abstract: High-quality annotations of structured representations are expensive to collect over large corpora.
arXiv:2606. 02255v1 Announce Type: cross Abstract: Human annotation is the empirical foundation of much NLP research, from dataset construction to model evaluation, but papers often leave unclear who produced the annotations and how the annotation process was controlled.
arXiv:2604. 17289v2 Announce Type: replace Abstract: Supervised fine-tuning of large language models relies on human-annotated data, yet annotation pipelines routinely involve multiple crowdworkers of heterogeneous expertise.
LakeHopper is a method for adapting column type annotators (CTA) from one data lake to another by treating cross‑lake adaptation as a knowledge‑management problem. It decomposes the source annotator’s knowledge into source‑specific, shared, and target‑specific parts, and then uses three mechanisms—label‑set realignment, LLM‑verified gap discovery, and cluster‑based propagation with rehearsal fine‑tuning—to adapt the annotator under a limited annotation budget. The approach achieves up to a 71.4% relative macro‑F1 improvement over three PLM backbones, reaches near‑full data quality with less than 6% of target labels, and trains 27–131 times faster than fine‑tuned table LLMs.
The paper investigates whether large language models can learn and reproduce annotator‑specific label‑explanation behavior, using two sentence‑pair tasks with four annotators each. It finds that individual annotator patterns are weak at the single‑annotation level but become detectable after reducing input‑content effects and aggregating across annotators. The authors propose cross‑annotator preference optimization (CAPO), which improves upon prompting and supervised fine‑tuning by better capturing annotator‑specific reasoning while maintaining stable attribution.
arXiv:2609.24372v1 Announce Type: new Abstract: In-context learning (ICL) based on large language models (LLMs) has shown promising potential in alleviating performance bottlenecks caused by the limi...
Event analysis is an essential and fundamental direction of information extraction, involving various event-centric tasks at different granularity of documents. While large language models (LLMs) have preliminarily achieved promising performance in part of these tasks individually, their capability in event analysis still lacks comprehensive understanding due to restricted document granularity, task designs, and data source of existing benchmarks.
Large language models (LLMs) are increasingly used to annotate datasets for training smaller, task‑specialized models such as named entity recognition (NER). However, current fine‑tuning processes ignore the annotation noise introduced by LLMs, leading to degraded performance, and existing noise‑robust losses fail to handle the heterogeneous nature of NER noise (e.g., missing mentions vs. type errors). The authors propose error‑type‑aware loss reweighting, which applies separate reweighting rules for different erroneous token types, improving F1 scores by 0.8–2.0 percentage points on average and up to 4.6 points on Wikigold at 24.1% noise.
The paper introduces the Necessary Tool‑Evidence Path (NTEP) annotation scheme and its associated reward mechanism (NTEP‑R) to better supervise vision‑language models that use external tools. By explicitly specifying which evidence is needed and penalizing redundant tool calls, the authors train an 8B‑parameter model that shows improved accuracy and tool‑use efficiency across seven image‑grounded benchmarks. The approach demonstrates that fine‑grained supervision of tool‑evidence paths is essential for robust agentic VLM performance.
arXiv:2606. 02837v1 Announce Type: cross Abstract: Accurate translation from Natural Language to First-Order Logic (NL-to-FOL) underpins neurosymbolic AI systems and Natural Language Inference (NLI), making the quality of NL-to-FOL benchmarks essential -- yet these datasets have never been rigorously audited.
arXiv:2604. 09497v2 Announce Type: replace-cross Abstract: Accurate evaluation is central to the large language model (LLM) ecosystem, guiding model selection and downstream adoption across diverse use cases.
arXiv:2606. 08718v1 Announce Type: cross Abstract: While Deep Active Learning (DAL) effectively reduces human annotation costs, its efficacy is constrained by human annotation errors.
The paper introduces Lens, a training‑free framework that aligns multimodal representations with the semantic perspective required by downstream tasks. Lens uses a task‑specific readout phrase to anchor the perspective and then aggregates token states after the full input, ensuring the extracted representation reflects task‑conditioned evidence integration rather than generic salient content. The method achieves a Precision@1 of 63.9 across 36 MMEB datasets, outperforming the nearest training‑free baseline by 10.2 points.