Low Resource Languages (LRLs) pose significant challenges for hate speech detection because of a scarcity of readily available annotated data, language variation, non-standard spelling, and context-dependent ambiguity. Beyond the problem of informal conventions of writing in Roman Urdu, there is also the issue of code-...
Toneema Zubair, Muhammad Junaid Asif, Faisal Kamiran et al.· 0 citations
Pre-registration is increasingly proposed as a trust mechanism for machine-learning research involving LLM-generated content, but its canonical form assumes a frozen protocol can be executed unchanged. Software-intensive studies violate this assumption: the protocol is partly implemented, and implementations carry defe...
In mission-critical networks, a missed jamming event is costlier than a false alarm, so detectors should favor recall, operate causally, and work without labeled attack data. Retrospective Key Performance Indicator (KPI) detectors meet the label-free requirement but rely on future context and cannot run in streaming op...
The rapid scaling of large language models (LLMs) has made communication overhead a critical bottleneck in distributed model-parallel training. Although existing low-precision compression methods can effectively reduce communication costs, further reducing the communication footprint to ultra-low-bit formats such as FP...
Man Liu, Xingchen Liu, Hairui Zhao et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Multi-agent LLM systems assign different responsibilities to different agents: one plans, another retrieves evidence, another verifies, another executes. This division of labor is only meaningful if each agent stays within the functions it is authorized to perform. Over many turns, however, an agent can produce a local...
Maisha Maliha, Vishal Pramanik, Sumit Kumar Jha· 0 citations
Empirical evidence is provided that planning and coding can be separated to a considerable extent in LLM-based code generation, which may offer a more flexible way to construct code-generation systems.
Wen-Tao Wang, Ze-Yu Sun, Ru-Wei Pan et al.· 0 citations
Long-horizon multi-agent systems suffer from three tightly coupled failures: task drift, role drift, and state staleness. We test the hypothesis that these share a common representational cause: agent hidden states move away from the directions encoding the active task, assigned role, and current shared state. A pilot...
Vishal Pramanik, Maisha Maliha, Susmit Jha et al.· 0 citations
Answering geographic queries over Earth observation (EO) archives requires solving a joint retrieval-and-derivation problem under strict spatiotemporal constraints. Existing LLM agents fail to ground observation items or suffer from search-space explosion. We propose OSGR, a two-stage framework that factorizes this sea...
Dazhou Yu, Zerong Wang, Riyang Bao et al.· 0 citations
Discrete diffusion models with parallel decoding are often distilled using token-wise KL objectives. Although token-wise KL exactly matches the corresponding product-form block distributions, its probability-space optimization geometry and teacher-only candidate truncation may provide insufficient supervision under agg...
Peng Tu, Baoyou Chen, Haoyuan Xia et al.· 0 citations
Harness evolution from a common base exhibits Locality, Complementarity, and Nonstationarity: variants repair different failures, and their utility changes as the policy learns. Rather than seeking a universally superior harness, we introduce Harness-S to selectively rescue failures of a base execution system through s...
Kangning Zhang, Wenxiang Jiao, Bowen Fang et al.· 0 citations
External text can affect a retrieval-augmented generation (RAG) system only after the retriever admits it to the model context. We stress this admission step while varying document content, attacker query information, per-target poison budget, and contamination scope. Across 623 Benchmarking Information Retrieval (BEIR...
Janet Sung, Kainan Zhou, Gangzhen Qian et al.· 0 citations
Inoculation prompting is a method to reduce undesired behaviours such as reward hacking in frontier models. It works by training a model on harmful examples under a prompt that specifies the undesired behaviour, which reduces the model's tendency to exhibit it unless prompted. However, the inoculation prompt is written...
