A focused feed for RLHF, preference data, rater protocols, agent evaluation, and LLM-as-judge research.
Every paper includes structured metadata for quick triage.
Experiments on three multimodal MoE models across six benchmarks demonstrate consistent improvements, with gains of up to 3.17% on complex visual reasoning tasks.
Extensive evaluations across 18 diverse benchmarks demonstrate its superior performance over strong open-source and leading proprietary frontier models.
Crucially, the photonic advantage grows with context length: as N increases, the electronic scan cost rises linearly while the photonic evaluation remains O(1).
Hardware-impaired needle-in-a-haystack evaluation on Qwen2.5-7B confirms 100% accuracy from 4K through 64K tokens at k=32, with 16x traffic reduction at 64K context.
Moreover, we systematically explore and validate key insights on the distillation strategies and the potential scalability of MTP through extensive experiments on seven benchmarks.
Extensive experiments on MT-VQA benchmarks and across multiple LVLM architectures demonstrate that MetaCompress achieves superior efficiency-accuracy trade-offs while maintaining strong generalization across dialogue turns.
Experiments on LLaDA-8B-Instruct and Dream-7B-Instruct show that EntropyCache achieves 15.2\times-26.4\times speedup on standard benchmarks and 22.4\times-24.1\times on chain-of-thought benchmarks, with competitive accuracy and decision…
Experiments on mathematical reasoning benchmarks demonstrate that InfoDensity matches or surpasses state-of-the-art baselines in accuracy while significantly reducing token usage, achieving a strong accuracy-efficiency trade-off.
While most red-teaming work emphasizes adversarial prompt search (input-space optimization), we show that safety failures can also be systematically exposed through diverse response generation (output-space exploration) for a fixed…
Across multiple jailbreak benchmarks and open-source LLMs, PDPS achieves attack success rates comparable to large-scale IID sampling while using only 8% to 29% of the computational cost.
The models were developed through a four-stage training pipeline: continued pre-training on Portuguese and Brazilian legal corpora, long-context extension to 128K tokens, supervised fine-tuning on instruction data spanning chat, code, legal…
We evaluate the models on six benchmark categories: conversational capabilities in Brazilian Portuguese, knowledge of Brazilian legislation, long-context understanding, instruction following, standardized exams, and agentic capabilities…
Multi-agent LLM systems increasingly tackle complex reasoning, yet their interaction patterns remain limited to voting, unstructured debate, or pipeline orchestration.
However, DCI consumes ~62x single-agent tokens, and single-agent generation outperforms DCI on overall quality.
In this paper, we propose TopoChunker, an agentic framework that maps heterogeneous documents onto a Structured Intermediate Representation (SIR) to explicitly preserve cross-segment dependencies.
To balance structural fidelity with computational cost, TopoChunker employs a dual-agent architecture.
Long-context agentic workflows have emerged as a defining use case for large language models, making attention efficiency critical for both inference speed and serving cost.
The models were evaluated on 25 tasks, including the KLEJ benchmark, a newly introduced financial task suite (FinBench), and other classification and regression tasks, specifically those requiring long-document understanding.
Moreover, importance estimation in prior work is computationally expensive and becomes prohibitive when continuous re-evaluation is required during long generation.