A focused feed for RLHF, preference data, rater protocols, agent evaluation, and LLM-as-judge research.
Every paper includes structured metadata for quick triage.
Across multiple steering benchmarks, we show that SKOP achieves the best joint steering-utility trade-off, reducing utility degradation by 5-7x while retaining over 95% of vanilla steering efficacy.
To overcome these limitations, we present MANTRA, a framework for automatically synthesizing machine-checkable compliance benchmarks from natural-language manuals and tool schemas.
Safety benchmarks are routinely treated as evidence about how a language model will behave once deployed, but this inference is fragile if behavior depends on whether a prompt looks like an evaluation.
Paradoxically, we observe that tool-enabled evaluation can degrade reasoning performance even when the strong thinking models make almost no actual tool calls.
In contrast, fully unstructured teams enable adaptability and exploration but suffer from inefficiencies such as error propagation, inter-agent conflicts, and wasted resources (measured in time, tokens, or file operations).
Human label variation has been established as a central phenomenon in NLP: the perspectives different annotators have on the same item need to be embraced.
Laughter is a social non-vocalization that is universal across cultures and languages, and is crucial for human communication, including social bonding and communication signaling.
Agentic RAG extends this paradigm by replacing single-step retrieval with a multi-step process, in which the large language model (LLM) acts as a search agent that generates intermediate thoughts and subqueries to iteratively interact with…
In this paper, we introduce a new multi-genre benchmark (more than 1000 samples) for semantic segmentation in conversational Arabic, focusing on dialectal discourse.
Across three model families, six scales, and six math reasoning benchmarks, ReasonMaxxer matches or exceeds full RL performance while requiring only tens of problems and minutes of single-GPU training, a reduction in training cost of…
Browse by Topic
Jump directly into tag and hub pages to crawl deeper content clusters.
Multi-agent debate (MAD), and more broadly closed-system reasoning where agents iteratively transform each other's outputs, tends to preserve answer accuracy while degrading the reasoning behind those answers.
An R6 cohort study (Korean n=10x30 FEVER; English n=3x200 SciFact) finds inter-rater Fleiss kappa <= +0.018 with 0.8-1.4 Likert intra-rater shifts across language and domain -- the human agreement that faithfulness metrics have been…
Annotation quality is ensured through a multi-stage framework with three independent annotators and dimension-wise Fleiss Kappa (κ) agreement, yielding reliable and reproducible labels with κ values of 0.82 and 0.88 for structural and…
Statistical analyses demonstrate realistic structural and temporal distributions, while baseline evaluations show that dual-encoder architectures leveraging complementary language-specific representations consistently outperform strong…
To address this problem, this paper proposes a human-machine collaborative framework that integrates human knowledge into the learning process rather than relying solely on data-driven models.
Experiments are conducted on a Vietnamese speech dataset of 2,764 samples across three emotion classes (calm, angry, panic), with high inter-annotator agreement (Fleiss Kappa = 0.8574), ensuring reliable ground truth.
We present a systematic evaluation of instruction-tuned LLMs across three open essay-scoring datasets (ASAP 2.0, ELLIPSE, and DREsS) that cover both holistic and analytic scoring.
Our results show that strong open-weight models achieve moderate to high agreement with humans on holistic scoring (Quadratic Weighted Kappa about 0.6), but this does not transfer uniformly to analytic scoring.
On ELT-Bench, the first benchmark for end-to-end ELT pipeline construction, AI agents initially showed low success rates, suggesting they lacked practical utility.
Second, we develop an Auditor-Corrector methodology that combines scalable LLM-driven root-cause analysis with rigorous human validation (inter-annotator agreement Fleiss' kappa = 0.85) to audit benchmark quality.
Using these guidelines, annotators achieved high agreement in clause segmentation (Fleiss' kappa = 0.80) and moderate agreement in two structural classification tasks (Krippendorff's alpha = 0.41 and 0.45, respectively), one of which is…
Autonomous agents operating in continuous environments must decide not only what to do, but when to act.
High spread indicates a branching, uncertain future and drives the agent to act sooner; low spread signals predictability and permits longer rest intervals.
Expert evaluations further validated the quality of the model's reasoning, with mean scores exceeding 4.0/5.0 for factual accuracy, evidence comprehensiveness, and logical coherence.
Three classifiers (a regex-only detector, a regex-plus-LLM pipeline, and a Claude Sonnet 4 judge) are applied to 10,276 influenced reasoning traces from 12 open-weight models spanning 9 families and 7B to 1T parameters.
The disagreements are systematic: Cohen's kappa ranges from 0.06 ("slight") for sycophancy hints to 0.42 ("moderate") for grader hints, and the asymmetry is pronounced: for sycophancy, 883 cases are classified as faithful by the pipeline…
Results: Against a human majority-vote standard (N=467), the agent achieved 95.8% emergency sensitivity and 88.5% sensitivity for all actionable alerts (85.7% specificity).
In LOO analysis, the agent outperformed every clinician in emergency sensitivity (97.5% vs.
It contains 10,000 samples with linguistic feature annotations across 16 politeness categories and achieves substantial inter-annotator agreement (kappa = 0.703).
We benchmark 40 model configurations, including traditional machine learning, transformer-based models, and large language models.
Objective: This paper introduces a patient simulator for scalable, automated evaluation of healthcare conversational agents, generating realistic, controllable interactions that systematically vary across medical, linguistic, and behavioral…
Medical concept fidelity was high (96.6% across 8,210 concepts), validated by human annotators (0.73 kappa) and an LLM judge with comparable agreement (0.78 kappa).
We quantitatively illustrate that that the level of difficulty for human experts to perform the task of scoring written work of children has no observed statistical effect on LLM performance.
Particularly, we show that some scoring tasks measured as the easiest by human scorers were the hardest for LLMs.
We build a human expert-annotated ReviewScore dataset to check the ability of LLMs to automate ReviewScore evaluation.
The models show F1 scores of 0.4--0.5 and kappa scores of 0.3--0.4, indicating moderate agreement but also suggesting that fully automating the evaluation remains challenging.