Human Feedback and Eval Paper Explorer

Match reason: Ranked by recency.

• Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Match reason: Ranked by recency.

• We present a 14-day (February 9-22, 2026) evaluation of six AI chatbots (Gemini 3 Flash and Pro, Grok 4, Claude 4.5 Sonnet, GPT-5 and GPT-4o mini) on 2,100 factual questions derived from same-day BBC News reporting across six regional…
• The same systems, however, lose 11-13% under free-response evaluation, and 16-17% across the cohort.

Match reason: Ranked by recency.

• Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Match reason: Ranked by recency.

• We show that PCT preserves overall helpfulness, substantially reduces covert political bias, and generalizes to held-out benchmarks.

Match reason: Ranked by recency.

• Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Match reason: Ranked by recency.

• Using \sim50k morally-annotated social media posts from a diverse range of topics, we apply a principled four-method validation pipeline: LaBSE cross-lingual embedding similarity, Centered Kernel Alignment (CKA), LLM-as-judge evaluation,…

Match reason: Ranked by recency.

• Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Match reason: Ranked by recency.

• Traditional safety benchmarks for language models evaluate generated text: whether a model outputs toxic language, reproduces bias, or follows harmful instructions.
• We introduce Boiling the Frog, a benchmark that evaluates whether tool-using AI models deployed in corporate and office settings are susceptible to incremental attacks.

Match reason: Ranked by recency.

• Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Match reason: Ranked by recency.

• To address this gap, we present Agentic CLEAR, an automatic, dynamic, and easy-to-use evaluation framework.
• In our experiments on four benchmarks, seven agentic settings, and tens of thousands of LLM calls, we show that Agentic CLEAR produces high-quality, data-driven, insightful feedback.

Match reason: Ranked by recency.

• We investigate whether acoustic emotion recognition models can serve as proxies for the Pathos dimension in political speech analysis, as operationalised by the TRUST multi-agent large language model (LLM) pipeline.
• We further demonstrate, via a systematic quality evaluation of the Berlin Database of Emotional Speech (EMO-DB) using Gemini in an open-ended annotation paradigm, that standard SER benchmark corpora suffer from acted speech, cultural bias,…

Match reason: Ranked by recency.

• Across 75,898 API calls to 11 models from 4 providers (OpenAI, Anthropic, Google, and four open-source models), we present identical test items in isolation or following histories saturated with predominantly positive or negative…
• The simplest fix for evaluation pipelines is a fresh context per item; when batching is unavoidable, balancing the history helps.

Match reason: Ranked by recency.

• The graph is constructed through a disease-autonomous multi-agent pipeline in which multiple frontier LLMs independently extract knowledge from PubMed and PMC literature.
• We further introduce ChronoTQA, a benchmark of 3,341 questions across eight task types (six temporal plus two static controls), with a 12-question supplementary probe.

Match reason: Ranked by recency.

• Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning ability of LLMs, but often depends on external supervision from human annotations or gold-standard solutions.
• Across mathematical reasoning and code-generation benchmarks, our method improves stability and robustness over prior unsupervised RL approaches, while achieving performance close to supervised RLVR methods.

Match reason: Ranked by recency.

• As wearable and mobile devices become increasingly embedded in daily life, they offer a practical way to continuously sense human motion in the wild.
• We introduce AnyMo, a geometry-aware framework for setup-agnostic human motion modeling.

Match reason: Ranked by recency.

• Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Match reason: Ranked by recency.

• First, we introduce a comprehensive benchmark of over 7,000 temporally grounded questions and an evaluation protocol that enables analysis of whether models correctly associate facts with their corresponding time periods.

Match reason: Ranked by recency.

• Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Match reason: Ranked by recency.

• Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Match reason: Ranked by recency.

• Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.