Human Feedback and Eval Paper Explorer

Match reason: Matches selected tags (Law, Pairwise Preference).

• In agentic workflows, LLMs frequently process retrieved contexts that are legally protected from further training.
• The framework instruments preference data by pairing document triggers with feedback that rewards a distinctive stylistic response, inducing a latent trigger-conditioned preference if such data are used in training.

Match reason: Matches selected tags (Law, Pairwise Preference).

• Via the trigonometric series, we use the distance preference characterized by these centers to score keys according to their positions, and also leverage Q/K norms as an additional signal for importance estimation.

Match reason: Matches selected tags (Law, Pairwise Preference).

• We further demonstrate that constructing DPO preference pairs from NSRSA verification teaches the model to distinguish sound from flawed reasoning (reward accuracy 46% to 63%).

Match reason: Matches selected tags (Law, Pairwise Preference).

• 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…

Match reason: Matches selected tags (Law, Pairwise Preference).

• Realizing this agent requires overcoming significant challenges in data supervision, objective collapse, and evaluation bias.
• We address these issues by introducing the PersonaKnob dataset which features a compositional partial order structure of multiple persona preference.

Match reason: Matches selected tags (Law, Pairwise Preference).

• Large language model (LLM) agents are moving beyond prompting alone.
• ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool use, and OpenClaw highlights a newer direction in which agents…

Match reason: Matches selected tags (Law, Pairwise Preference).

• In blind pairwise evaluations by 28 MFA-trained readers and 516 college-educated general readers, AI text from in-context prompting was strongly disfavored by MFA readers for stylistic fidelity (OR=0.16) and quality (OR=0.13), while general…
• Fine-tuning ChatGPT on authors' complete works reversed these results: MFA readers favored AI for fidelity (OR=8.16) and quality (OR=1.87), with general readers showing even stronger preference (fidelity OR=16.65; quality OR=5.42).

Match reason: Matches selected tags (Law, Pairwise Preference).

Match reason: Matches selected tags (Law, Pairwise Preference).

• By sampling annotators from police-affiliated, justice-system-impacted, and non-affiliated Los Angeles residents, we enable the systematic study of perceptual differences across diverse communities.
• To this end, we (i) develop a domain-specific evaluation rubric grounded in procedural justice theory, LAPD training materials, and extensive fieldwork; (ii) introduce a rubric-driven preference data construction framework for…

Match reason: Matches selected tags (Law, Pairwise Preference).

• Game-theoretic interactions between agents with Large Language Models (LLMs) have revealed many emergent capabilities, yet the linguistic diversity of these interactions has not been sufficiently quantified.
• In this paper, we present the Conversational Robustness Evaluation Score: CORE, a metric to quantify the effectiveness of language use within multi-agent systems across different game-theoretic interactions.

Match reason: Matches selected tags (Law, Pairwise Preference).

Match reason: Matches selected tags (Law, Pairwise Preference).

• inward (community) contact suggests that α can be interpreted as an index of the preference for outward-oriented communication.