Human Feedback and Eval Paper Explorer

Match reason: Matches selected tags (Pairwise Preference).

• Long-term memory is essential for conversational agents to maintain coherence, track persistent tasks, and provide personalized interactions across extended dialogues.
• Experiments on the LoCoMo benchmark show that HyperMem achieves state-of-the-art performance with 92.73% LLM-as-a-judge accuracy, demonstrating the effectiveness of HyperMem for long-term conversations.

Match reason: Matches selected tags (Pairwise Preference).

• Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing diverse human values.
• To bridge this gap, we introduce Personalized RewardBench, a novel benchmark designed to rigorously assess reward models' capacity to model personalized preferences.

Match reason: Matches selected tags (Pairwise Preference).

• We present the first study of SPB in rubric-based evaluation, an increasingly popular benchmarking paradigm where judges issue binary verdicts on individual evaluation criteria, instead of assigning holistic scores or rankings.
• Using IFEval, a benchmark with programmatically verifiable rubrics, we show that SPB persists even when evaluation criteria are entirely objective: among rubrics where generators fail, judges can be up to 50\% more likely to incorrectly…

Match reason: Matches selected tags (Pairwise Preference).

• Experiments on the MMEB-V2 benchmark demonstrate that our model achieves a score of 71.2 with only 4B parameters, establishing a new state-of-the-art while significantly reducing reasoning overhead and inference latency.

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

• A board-certified radiologist and a radiology resident independently performed blinded pairwise evaluations across 4 criteria: terminology accuracy, readability, overall quality, and radiologist-style authenticity.
• Radiologist 2 rated readability as equivalent in 75% of cases and favored the human-edited translation for overall quality (40% vs 21%).

Match reason: Matches selected tags (Pairwise Preference).

• However, current reranking models are typically optimized on static human annotated relevance labels in isolation, decoupled from the downstream generation process.
• To bridge this gap, we introduce ReRanking Preference Optimization (RRPO), a reinforcement learning framework that directly aligns reranking with the LLM's generation quality.

Match reason: Matches selected tags (Pairwise Preference).

• Preference learning in Large Language Models (LLMs) has advanced significantly, yet existing methods remain limited by modest performance gains, high computational costs, hyperparameter sensitivity, and insufficient modeling of global…
• We introduce PLOT, which enhances Preference Learning in fine-tuning-based alignment through a token-level loss derived from Optimal Transport.

Match reason: Matches selected tags (Pairwise Preference).

• Unlike standard preference optimization which applies broad penalties, Self-Debias employs a fine-grained trajectory-level objective subject to dynamic debiasing constraints.

Match reason: Matches selected tags (Pairwise Preference).

• Recent progress spans supervised fine-tuning (SFT), preference optimization, reinforcement learning (RL), process supervision, verifier-guided methods, distillation, and multi-stage pipelines.
• SFT may serve either support expansion or policy reshaping, whereas preference-based methods are usually off-policy reshaping.

Match reason: Matches selected tags (Pairwise Preference).

• Personalized large language models (PLLMs) have garnered significant attention for their ability to align outputs with individual's needs and preferences.
• Extensive evaluations on long-horizon benchmarks using the Qwen-3 model family (4B to 32B) validate the effectiveness of TSUBASA, surpassing competitive memory-augmented systems that rely primarily on memory writing, such as Mem0 and…

Match reason: Matches selected tags (Pairwise Preference).

• Large language models (LLMs) are increasingly used as automated evaluators (LLM-as-a-Judge).
• Using a counterfactual design, we find that both humans and LLM judges assign higher trust to information labeled as human-authored than to the same content labeled as AI-generated.

Match reason: Matches selected tags (Pairwise Preference).

• Specifically, DRCR employs two complementary feedback signals, discourse coherence and response quality, to construct preference data for both context rewriting and response generation.

Match reason: Matches selected tags (Pairwise Preference).

• Our empirical analysis reveals that off-the-shelf LLMs and standard alignment techniques, including prompt engineering and Direct Preference Optimization, fail to reliably control output distributions.

Match reason: Matches selected tags (Pairwise Preference).

• JoyAI-LLM Flash is pretrained on a massive corpus of 20 trillion tokens and further optimized through a rigorous post-training pipeline, including supervised fine-tuning (SFT), Direct Preference Optimization (DPO), and large-scale…

Match reason: Matches selected tags (Pairwise Preference).

• Today's large language models (LLMs) are trained to align with user preferences through methods such as reinforcement learning.
• We then present a suite of evaluations to examine how current models handle these tradeoffs.

Match reason: Matches selected tags (Pairwise Preference).

• To address this issue, we propose Multi-Faceted Self-Consistent Preference Aligned CQR (MSPA-CQR).
• Then we propose prefix guided multi-faceted direct preference optimization to learn preference information from three different dimensions.

Match reason: Matches selected tags (Pairwise Preference).

• We introduce distinctiveness, a representation-level measure that evaluates how each learner differs from others in the cohort using pairwise distances, without requiring clustering, labels, or task-specific evaluation.
• Using student-authored questions collected through a conversational AI agent in an online learning environment, we compare representations based on individual questions with representations that aggregate patterns across a student's…

Match reason: Matches selected tags (Pairwise Preference).

• Large language models achieve strong performance on many language tasks, yet it remains unclear whether they integrate world knowledge with syntactic structure in a human-like, structure-sensitive way during ambiguity resolution.
• In a speeded forced-choice comprehension experiment, humans show a large, correctly directed plausibility effect.

Match reason: Matches selected tags (Pairwise Preference).

• Reinforcement Learning from Human Feedback (RLHF), using algorithms like Proximal Policy Optimization (PPO), aligns Large Language Models (LLMs) with human values but is costly and unstable.
• However, these methods still require voluminous data to learn preferences and may weaken the generalization ability of LLMs.