Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

4386128171 · May 202619922001200920172026
48 results for LLM alignment

Inference-aware meta-alignment of LLMs reduces computational cost.

problem Aligning LLMs to diverse human preferences is challenging due to conflicting criteria.
method IAMA trains a base model to be aligned to multiple tasks via different inference-time alignment algorithms, using non-linear GRPO for optimization.
result IAMA enables effective alignment of LLMs to multiple criteria with limited computational budget.

The paper explores game-theoretic alignment of LLMs with human preferences, finding limitations and conditions.

problem Aligning LLMs with human preferences using game theory.
method Systematic study of payoff choices in a two-player zero-sum game for desirable alignment properties.
result Impossibility of preference matching in game-theoretic LLM alignment under standard assumptions.

Paper explores limits and possibilities of aligning LLMs with human preferences.

problem Aligning LLMs with diverse human preferences to ensure fairness and informed outcomes.
method Analysis of probabilistic representation of human preferences and preservation of diverse preferences.
result LLMs can't fully align with human preferences using reward-based approaches due to Condorcet cycles, but mixed strategies are statistically possible.

A new method reduces preference distortion in LLM alignment.

problem Vulnerability of traditional LLM alignment methods to human preference heterogeneity.
method Sign Estimator: A simple, provably consistent, and efficient estimator using binary classification loss.
result Substantially reduces preference distortion over a panel of simulated personas.

Study compares DSPy teleprompter algorithms for aligning LLM evaluations with human annotations.

problem Aligning LLM evaluation metrics with human annotations.
method Comparative analysis of five teleprompter algorithms within the DSPy framework.
result Certain teleprompters outperform others in detecting hallucinations.

The paper addresses poor calibration in fine-tuned LLMs after preference alignment.

problem Poor calibration in fine-tuned Large Language Models (LLMs) after preference alignment.
method Proposes a calibration-aware fine-tuning approach to restore calibration without compromising model performance.
result Demonstrates the effectiveness of the proposed methods through extensive experiments.

DPA aligns LLMs with multi-objective rewards for diverse user preferences.

problem Fine-grained control over LLMs for diverse user needs.
method Integrates multi-objective reward modeling and directional preference control.
result DPA offers better performance trade-offs and intuitive user control over LLM generation.

Framework controls uncertainty in LLMs without labels or probabilities.

problem Managing uncertainty in black-box LLMs without token-level probability or true labels.
method Integrates generative models, UCP, and conformal alignment to control uncertainty.
result Achieves close-to-nominal coverage and tighter thresholds than split UCP.

Study examines if LLMs' trading styles match real market behavior.

problem Lack of behavioral consistency in LLMs' trading strategies.
method Year-long simulations with LLMs, operationalizing behavioral finance drivers, and comparing with financial theory.
result LLMs' strategy switching is only partially consistent with behavioral finance theories.

New RLHF approach mitigates bias in aligning LLMs with human preferences.

problem Algorithmic bias in RLHF leading to preference collapse.
method Preference Matching (PM) RLHF, using PM regularizer and conditional variant.
result 29% to 41% improvement in alignment with human preferences.

Direct Density Ratio Optimization aligns LLMs with human preferences without assuming specific models.

problem Statistical inconsistency in aligning LLMs with human preferences.
method Direct Density Ratio Optimization (DDRO) estimates density ratio directly.
result DDRO is statistically consistent, converging to true human preferences as data grows.

Auto-CEI improves LLM reasoning by balancing assertiveness and conservativeness.

problem Hallucinations and laziness in LLM reasoning tasks.
method Expert Iteration explores reasoning trajectories, guiding incorrect paths back on track and promoting appropriate 'I don't know' responses.
result Auto-CEI achieves superior alignment in logical reasoning, mathematics, and planning tasks.

Faster WIND accelerates iterative BOND for LLM alignment.

problem Iterative BOND is inefficient in practice due to sample and computation inefficiency.
method Unified game-theoretic connection to self-play alignment, WIND framework with efficient algorithms.
result WIND variant achieves superior sample efficiency and faster computation.

FLARKO uses LLMs, KGs, and KTO to generate profitable, behaviorally aligned financial recommendations.

problem Financial recommendation systems often fail to account for behavioral and regulatory factors.
method FLARKO integrates LLMs, KGs, and KTO to generate profitable and behaviorally aligned recommendations.
result FLARKO consistently outperforms state-of-the-art recommendation baselines on behavioral alignment and joint profitability.

LLM evaluation suffers from systematic biases and lacks reliable positive judgments.

problem LLM evaluation suffers from systematic biases and lacks reliable positive judgments.
method Formulate LLM evaluation as a positive-unlabelled learning problem and propose a geometric auditing framework based on Partial Optimal Transport.
result Improved alignment with human preferences, increased robustness to presentation biases, and interpretable confidence estimates.

The paper introduces Relative Bias to quantify LLM bias systematically.

problem Quantifying bias in LLMs is challenging due to ambiguity and rapid model emergence.
method Relative Bias framework using Embedding Transformation and LLM-as-a-Judge methodologies.
result The two scoring methods show strong alignment, providing a systematic approach.

New benchmark uncovers hidden biases in LLMs that refuse to answer certain queries.

problem Evaluating fairness in LLMs, especially in sensitive applications.
method Silenced Bias Benchmark (SBB) using activation steering to reduce model refusals during QA.
result Exposes hidden unfair preferences in LLMs' latent space, distinguishing direct responses from underlying fairness issues.

Extends reinforcement learning alignment to scalar rewards, improving math reasoning.

problem Designing reinforcement learning algorithms for general LLM alignment.
method Introduces f-GRPO and f-HAL, estimating f-divergences between reward-aligned and unaligned distributions.
result Improves math reasoning RLVR tasks and mitigates reward hacking.

Method tackles uncertainty in reward models for LLMs from heterogeneous human feedback.

problem Uncertainty in reward models for LLMs from heterogeneous human feedback.
method Heterogeneous preference framework and alternating gradient descent algorithm.
result Established theoretical guarantees for estimator convergence and asymptotic distribution.

Study reveals LLM personality patterns but lacks behavioral consistency.

problem Understanding and validating personality traits in LLMs.
method Characterized LLM personality across three dimensions: training dynamics, self-report validity, and intervention effects.
result Self-reported traits do not reliably predict behavior, and instructional alignment affects trait expression but not behavior.

Shorter adversarial prompts help protect LLMs from jailbreak attacks.

problem Protecting large language models from jailbreak attacks with long adversarial suffixes.
method Adversarial training on shorter adversarial suffixes to defend against longer adversarial suffixes.
result Aligning LLMs on shorter adversarial suffixes can effectively defend against jailbreak attacks with longer suffixes.

New research shows label refinement and weak training have limitations for aligning LLMs.

problem Limitations of refinement methods for aligning large language models.
method Analyzed probabilistic assumptions and alternative approaches to label refinement and weak training.
result Label refinement and weak training suffer from irreducible error, leaving a performance gap.

New framework assesses LLMs' expertise using nonparametric ranking and confidence diagrams.

problem Evaluating and ranking large language models (LLMs) for alignment and performance.
method Nonparametric contextual ranking, confidence diagram, Gaussian multiplier bootstrap.
result Validated confidence diagram for assessing LLMs' domain-specific expertise.

Enhances stock return prediction using LLMs and hybrid models.

problem Insufficient use of semantic information and alignment of LLMs with stock features.
method LG model with three strategies for global information modeling and SCRL for embedding alignment.
result Superior performance in Rank Information Coefficient and returns compared to models relying only on stock features.

LLMs struggle with zero-shot annotation tasks due to model-internalized priors.

problem Impact of model-internalized priors on LLM performance in zero-shot annotation tasks.
method Investigated three dimensions: familiarity, decision stickiness, and susceptibility to misaligned task definitions.
result Nearly two-thirds of zero-shot errors are resistant to correction, with a rescue rate of 34.8%. Definition-Specific Familiarity (DSF) shows a positive association with model performance.

SAIL improves online alignment of large language models with minimal feedback.

problem Offline RLHF methods often lead to sub-optimal performance due to fixed preference datasets.
method SAIL uses bilevel optimization and a single-level first-order method to iteratively refine model alignment.
result SAIL significantly improves alignment performance on open-sourced datasets with minimal computational overhead.

COCA refactors training data to identify and erase unsafe concepts in LLMs.

problem Identifying and erasing unsafe concepts in Large Language Models (LLMs) for safety alignment.
method Concept Concentration (COCA) refactors training data with an explicit reasoning process to identify and erase unsafe concepts.
result COCA significantly reduces both in-distribution and out-of-distribution jailbreak success rates while maintaining strong performance on regular tasks.

DRO-REBEL improves LLM alignment by robustly updating models online.

problem Overfitting and drifting of LLMs during RLHF.
method DRO-REBEL uses type-pp Wasserstein, KL, and χ2χ^2 ambiguity sets for robust online updates.
result DRO-REBEL achieves faster convergence and better performance than prior methods.

ELS framework improves safety alignment by dynamically steering LLMs towards helpful responses.

problem Over-Refusal in Aligned Large Language Models
method Fine-tuning free framework using an Energy-Based Model (EBM) to dynamically steer LLMs during inference.
result Extensive experiments show a significant reduction in false refusals (from 57.3% to 82.6%) while maintaining safety performance.