arXiv AI

One Model, Two Precisions: Does Disagreement Between Quantized Copies Tell You When a Small Model Is Wrong?

The paper investigates whether disagreement between two quantized versions of the same language model can serve as an error signal for tasks such as abstention and escalation. Using Qwen3-0.6B and Qwen3-1.7B, the authors compare an 8‑bit copy with lower‑precision copies (3–6 bits) on multiple-choice datasets, measuring error detection via AUROC, risk‑coverage, and ECE. Results show modest gains over entropy alone, with additional forward passes offering limited improvement, and the study provides a deployment recipe and discusses scenarios where the method is ineffective.

arXiv AI
6d ago

Bits or permutations? Spending a fixed inference budget on weight precision or on option-order averaging in small local language models

The study investigates how to best allocate a fixed inference budget between reducing weight precision (quantization) and averaging over different answer‑option orders in small local language models. Experiments on Qwen3‑0.6B and Qwen3‑1.7B show that 6‑bit quantization retains or even slightly improves accuracy compared to fp16, while 4‑bit quantization introduces significant answer‑slot skew. Averaging four cyclic option orders can recover a large accuracy gain at 4 bits, and cost‑matched analysis indicates that using 6‑bit weights plus up to four order averages is the most efficient strategy when the budget allows at least 6 bits per weight.

By Mohammed Nayeem Khan, Logesh L, Aliyas Ahmad Misri
arXiv AI
6d ago

Precision on Demand: Escalating Weight Bits at Uncertain Decoding Steps in a Small Local Model

The paper proposes a dynamic weight‑precision strategy for local decoding, storing 8‑bit weights but using only the top 4 bits during most steps and escalating to full precision when the low‑precision output distribution is uncertain (high entropy or small top‑two margin). Experiments on Qwen3‑0.6B with the GSM8K benchmark show that a 15% escalation budget captures 78% of low‑precision argmax flips, outperforming a random gate, and that an entropy gate at 16% escalation achieves 62.7% accuracy with only 0.87 of the weight‑byte cost of using all‑high precision. The study demonstrates that selective precision escalation can reduce computational cost while maintaining competitive performance.

By Mohammed Nayeem Khan, Logesh L, Aliyas Ahmad Misri
arXiv Machine Learning
Aug 13

LODESTAR: Trustworthy Entropy Is Navigated, Not Merely Measured -- Reinforced Polarizer Keeps a Frozen LLM from Being Confidently Misled by the Wrong Evidence

arXiv:2608. 11922v1 Announce Type: cross Abstract: Predictive-distribution entropy makes a strong selection rule in retrieval-augmented question answering: across five QA benchmarks, keeping the candidate answer that a frozen respondent LLM produces with the lowest answer-token entropy lifts mean answer $F_1$ from 0.

By Po-Jen Ko, Che-Cheng Wu, Hung-Chun Hsu, Li-Yang Chang, Chuan-Ju Wang
arXiv AI
Oct 27

ThinkBit: Search Codewords, Recalibrate Scales, Select by Reasoning

ThinkBit is a two‑bit scalar quantization framework designed to preserve reasoning capabilities in language models. It assigns each layer a ternary, 2‑bit, or 3‑bit tier based on sensitivity, then uses a Gumbel‑softmax search to find optimal codewords block‑by‑block. After freezing codewords, it recalibrates shared scales via knowledge‑distillation and performs a brief quantization‑aware training, finally selecting the best checkpoint with paired reasoning tests.

By Rhea Sanjay Sukthanker, Pashmina Cameron
arXiv AI
Sep 15

Option-Aware Retrieval and Task-Specific VLM Adaptation for Medical VQA

The paper presents a system for the MedReason 2026 challenge that tackles both multiple‑choice and open‑ended medical visual question answering using offline, containerized inference. Key findings include that comparing answer semantics rather than labels boosts retrieval‑only accuracy from 20.0 % to 57.5 % on a 200‑case holdout, and that varying the number of in‑prompt retrieved examples has minimal impact on final accuracy (93.5 %–94.0 %). The final system achieves 94.0 % MCQ accuracy on the development set and 93.20 % on the official pre‑evaluation, far surpassing the off‑the‑shelf baseline. "whyItMatters":"The results demonstrate that semantic‑aware retrieval and careful adapter tuning can dramatically improve medical VQA performance, offering a practical approach for high‑accuracy, offline inference in clinical settings."

By Tristan Kirscher (ICube, Institut Strauss), Niklas C. Koser (CAU), Soren Pirk (CAU)
arXiv AI
Oct 31

Neighborhood Elites: Quality-Diversity Search for Uncertainty Quantification in Question Answering

The paper introduces Neighborhood Elites (NE), a quality‑diversity search method for generating answer‑preserving rewrites in question answering. NE explicitly controls two dimensions—type of edit and explicitness of support—to create diverse perturbations that improve uncertainty quantification. Across five extractive‑QA datasets and five instruction‑tuned LLMs, NE outperforms other constructors, achieving higher AUROC and AUPRC scores and surpassing semantic entropy baselines.

By Mesut Ceylan, Arda Baris Basaran, Elgar Fleisch, Filipe Barata